WO2019140950A1 - 一种车辆定位的方法以及车辆定位装置 - Google Patents
一种车辆定位的方法以及车辆定位装置 Download PDFInfo
- Publication number
- WO2019140950A1 WO2019140950A1 PCT/CN2018/108329 CN2018108329W WO2019140950A1 WO 2019140950 A1 WO2019140950 A1 WO 2019140950A1 CN 2018108329 W CN2018108329 W CN 2018108329W WO 2019140950 A1 WO2019140950 A1 WO 2019140950A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- information
- target
- vehicle
- stationary
- road
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 92
- 238000005259 measurement Methods 0.000 claims abstract description 193
- 230000003068 static effect Effects 0.000 claims abstract description 76
- 230000006641 stabilisation Effects 0.000 claims description 43
- 238000011105 stabilization Methods 0.000 claims description 43
- 230000004927 fusion Effects 0.000 claims description 41
- 238000004364 calculation method Methods 0.000 claims description 37
- 238000001514 detection method Methods 0.000 claims description 29
- 238000013519 translation Methods 0.000 claims description 17
- 238000005452 bending Methods 0.000 claims description 10
- 230000000087 stabilizing effect Effects 0.000 claims 2
- 238000013461 design Methods 0.000 description 47
- 238000010586 diagram Methods 0.000 description 31
- 238000012545 processing Methods 0.000 description 22
- 230000008569 process Effects 0.000 description 18
- 230000006870 function Effects 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000001965 increasing effect Effects 0.000 description 5
- 230000001788 irregular Effects 0.000 description 5
- 238000004590 computer program Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000007726 management method Methods 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000005236 sound signal Effects 0.000 description 2
- 125000000205 L-threonino group Chemical group [H]OC(=O)[C@@]([H])(N([H])[*])[C@](C([H])([H])[H])([H])O[H] 0.000 description 1
- 241000699670 Mus sp. Species 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012905 input function Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000003137 locomotive effect Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000010079 rubber tapping Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010897 surface acoustic wave method Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000004804 winding Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3602—Input other than that of destination using image analysis, e.g. detection of road signs, lanes, buildings, real preceding vehicles using a camera
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/28—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network with correlation of data from several navigational instruments
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/36—Input/output arrangements for on-board computers
- G01C21/3626—Details of the output of route guidance instructions
- G01C21/3658—Lane guidance
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/66—Radar-tracking systems; Analogous systems
- G01S13/72—Radar-tracking systems; Analogous systems for two-dimensional tracking, e.g. combination of angle and range tracking, track-while-scan radar
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/86—Combinations of radar systems with non-radar systems, e.g. sonar, direction finder
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/87—Combinations of radar systems, e.g. primary radar and secondary radar
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/254—Fusion techniques of classification results, e.g. of results related to same input data
- G06F18/256—Fusion techniques of classification results, e.g. of results related to same input data of results relating to different input data, e.g. multimodal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/809—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data
- G06V10/811—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of classification results, e.g. where the classifiers operate on the same input data the classifiers operating on different input data, e.g. multi-modal recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/588—Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/932—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles using own vehicle data, e.g. ground speed, steering wheel direction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
- G01S2013/93271—Sensor installation details in the front of the vehicles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/93—Radar or analogous systems specially adapted for specific applications for anti-collision purposes
- G01S13/931—Radar or analogous systems specially adapted for specific applications for anti-collision purposes of land vehicles
- G01S2013/9327—Sensor installation details
- G01S2013/93274—Sensor installation details on the side of the vehicles
Definitions
- the present application relates to the field of signal processing technologies, and in particular, to a method for positioning a vehicle and a vehicle positioning device.
- vehicle positioning mainly relies on global position system (GPS), real-time kinematic (RTK), camera and laser radar.
- GPS global position system
- RTK real-time kinematic
- a common vehicle positioning method is to comprehensively pre-store maps, GPS position information and millimeter wave measurement information to determine the possible location of the vehicle, and calculate the probability of occurrence of the location of the vehicle, thereby determining the specific location of the vehicle.
- the forward radar coverage angle installed on the vehicle is usually narrow, so it is difficult to accurately estimate the positional relationship between the vehicle and the surrounding target on an unstructured road (such as a road such as a winding lane), thereby reducing The accuracy of vehicle positioning.
- the present application provides a method for locating a vehicle and a vehicle locating device, which can locate the central city, the tunnel and the irregular road, improve the confidence and reliability of the positioning, and further improve the vehicle planning control through the road curvature information.
- System to plan the vehicle's driving trajectory.
- the first aspect of the present application provides a method for locating a vehicle, which can solve the problem of advanced assisted driving and automatic driving lane level positioning in the case of a central city, a tunnel, and an irregular road, thereby assisting in better completion.
- Vehicle planning control The method for positioning a vehicle may specifically include the following steps:
- the vehicle positioning device acquires measurement information within a preset angle range by the measurement device, wherein the measurement information includes a plurality of static target information, and the plurality of stationary target information are used to represent information of a plurality of stationary targets,
- the stationary target information is in one-to-one correspondence with the information of a plurality of stationary targets.
- the stationary target can be an object that does not move freely, such as a roadside tree, a guardrail, or a traffic light.
- the vehicle positioning device determines current road boundary information corresponding to the current frame time according to the measurement information, and then determines first target positioning information according to the current road boundary information, where the first target positioning information is used to indicate that the target vehicle is located in the road. s position. For example, it can be expressed as the third lane from the left to the right of the six lanes at the current time.
- the vehicle positioning device determines road curvature information based on the current road boundary information and the historical road boundary information, wherein the road curvature information is used to indicate the degree of curvature of the road where the target vehicle is located, and the historical road boundary information includes at least one road boundary corresponding to the historical frame time.
- the historical frame time is the time at which the road boundary information and the road curvature information are acquired before the current frame time. Combining the information of the current frame time and the historical frame time to calculate, fully consider the driving situation of the self-vehicle for a period of time, so that the obtained result has stronger reliability.
- the vehicle positioning device outputs the first target positioning information and the road curvature information through the output device.
- the measuring equipment will perform active measurement, it is less affected by the light climate in the visible range. Under the central city, tunnel culvert and non-ideal meteorological conditions, the positional relationship between the vehicle and the surrounding targets can be obtained by using the measuring equipment. Thereby determining the positioning information of the vehicle in the road, thereby improving the confidence and reliability of the positioning information. In addition, road curvature information is determined by these positional relationships, which can estimate the curvature of the lane in which the vehicle is located, thereby improving the accuracy of vehicle positioning. Achieve better vehicle planning control in advanced assisted driving or automatic driving lane level positioning.
- the vehicle positioning device acquires the measurement information in the preset angle range by using the measurement device, and may include the following steps:
- the tracking information of the plurality of stationary targets in the preset angle range is acquired by the vehicle positioning device through the millimeter wave radar, wherein the tracking information includes position information and speed information of the plurality of stationary targets in the radar coordinate system, and then according to the tracking information and
- the calibration parameters of the millimeter wave radar calculate measurement information, wherein the measurement information includes position information and speed information of a plurality of stationary targets in a vehicle coordinate system, and the calibration parameters include a rotation amount and a translation amount.
- the radar coordinate system is a coordinate system for acquiring tracking information
- the vehicle coordinate system is a coordinate established with the target vehicle as an origin.
- the millimeter wave radar has a very wide frequency band and is suitable for various wideband signal processing. It also has angle resolution and tracking capability, and has wide Doppler broadband, obvious Doppler effect, good Doppler resolution, and millimeter wave.
- the radar wavelength is short, and the scattering characteristics of the target are described accurately, finely and with high speed measurement accuracy.
- the preset angle range includes a first preset angle range and a second preset angle range
- the vehicle positioning device acquires the tracking information of the plurality of stationary targets in the preset angle range by using the millimeter wave radar, and may include the following steps:
- the vehicle positioning device acquires first tracking information of the plurality of first stationary targets in the first preset angle range by using the first millimeter wave radar, and acquires the second second stationary targets in the second preset angle range by using the second millimeter wave radar Second tracking information, wherein the tracking information comprises first tracking information and second tracking information, the plurality of stationary targets comprising a plurality of first stationary targets and a plurality of second stationary targets, the millimeter wave radar comprising a first millimeter wave radar and In the second millimeter wave radar, the detection distance and the coverage angle of the first millimeter wave radar are different from the detection distance and coverage angle of the second millimeter wave radar.
- the coverage of the second millimeter wave radar is larger than the coverage of the first millimeter wave radar, because the farther the detection distance is, the smaller the coverage is. Conversely, if the detection distance of the first millimeter wave radar is smaller than the detection distance of the second millimeter wave, the coverage of the second millimeter wave radar is smaller than the coverage of the first millimeter wave radar, because the closer the detection distance is, the more the coverage is. Big.
- the vehicle positioning device calculates the measurement information according to the tracking information and the calibration parameters of the millimeter wave radar, and may include the following steps:
- the vehicle positioning device calculates the first measurement information in the first preset angle range according to the first tracking information and the calibration parameter of the millimeter wave radar, and calculates the second preset angle range according to the second tracking information and the calibration parameter of the millimeter wave radar.
- the second measurement information wherein the measurement information includes the first measurement information and the second measurement information.
- the first millimeter wave radar and the second millimeter wave radar can be used to obtain different measurement information, and the information acquisition manner does not require high-cost real-time dynamic positioning, large data volume image or point cloud information. It mainly relies on the information of millimeter wave radar. With 5 millimeter wave radars, each radar can output up to 32 targets as an example. The data volume is only a few hundred kilobytes per second, which is much smaller than the visual image and the laser point cloud. .
- the vehicle positioning device may calculate the measurement information by:
- V xc , V yc R ⁇ (V xr , V yr );
- (x c , y c ) represents the position information of the stationary target in the vehicle coordinate system
- x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system.
- (x r , y r ) represents the position information of the stationary target in the radar coordinate system
- x r represents the horizontal axis coordinate of the stationary target in the radar coordinate system
- y r represents the vertical axis coordinate of the stationary target in the radar coordinate system
- R represents the amount of rotation
- T represents the amount of translation
- (V xc , V yc ) represents the velocity information of the stationary target in the vehicle coordinate system
- V xc represents the velocity of the stationary target in the horizontal axis direction of the vehicle coordinate system
- V yc represents the stationary target.
- the velocity in the vertical axis direction (V xr , V yr ) represents the velocity information of the stationary target in the radar coordinate system
- V xr represents the velocity of the stationary target in the horizontal axis direction of the radar coordinate system
- V yr represents The velocity of the stationary target in the direction of the longitudinal axis of the radar coordinate system.
- the measurement information in the radar coordinate system can be converted into the measurement information in the vehicle coordinate system, and the position information and the speed information are respectively converted, so that the perspective of the vehicle can be taken from the perspective of the vehicle.
- the positioning of the vehicle is completed, which improves the feasibility of the scheme.
- the vehicle positioning device determines the road curvature information according to the road boundary information and the historical road boundary information, and may include the following steps:
- the vehicle positioning device calculates the occupation probability of each grid unit in the grid area according to the road boundary information and the historical road boundary information, wherein the grid area covers the target vehicle, the grid area tracks the target vehicle, and the grid area includes Multiple grid cells. Then, the vehicle positioning device acquires a probability raster map according to the occupation probability of each grid unit in the grid area, and then determines the fusion boundary information by the target grid unit in the probability raster map, wherein the occupancy probability of the target grid unit Greater than the preset probability threshold, in general, the occupancy probability of the target grid unit approaches 1. Finally, the vehicle positioning device calculates road curvature information based on the fusion boundary information.
- the vehicle positioning device may calculate the occupation probability of each grid unit by:
- p n (x c , y c ) min(p(x c , y c )+p n-1 (x c , y c ), 1);
- p n (x c , y c ) represents the occupation probability of n-frame raster cells
- p(x c , y c ) represents road boundary information
- p n-1 (x c , y c ) represents n-1 frames
- x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system
- (x c , y c ) represents the stationary target in the vehicle coordinate system
- the lower position information, (x c , y c )' represents the average value of the position information of the multi-frame stationary target in the vehicle coordinate system
- S represents the covariance of x c and y c .
- the static target information acquired by the millimeter wave radar can be used for local positioning, and the road boundary information solved by the history and the currently solved road boundary information are used for weighted average, thereby obtaining stable road boundary information, so as to obtain stable road boundary information, The reliability of this upgrade program.
- the vehicle positioning device may calculate road curvature information by:
- Q represents the road curvature information, g ⁇ (x c) represented by fusion boundary information, g ⁇ '(x c) represented by the first derivative of g ⁇ (x c) a, g ⁇ "(x c) represented by g ⁇ (x The second derivative of c ).
- the vehicle positioning device may perform the following steps before determining the current road boundary information corresponding to the current frame time according to the measurement information. :
- the vehicle positioning device acquires the candidate stationary target information and the M reference stationary target information from the measurement information, wherein M is an integer greater than 1, and generally 5 reference stationary target information can be selected. Then, the average distance between the M reference stationary target information and the candidate stationary target information is calculated, assuming that there are 5 reference stationary targets, and the averaged distance is calculated according to the distance of each reference stationary target to the candidate stationary target.
- the vehicle positioning device will remove the candidate stationary target information from the measurement information.
- the candidate stationary target information is any one of a plurality of static target information
- the reference stationary target information is static target information in which the distance between the plurality of stationary target information and the candidate stationary target information is less than the distance preset value.
- the to-be-selected still target information that does not satisfy the preset static target condition can be eliminated, and the static target information that meets the requirement is left for performing subsequent positioning calculation and road boundary information calculation.
- the accuracy of the calculation can be effectively improved.
- the vehicle positioning device may calculate the average distance by:
- d denotes the average distance
- M denotes the number of reference still information
- P denotes the position information of the still target information to be selected
- P i denotes the position information of the i-th reference still information
- i is greater than 0 and less than or equal to M Integer.
- the vehicle positioning device if the average distance does not satisfy the preset stationary target condition, the vehicle positioning device removes the candidate stationary target information from the measurement information. , can include the following steps:
- the vehicle positioning device determines that the average distance does not satisfy the preset stationary target condition, and then the candidate stationary target information is removed from the measurement information.
- the to-be-selected still target information whose average distance is greater than the threshold threshold can be eliminated, and the static target information that meets the requirement is left for performing subsequent positioning calculation and road boundary information calculation. In the above manner, the accuracy of the calculation can be effectively improved.
- the vehicle positioning device may calculate the road boundary information by:
- f ⁇ (x c ) represents road boundary information
- ⁇ 0 represents the first coefficient
- ⁇ 1 represents the second coefficient
- ⁇ 2 represents the third coefficient
- ⁇ 3 represents the fourth coefficient
- x c represents the stationary target in the vehicle coordinate system.
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system
- (x c , y c ) represents the position information of the stationary target in the vehicle coordinate system
- ⁇ represents the regular term coefficient
- ⁇ j represents the j coefficients
- j is an integer greater than or equal to 0 and less than or equal to 3.
- the vehicle positioning device determines the first target positioning information according to the road boundary information corresponding to the current frame time, and may include the following step:
- the vehicle positioning device calculates the stabilization boundary information of the current frame time according to the current road boundary information and the historical road boundary information, and then acquires the first distance of the target vehicle to the left boundary of the road according to the stabilization boundary information of the current frame time, and The second distance from the target vehicle to the right side boundary of the road, and finally the vehicle positioning device calculates the first target positioning information of the current frame time according to the first distance and the second distance.
- the relationship between the stabilization boundary information and the fusion boundary information is like the relationship between "line” and "face", and multiple stabilization boundary information can obtain a fusion boundary information.
- the fusion boundary information of the current frame time can be calculated according to the road boundary information corresponding to the current frame time and the historical road boundary information, and the vehicle is obtained according to the fusion boundary information of the current frame time to the left boundary of the road.
- the vehicle positioning device can calculate the stabilization boundary information corresponding to the current frame moment by:
- f ⁇ ' represents the stabilization boundary information corresponding to the current frame time
- f ⁇ _w (x c ) represents the historical road boundary information corresponding to the wth frame
- W represents the number of historical road boundary information
- x c represents the stationary target In the horizontal coordinate of the vehicle coordinate system
- ⁇ represents the average of the lane boundaries of the W frame.
- a method for calculating the stabilization boundary information is introduced, and the fusion boundary information calculated by the method has good reliability and is operable.
- the vehicle positioning apparatus may calculate the first target positioning information of the current frame moment by:
- Location represents the first target location information of the current frame time
- ceil represents the upward rounding calculation mode
- R L represents the first distance of the target vehicle to the left boundary of the road
- R R represents the target vehicle to the right boundary of the road.
- the second distance, D represents the width of the lane
- N represents the number of lanes.
- a method for calculating the first target positioning information is introduced, and the first target positioning information calculated by the method has good reliability and is operable.
- the measurement information may further include at least one moving target information, where the vehicle positioning device determines the first target according to the current road boundary information.
- the vehicle positioning device acquires at least one moving target information from the measurement information, wherein each moving target information carries a target number, and the target number is used to calibrate different moving targets, and the moving target generally refers to a vehicle that moves on the road.
- each moving target information carries a target number
- the target number is used to calibrate different moving targets
- the moving target generally refers to a vehicle that moves on the road.
- it can also be a bicycle, a motorcycle or other type of locomotive.
- the vehicle positioning device determines the lane occupying information according to the at least one moving target information and the corresponding historical moving target information, and finally determines the second target positioning information corresponding to the current frame moment according to the lane occupying information, wherein the second target positioning information is used for Indicates where the target vehicle is located on the road.
- a plurality of stationary target information and moving target information are simultaneously acquired by the millimeter wave radar, and the road boundary information is calculated by combining the two to realize the positioning of the vehicle.
- the moving target information can assist the static target information to calculate the road boundary information, so that the vehicle positioning can be accurately completed when the traffic volume is large, thereby improving the feasibility and flexibility of the solution, and increasing the confidence of the positioning. degree.
- the vehicle positioning device determines the lane occupancy information according to the at least one moving target information of the current frame time and the corresponding historical moving target information.
- the vehicle positioning device acquires K-frame moving target information data according to at least one moving target information and historical moving target information corresponding to the at least one moving target information, wherein K is a positive integer, and then according to at least one moving target information and at least one moving target
- the historical moving target information corresponding to the information acquires a case where the L kth lane is occupied in the k frame, where k is an integer greater than 0 and less than or equal to K;
- the vehicle positioning device may determine that the L k lanes are occupied, wherein the lane occupancy ratio is a ratio of k frames to K frames. On the other hand, if the lane occupancy ratio is greater than or equal to the preset ratio, the vehicle positioning device may determine that the L k lanes are not occupied, and may determine the unoccupied L k lanes as the second corresponding to the current frame moment. Targeting information.
- the K-frame moving target information data is acquired according to the at least one moving target information of the current frame time and the at least one moving target information and the corresponding historical moving target information, and the moving target information and the history according to the current frame time are obtained.
- the moving target information acquires a case where the L kth lane is occupied in the k images.
- the vehicle positioning device determines the first target positioning information according to the road boundary information corresponding to the current frame time, and may include the following step:
- the vehicle positioning device first determines the confidence of the first target positioning information according to the second target positioning information, wherein the confidence is used to indicate the degree of trust of the first target positioning information, and the confidence may be expressed as a percentage. The vehicle positioning device then determines the first target positioning information of the current time based on the confidence.
- the positioning can be performed again or an alarm notification can be triggered.
- the second target positioning information determined by the moving target information can be used to determine the confidence level of the first target positioning information, and the confidence level indicates the degree of the segment estimation, thereby improving the feasibility of the fusion positioning. And practicality.
- a second aspect of the present application provides a vehicle positioning apparatus, which may include:
- An acquiring module configured to acquire measurement information in a preset angle range by using a measurement device, where the measurement information includes a plurality of static target information, and the plurality of static target information is used to represent information of multiple stationary targets,
- the static target information is in one-to-one correspondence with the information of the plurality of stationary targets;
- a determining module configured to determine, according to the measurement information acquired by the acquiring module, current road boundary information corresponding to the current frame time;
- a determining module configured to determine first target positioning information according to current road boundary information, where the first target positioning information is used to indicate a location where the target vehicle is located in the road;
- a determining module configured to determine road curvature information according to current road boundary information and historical road boundary information, wherein the road curvature information is used to indicate a degree of bending of the road where the target vehicle is located, and the historical road boundary information includes at least one road corresponding to the historical frame time
- the boundary information, the historical frame time is the time when the road boundary information and the road curvature information are acquired before the current frame time;
- an output module configured to output first target positioning information determined by the determining module and determine road curvature information determined by the module.
- the acquiring module is specifically configured to acquire tracking information of a plurality of stationary targets in a preset angle range by using a millimeter wave radar, wherein the tracking information includes position information and speed information of the plurality of stationary targets in the radar coordinate system;
- the measurement information is calculated according to the tracking information and the calibration parameters of the millimeter wave radar, wherein the measurement information includes position information and speed information of the plurality of stationary targets in the vehicle coordinate system, and the calibration parameters include the rotation amount and the translation amount.
- the preset angle range includes a first preset angle range and a second preset angle range
- the acquiring module is configured to acquire, by using the first millimeter wave radar, first tracking information of the plurality of first stationary targets in the first preset angle range, and acquire a plurality of second preset angle ranges by using the second millimeter wave radar Second tracking information of the stationary target, wherein the tracking information comprises first tracking information and second tracking information, the plurality of stationary targets comprise a plurality of first stationary targets and a plurality of second stationary targets, and the millimeter wave radar comprises the first millimeter Wave radar and second millimeter wave radar, the detection distance and coverage angle of the first millimeter wave radar are different from the detection distance and coverage angle of the second millimeter wave radar;
- the measurement information is calculated based on the tracking information and the calibration parameters of the millimeter wave radar, including:
- the acquisition module is specifically configured to calculate measurement information by:
- V xc , V yc R ⁇ (V xr , V yr );
- (x c , y c ) represents the position information of the stationary target in the vehicle coordinate system
- x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system.
- (x r , y r ) represents the position information of the stationary target in the radar coordinate system
- x r represents the horizontal axis coordinate of the stationary target in the radar coordinate system
- y r represents the vertical axis coordinate of the stationary target in the radar coordinate system
- R represents the amount of rotation
- T represents the amount of translation
- (V xc , V yc ) represents the velocity information of the stationary target in the vehicle coordinate system
- V xc represents the velocity of the stationary target in the horizontal axis direction of the vehicle coordinate system
- V yc represents the stationary target.
- the velocity in the vertical axis direction (V xr , V yr ) represents the velocity information of the stationary target in the radar coordinate system
- V xr represents the velocity of the stationary target in the horizontal axis direction of the radar coordinate system
- V yr represents The velocity of the stationary target in the direction of the longitudinal axis of the radar coordinate system.
- a determining module configured to calculate an occupation probability of each grid unit in the grid area according to the road boundary information and the historical road boundary information, wherein the grid area covers the target vehicle, and the grid area includes a plurality of grid units;
- the fusion boundary information is determined according to the target grid unit in the probability raster map, wherein the occupancy probability of the target grid unit is greater than a preset probability threshold.
- the road curvature information is calculated based on the fusion boundary information.
- the determination module is specifically used to calculate the occupation probability of each grid unit by:
- p n (x c , y c ) min(p(x c , y c )+p n-1 (x c , y c ), 1);
- p n (x c , y c ) represents the occupation probability of n-frame raster cells
- p(x c , y c ) represents road boundary information
- p n-1 (x c , y c ) represents n-1 frames
- x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system
- (x c , y c ) represents the stationary target in the vehicle coordinate system
- the lower position information, (x c , y c )' represents the average value of the position information of the multi-frame stationary target in the vehicle coordinate system
- S represents the covariance of x c and y c .
- the determining module is specifically configured to calculate road curvature information by:
- Q represents the road curvature information, g ⁇ (x c) represented by fusion boundary information, g ⁇ '(x c) represented by the first derivative of g ⁇ (x c) a, g ⁇ "(x c) represented by g ⁇ (x The second derivative of c ).
- the vehicle positioning device further includes a calculation module and a culling module
- the acquiring module is further configured to: before the determining module determines the current road boundary information corresponding to the current frame time according to the measurement information, obtain the to-be-selected still target information and the M reference stationary target information from the measurement information, where M is greater than 1. Integer
- a calculation module configured to calculate an average distance between the M reference stationary target information acquired by the acquiring module and the candidate stationary target information
- the culling module is configured to remove the candidate static target information from the measurement information if the average distance calculated by the calculation module does not satisfy the preset static target condition;
- the candidate stationary target information is any one of a plurality of static target information
- the reference stationary target information is static target information in which the distance between the plurality of stationary target information and the candidate stationary target information is less than the distance preset value.
- the calculation module is specifically used to calculate the average distance as follows:
- d denotes the average distance
- M denotes the number of reference still information
- P denotes the position information of the still target information to be selected
- P i denotes the position information of the i-th reference still information
- i is greater than 0 and less than or equal to M Integer.
- the culling module is specifically configured to determine that the average distance does not satisfy the preset static target condition if the average distance is greater than the threshold threshold, and remove the candidate stationary target information from the measurement information.
- the determination module is specifically used to calculate road boundary information by:
- f ⁇ (x c ) represents road boundary information
- ⁇ 0 represents the first coefficient
- ⁇ 1 represents the second coefficient
- ⁇ 2 represents the third coefficient
- ⁇ 3 represents the fourth coefficient
- x c represents the stationary target in the vehicle coordinate system.
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system
- (x c , y c ) represents the position information of the stationary target in the vehicle coordinate system
- ⁇ represents the regular term coefficient
- ⁇ j represents the j coefficients
- j is an integer greater than or equal to 0 and less than or equal to 3.
- a determining module configured to calculate a stabilization boundary information of a current frame time according to current road boundary information and historical road boundary information
- the determining module is specifically configured to calculate the stabilization boundary information corresponding to the current frame moment by:
- f ⁇ ' represents the stabilization boundary information corresponding to the current frame time
- f ⁇ _w (x c ) represents the historical road boundary information corresponding to the wth frame
- W represents the number of historical road boundary information
- x c represents the stationary target In the horizontal coordinate of the vehicle coordinate system
- ⁇ represents the average of the lane boundaries of the W frame.
- the determining module is specifically configured to calculate the first target positioning information of the current frame moment by:
- Location represents the first target location information of the current frame time
- ceil represents the upward rounding calculation mode
- R L represents the first distance of the target vehicle to the left boundary of the road
- R R represents the target vehicle to the right boundary of the road.
- the second distance, D represents the width of the lane
- N represents the number of lanes.
- the measurement information further includes: at least one moving target information
- the acquiring module is further configured to: acquire, by the determining information, at least one moving target information, where each moving target information carries a target number, and the target number is used for calibration, before the determining module determines the first target positioning information according to the current road boundary information.
- Different sports targets are further configured to: acquire, by the determining information, at least one moving target information, where each moving target information carries a target number, and the target number is used for calibration, before the determining module determines the first target positioning information according to the current road boundary information. Different sports targets;
- a determining module configured to determine lane occupying information according to the at least one moving target information acquired by the acquiring module and the corresponding historical moving target information
- the determining module is further configured to determine, according to the lane occupancy information, second target positioning information corresponding to the current frame moment, where the second target positioning information is used to indicate a location of the target vehicle in the road.
- the acquiring module is configured to acquire K-frame moving target information data according to the at least one moving target information and the historical moving target information corresponding to the at least one moving target information, where K is a positive integer;
- the lane occupancy ratio is less than a preset ratio, determining that the L k lanes are occupied, wherein the lane occupancy ratio is a ratio of k frames to K frames;
- lane occupancy ratio is greater than or equal to a preset ratio, determining that the L k lanes are not occupied
- the determining module is specifically configured to determine the L k lanes that are not occupied as the second target positioning information corresponding to the current frame moment.
- a determining module configured to determine a confidence level of the first target positioning information according to the second target positioning information, where the confidence is used to indicate the reliability of the first target positioning information
- the first target positioning information at the current time is determined according to the confidence level.
- a third aspect of the present application provides a vehicle positioning apparatus, which may include: a memory, a transceiver, a processor, and a bus system;
- the memory is used to store programs and instructions
- the transceiver is configured to receive or transmit information under control of the processor
- the processor is configured to execute a program in the memory
- the bus system is configured to connect the memory, the transceiver, and the processor to cause the memory, the transceiver, and the processor to communicate;
- the processor is configured to invoke program instructions in the memory, and the processor is configured to perform the following steps:
- the measurement information within the preset angle range is acquired by the measurement device, wherein the measurement information includes a plurality of static target information, the plurality of static target information being used to represent information of the plurality of stationary targets,
- the plurality of stationary target information are in one-to-one correspondence with the information of the plurality of stationary targets;
- Determining road curvature information according to the current road boundary information and historical road boundary information wherein the road curvature information is used to indicate a degree of bending of the road where the target vehicle is located, and the historical road boundary information includes at least one historical frame time Corresponding road boundary information, where the historical frame time is a time when the road boundary information and the road curvature information are acquired before the current frame time;
- the first target positioning information and the road curvature information are output.
- the processor is specifically configured to perform the following steps:
- the millimeter wave radar Obtaining, by the millimeter wave radar, tracking information of the plurality of stationary targets in the preset angle range, wherein the tracking information includes position information and speed information of the plurality of stationary targets in a radar coordinate system;
- the measurement information includes position information and speed information of the plurality of stationary targets in a vehicle coordinate system
- the calibration parameters include The amount of rotation and the amount of translation.
- the preset angle range includes a first preset angle range and a second preset angle range
- the processor is specifically configured to perform the following steps:
- the first millimeter wave radar Obtaining, by the first millimeter wave radar, first tracking information of the plurality of first stationary targets in the first preset angle range, and acquiring, by the second millimeter wave radar, the plurality of second static in the second preset angle range Second tracking information of the target, wherein the tracking information includes the first tracking information and the second tracking information, the plurality of stationary targets including the plurality of first stationary targets and the plurality of second a stationary target, the millimeter wave radar including the first millimeter wave radar and the second millimeter wave radar, a detection distance and a coverage angle of the first millimeter wave radar and a detection distance of the second millimeter wave radar Different coverage angles;
- the processor is specifically configured to perform the following steps:
- the measurement information is calculated by:
- V xc , V yc R ⁇ (V xr , V yr );
- (x c , y c ) represents position information of the stationary target in the vehicle coordinate system
- x c represents horizontal axis coordinates of the stationary target in the vehicle coordinate system
- the y c a vertical axis coordinate indicating the stationary target in the vehicle coordinate system
- the (x r , y r ) indicating position information of the stationary target in the radar coordinate system
- the x r indicating the stationary a horizontal axis coordinate of the target in the radar coordinate system
- the y r represents a vertical axis coordinate of the stationary target in the radar coordinate system
- the R represents the amount of rotation
- the T represents the translation
- (V xc , V yc ) represents speed information of the stationary target in the vehicle coordinate system
- the V xc represents a speed of the stationary target in a horizontal axis direction of the vehicle coordinate system
- V yc represents the velocity of the stationary target in the longitudinal axis direction of the vehicle coordinate system
- the processor is specifically configured to perform the following steps:
- the fusion boundary information is determined according to the target grid unit in the probability raster map, wherein the occupancy probability of the target grid unit is greater than a preset probability threshold.
- the road curvature information is calculated according to the fusion boundary information.
- the processor is specifically configured to perform the following steps:
- the occupancy probability of each of the grid cells is calculated as follows:
- p n (x c , y c ) min(p(x c , y c )+p n-1 (x c , y c ), 1);
- the p n (x c , y c ) represents an occupation probability of an n frame raster unit
- the p(x c , y c ) representing the road boundary information
- the p n-1 (x c , y c ) represents the historical road boundary information of the n-1 frame
- the x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the y c represents the stationary target in the vehicle a vertical axis coordinate in a coordinate system
- the (x c , y c ) indicating position information of the stationary target in the vehicle coordinate system
- the (x c , y c )′ represents a plurality of frames of the stationary target
- the S representing a covariance of the x c and the y c .
- the processor is specifically configured to perform the following steps:
- the road curvature information is calculated by:
- Q represents the road curvature information
- the g ⁇ (x c ) represents the fusion boundary information
- the g ⁇ '(x c ) represents a first derivative of the g ⁇ (x c )
- the g ⁇ "(x c ) represents the second derivative of the g ⁇ (x c ).
- the processor is further configured to perform the following steps:
- the candidate stationary target information is removed from the measurement information
- the candidate stationary target information is any one of the plurality of static target information
- the reference stationary target information is that the distance between the plurality of stationary target information and the candidate stationary target information is less than a distance The static target information of the preset value.
- the processor is specifically configured to perform the following steps:
- the average distance is calculated as follows:
- the d represents the average distance
- the M represents the number of the reference still information
- the P represents the location information of the candidate stationary target information
- the P i represents the ith reference Position information of the still information, the i being an integer greater than 0 and less than or equal to the M.
- the processor is specifically configured to perform the following steps:
- the threshold threshold it is determined that the average distance does not satisfy the preset stationary target condition, and the candidate stationary target information is removed from the measurement information.
- the processor is specifically configured to perform the following steps:
- the road boundary information is calculated by:
- f ⁇ (x c ) represents the road boundary information
- the ⁇ 0 represents a first coefficient
- the ⁇ 1 represents a second coefficient
- the ⁇ 2 represents a third coefficient
- the ⁇ 3 represents a a four coefficient
- the x c representing a horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the y c representing a vertical axis coordinate of the stationary target in the vehicle coordinate system
- the (x c , y c ) represents position information of the stationary target in the vehicle coordinate system
- the ⁇ represents a regular term coefficient
- the ⁇ j represents a j-th coefficient
- the j is greater than or equal to 0 and less than or equal to An integer of 3.
- the processor is specifically configured to perform the following steps:
- the processor is specifically configured to perform the following steps:
- the f ⁇ ' represents the stabilization boundary information corresponding to the current frame time
- the f ⁇ _w (x c ) represents historical road boundary information corresponding to the wth frame
- the W represents the history The number of road boundary information
- the x c indicating the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the ⁇ indicating the lane boundary average of the W frame.
- the processor is specifically configured to perform the following steps:
- the location represents the first target positioning information of the current frame time
- the ceil represents a rounding calculation manner
- the R L represents the target vehicle to the left side boundary of the road.
- the R R represents a second distance from the target vehicle to the right side boundary of the road
- the D represents the width of the lane
- the N represents the number of lanes.
- the processor is further configured to perform the following steps:
- each moving target information carries a target number, and the target number is used to calibrate different moving targets;
- the processor is specifically configured to perform the following steps:
- Determining, according to the lane occupancy information, the second target positioning information corresponding to the current frame moment including:
- the L k lanes that are not occupied are determined as the second target positioning information corresponding to the current frame moment.
- an embodiment of the present application provides a computer device, including: a processor, a memory, a bus, and a communication interface; the memory is configured to store a computer execution instruction, and the processor is connected to the memory through the bus, when the server runs The processor executes the computer-executed instructions stored by the memory to cause the server to perform the method of any of the above aspects.
- an embodiment of the present application provides a computer readable storage medium for storing computer software instructions for use in the above method, which when executed on a computer, enable the computer to perform the method of any of the above aspects.
- an embodiment of the present application provides a computer program product comprising instructions that, when run on a computer, cause the computer to perform the method of any of the above aspects.
- the present application has the following advantages:
- a method for positioning a vehicle is provided.
- the vehicle positioning device acquires measurement information within a preset angle range by using a millimeter wave radar, wherein the measurement information includes a plurality of stationary target information, and then the vehicle positioning device according to the measurement
- the information determines the road boundary information corresponding to the current frame time
- the vehicle positioning device determines the first target positioning information according to the road boundary information corresponding to the current frame time, where the first target positioning information is used to indicate the location of the vehicle in the lane
- the vehicle positioning device determines road curvature information according to the road boundary information and the historical road boundary information, wherein the road curvature information is used to indicate the degree of road curvature where the vehicle is located, and the historical road boundary information includes road boundary information corresponding to at least one historical frame time, history
- the frame time is the time at which the road boundary information and the road curvature information are acquired before the current frame time.
- the millimeter-wave radar performs active measurement, it is less affected by the light climate in the visible range. Under the central city, tunnel culvert and non-ideal meteorological conditions, the millimeter-wave radar can be used to obtain the vehicle and the surrounding targets. The positional relationship between the two, thereby determining the positioning information of the vehicle in the road, thereby improving the confidence and reliability of the positioning information. In addition, road curvature information is determined by these positional relationships, which can estimate the curvature of the lane in which the vehicle is located, thereby improving the accuracy of vehicle positioning.
- FIG. 1 is a schematic structural diagram of a vehicle positioning system in an embodiment of the present application.
- FIG. 2 is a schematic diagram of implementation of a product of a vehicle positioning device according to an embodiment of the present application
- FIG. 3 is a schematic diagram of a core flow of a method for positioning a vehicle in an embodiment of the present application
- FIG. 4 is a schematic diagram of an embodiment of a vehicle positioning scenario in an embodiment of the present application.
- FIG. 5 is a schematic diagram of an embodiment of a method for positioning a vehicle according to an embodiment of the present application.
- FIG. 6 is a schematic diagram of a scene of acquiring a target by a millimeter wave radar according to an embodiment of the present application
- FIG. 7 is a schematic diagram of a millimeter wave radar coordinate system and a vehicle coordinate system in the embodiment of the present application;
- FIG. 8 is a schematic flowchart of obtaining measurement information in a preset angle range according to an embodiment of the present application.
- FIG. 9 is a schematic flowchart of constructing a probability raster graph in the embodiment of the present application.
- FIG. 10 is a schematic diagram of a probability raster diagram in the embodiment of the present application.
- FIG. 11 is a schematic diagram of a result of constructing a probability raster graph in an embodiment of the present application.
- FIG. 12 is a schematic flow chart of positioning a stationary target information by a millimeter wave radar according to an embodiment of the present application
- FIG. 13 is a schematic diagram of determining static target information of an abnormality to be selected in the embodiment of the present application.
- FIG. 14 is a schematic diagram of another embodiment of a method for positioning a vehicle according to an embodiment of the present application.
- 15 is a schematic flow chart of positioning motion target information of a millimeter wave radar in an embodiment of the present application.
- 16 is a schematic diagram of the moving target information occupying a lane in the embodiment of the present application.
- 17 is a schematic diagram of a millimeter wave radar combining stationary target information and moving target information in an embodiment of the present application
- FIG. 18 is a schematic diagram of an embodiment of a vehicle positioning device according to an embodiment of the present application.
- FIG. 19 is a schematic diagram of another embodiment of a vehicle positioning device according to an embodiment of the present application.
- FIG. 20 is a schematic structural diagram of a vehicle positioning device according to an embodiment of the present application.
- the present application provides a method for locating a vehicle and a vehicle locating device, which can locate the central city, the tunnel and the irregular road, improve the confidence and reliability of the positioning, and further improve the vehicle planning control through the road curvature information.
- System to plan the vehicle's driving trajectory.
- the present application can be applied to central urban areas, tunnels, and irregular road conditions.
- the vehicle In order to complete driving planning guidance at the lane level, the vehicle needs to know information about its own surrounding road environment, that is, local location information including the self-vehicle relative to the surrounding road environment. And elemental information about the road around the vehicle (such as road curvature, etc.).
- the vehicle can sense the surroundings of the vehicle by means of on-board sensors, and control the steering and speed of the vehicle based on the road, vehicle position and obstacle information obtained by the perception, so that the vehicle can travel safely and reliably on the road.
- FIG. 1 is a schematic structural diagram of a vehicle positioning system according to an embodiment of the present application.
- the positioning sensing and synchronization hardware system S1 includes a sensor and a synchronization unit required for positioning in the present application, wherein
- the sensor specifically includes an initial global positioning system (GPS) receiver and a millimeter wave radar sensor.
- the positioning data acquisition system S2 collects the positioning sensor data and the synchronization data of the positioning sensing and synchronization hardware system S1, and sends the positioning sensor data and the synchronization data to the millimeter wave radar positioning processing system S3 of the vehicle end.
- the processor on the vehicle side can complete the construction of the local positioning and probability raster map in the present application in combination with the vehicle map system S4, and send the positioning result to the vehicle computer S5 for subsequent driving planning and use.
- the processor on the vehicle side can also transmit the positioning sensor data and the synchronization data to the cloud computing center S6 through the vehicle gateway, and the cloud computing center S6 integrates the cloud map to complete the vehicle local positioning and the probability raster map construction, and through the vehicle gateway.
- the information is passed to the millimeter wave radar positioning processing system S3 and then passed to the vehicle computer S5 for use in driving planning.
- FIG. 2 is a schematic diagram of a product implementation of a vehicle positioning device according to an embodiment of the present application.
- the present application requires a GPS receiver to provide initialization during the positioning process.
- the medium-to-medium-long-range millimeter-wave radar, the short-range millimeter-wave radar, the lane number map, and the positioning algorithm processing equipment are required in the local positioning process, that is, the product realization diagram shown in FIG.
- the product implementation mainly includes the following components:
- a GPS receiver for receiving GPS signals and providing an initial reference position for positioning of the vehicle.
- the GPS receiver is an instrument that receives GPS satellite signals and determines the spatial position of the ground.
- the navigation and positioning signals transmitted by the GPS satellites are information resources that can be shared by a large number of users.
- receiving devices that can receive, track, transform and measure GPS signals, that is, GPS signal receivers.
- millimeter wave radar Medium-long-range millimeter-wave radar and short-range millimeter-wave radar are used to obtain stationary target information and moving target information of the vehicle's circumferential direction.
- the millimeter wave radar also has the following characteristics:
- a lane number map for providing information on the number of lanes owned by the road.
- Data synchronization unit which is used to provide synchronization information for medium and long distance millimeter wave radar, short distance millimeter wave radar and lane number map, so that information maintains integrity and uniformity.
- Data acquisition device for collecting target information of forward medium and long distance millimeter wave radar, target information of short distance millimeter wave radar in four angular directions, GPS receiver information and synchronization time stamp information;
- Radar positioning processing board for completing local positioning and probability raster map construction of the circumferential millimeter wave radar, and the radar positioning processing board includes but is not limited to a digital signal processor that satisfies the level of the vehicle, such as digital signal processing (digital signal processing) Processing, DSP), field programmable gate array (FPGA), and micro control unit (MCU).
- DSP digital signal processing
- FPGA field programmable gate array
- MCU micro control unit
- the vehicle computer or the automatic driving calculation platform is configured to receive the positioning information transmitted by the radar positioning processing board and perform the driving planning.
- the processing capacity of the radar processing board is limited, the calculation of the partial positioning processing may be shared, such as For automated driving computing platforms.
- Cloud computing center which is used to complete the local processing of the millimeter wave radar and the calculation of the probability raster map in the cloud.
- FIG. 3 is a core flow of a method for positioning a vehicle according to an embodiment of the present application. Schematic, specifically:
- step 101 when the vehicle positioning is started, the vehicle local positioning initialization can be completed by inputting the GPS initial position and the lane number map.
- step 102 the medium and long distance millimeter wave radar and the short distance millimeter wave radar installed on the vehicle are turned on, and the data collected by the medium long distance radar and the short range radar frame interval is converted from the radar coordinate system to the vehicle coordinate system, thereby Obtain the target information of the toroidal millimeter wave radar.
- Steps 103 to 105 are the core steps in the present application.
- step 103 the stationary target information in the circular millimeter wave radar target is used, and the isolated abnormal target rejection, the optimal road boundary information solution, and the historical road boundary information are weighted. Then, combined with the number of lanes map to achieve stationary target positioning; using the moving target information and the historical moving target information in the circular millimeter wave radar target to determine the lane occupancy, the integrated lane number map and the lane occupying information, the moving target positioning can be completed.
- the stationary target positioning result and the moving target positioning result are combined to obtain the vehicle local positioning result.
- step 104 it is determined whether the local positioning of the vehicle is successful according to the positioning result obtained in step 103. If the positioning is successful, the process proceeds to step 105. Otherwise, if the positioning fails, the process proceeds to step 101, and the positioning is resumed.
- step 105 after the positioning is successful, the static target information of the multi-frame and the road boundary information determined by the positioning are merged, and the grid occupation probability is calculated according to the measurement target information and the prediction of the radar, and a grid probability map around the vehicle is constructed, and the calculated Road boundary curvature information in the road grid probability map.
- FIG. 4 is a schematic diagram of an embodiment of a vehicle positioning scene according to an embodiment of the present application.
- a medium and long distance millimeter installed in front of the vehicle Wave Radar and short-range millimeter-wave radar mounted at four corners provide the vehicle with circular millimeter-wave measurement information input.
- medium-long-range millimeter-wave radar is a combination of medium-range millimeter-wave radar (MRR) and long-range millimeter-wave radar (LRR), short-range millimeter-wave radar (short range radar, SRR).
- MRR medium-range millimeter-wave radar
- LRR long-range millimeter-wave radar
- SRR short-range millimeter-wave radar
- the method for locating a vehicle in the present application will be described below with reference to the embodiments and the accompanying drawings.
- the method for locating a vehicle provided by the present application may include the following two embodiments, specifically:
- Embodiment 1 is to complete vehicle positioning by using multiple stationary target information
- FIG. 5 is a schematic diagram of an embodiment of a method for locating a vehicle according to an embodiment of the present application.
- One embodiment of a method for locating a vehicle in an embodiment of the present application includes:
- the measurement information in the preset angle range is acquired by the measurement device, where the measurement information includes a plurality of static target information, and the plurality of static target information is used to represent information of multiple stationary targets, and multiple static targets Information is in one-to-one correspondence with information of a plurality of stationary targets;
- the vehicle positioning device may first respond to the local positioning start command, and then acquire the GPS receiver signal, the lane number map, and the synchronization unit signal, and then send to the vehicle data acquisition unit after synchronization, and the vehicle positioning device Initial local positioning information is collected from the data acquisition unit.
- the vehicle positioning device acquires measurement information within a preset angle range by using a measurement device, and the measurement information may include a plurality of static target information, the speed of the stationary target information relative to the ground reference frame is zero, and each of the stationary target information corresponds to a stationary image. Target information.
- the measuring device may be a millimeter wave radar
- the preset angle range may include a first preset angle range and a second preset angle range, where the first preset angle range and the second preset angle range are different, for example, the first The preset angle range is 120 degrees, and the second preset angle range is 60 degrees. It can be understood that the first preset angle range and the second preset angle range may also be other degrees, which are not limited herein.
- FIG. 6 is a schematic diagram of a scene of a millimeter wave radar acquiring target in the embodiment of the present application.
- the beam coverage of the short-range millimeter wave radar is a small sector of a dotted line
- the medium and long distance The beam coverage of the millimeter wave radar is a large sector of the dotted line
- the dot represents the stationary target detected by the millimeter wave radar
- the square represents the moving target detected by the millimeter wave radar.
- the vehicle positioning device acquires tracking information of a plurality of stationary targets and/or moving targets in a first preset angle range by using a first millimeter wave radar, and acquires a plurality of stationary targets in a second preset angle range by using a second millimeter wave radar / or tracking information of the moving target, wherein the detecting distance and the covering angle of the first millimeter wave radar are different from the detecting distance and the covering angle of the second millimeter wave radar.
- the detection distance of the first millimeter wave radar is greater than the detection distance of the second millimeter wave
- the second millimeter wave radar The coverage is greater than the coverage of the first millimeter wave radar, wherein the further the detection distance, the smaller the coverage (the coverage usually refers to the coverage angle).
- the detection distance of the first millimeter wave radar is smaller than the detection distance of the second millimeter wave
- the second millimeter wave radar The coverage is smaller than the coverage of the first millimeter wave radar, wherein the closer the detection distance is, the larger the coverage (the coverage usually refers to the coverage angle).
- the plurality of targets include stationary targets and/or moving targets, the stationary targets may be fixed objects such as roadside trees or guardrails, and the moving targets generally refer to moving vehicles.
- the vehicle positioning device acquires tracking information of a plurality of targets, the tracking information including position information and speed information of the target in the radar coordinate system.
- the tracking information including position information and speed information of the target in the radar coordinate system.
- the relative number of moving targets detected by millimeter wave radar is relatively small, and the front and rear frame target information are related, and each target has a unique number.
- the vehicle positioning device can calculate the measurement information in the preset angle range according to the tracking information and the calibration parameter of the millimeter wave radar, wherein the tracking information belongs to information in the radar coordinate system, and the measurement information in the preset angle range belongs to the vehicle coordinate system.
- the information, the calibration parameters include the amount of rotation and the amount of translation, and the measurement information within the preset angle range includes position information and speed information of the target in the vehicle coordinate system.
- the vehicle coordinate system and the radar coordinate system will be described below. Please refer to FIG. 7.
- FIG. 7 is a schematic diagram of the millimeter wave radar coordinate system and the vehicle coordinate system in the embodiment of the present application. As shown in the figure, the radar coordinate system is a radar.
- the geometric center is the origin, with the X-axis in the right direction of the sensor and the Y-axis in the forward direction of the sensor.
- the vehicle body coordinate system is based on the center of the rear axle of the vehicle as the origin O, with the vehicle traveling direction as the X axis and the rear axle pointing to the right as the Y axis.
- FIG. 8 is a schematic flowchart of obtaining measurement information in a preset angle range according to an embodiment of the present application, as shown in the figure, specifically:
- the quantity T, and the tracking information of the target includes position information (x r , y r ) and speed information (V xr , V yr ).
- step 2012 the calibration parameters of each millimeter wave radar to the vehicle coordinate system are read, and the position information (x r , y r ) and the velocity information (V xr , V yr ) in the above step 2011 are according to the following conversion relationship. From the radar coordinate system to the vehicle coordinate system, the position information in the vehicle coordinate system is expressed as (x c , y c ), and the speed information is expressed as (V xc , V yc ), and the conversion relationship is:
- V xc , V yc R ⁇ (V xr , V yr );
- (x c , y c ) represents the position information of the stationary target in the vehicle coordinate system
- x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system.
- (x r , y r ) represents the position information of the stationary target in the radar coordinate system
- x r represents the horizontal axis coordinate of the stationary target in the radar coordinate system
- y r represents the vertical axis coordinate of the stationary target in the radar coordinate system
- R represents the amount of rotation
- T represents the amount of translation
- (V xc , V yc ) represents the velocity information of the stationary target in the vehicle coordinate system
- V xc represents the velocity of the stationary target in the horizontal axis direction of the vehicle coordinate system
- V yc represents the stationary target.
- the velocity in the vertical axis direction (V xr , V yr ) represents the velocity information of the stationary target in the radar coordinate system
- V xr represents the velocity of the stationary target in the horizontal axis direction of the radar coordinate system
- V yr represents The velocity of the stationary target in the direction of the longitudinal axis of the radar coordinate system.
- step 2013 measurement information within a preset angle range under the vehicle coordinate system is output.
- the vehicle positioning device determines road boundary information corresponding to the current frame time according to the measurement information in the vehicle coordinate system, and the road boundary information is used to indicate the boundary of the road traveling region.
- the road boundary information can be expressed as a polynomial:
- f ⁇ (x c ) represents road boundary information
- ⁇ 0 represents the first coefficient
- ⁇ 1 represents the second coefficient
- ⁇ 2 represents the third coefficient
- ⁇ 3 represents the fourth coefficient
- x c represents the stationary target in the vehicle coordinate system.
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system
- (x c , y c ) represents the position information of the stationary target in the vehicle coordinate system
- ⁇ represents the regular term coefficient
- ⁇ j represents the j coefficients
- j is an integer greater than or equal to 0 and less than or equal to 3.
- the vehicle positioning device may determine the first target positioning information according to the road boundary information corresponding to the current frame time, where the first target positioning information is determined according to the stationary target information, and the first target positioning information is used to indicate The location of the vehicle in the lane, such as the second lane of the vehicle in five lanes.
- the process of determining the first target positioning information by the vehicle positioning device is: first, the vehicle positioning device calculates the stabilization boundary information of the current frame time according to the road boundary information corresponding to the current frame time and the historical road boundary information, and stabilizes the boundary information. The weighted average of the previous historical road boundary information and the current road boundary information is used to improve the stability of the current positioning result. Then, according to the stabilization boundary information of the current frame time, the first distance of the vehicle to the left boundary of the road and the second distance from the vehicle to the right boundary of the road are obtained, and finally the current frame time is calculated according to the first distance and the second distance. First target location information.
- the stabilization boundary information corresponding to the current frame time can be calculated as follows:
- f ⁇ ' represents the stabilization boundary information corresponding to the current frame time
- f ⁇ _w (x c ) represents the historical road boundary information corresponding to the wth frame
- W represents the number of historical road boundary information
- x c represents the stationary target In the horizontal coordinate of the vehicle coordinate system
- ⁇ represents the average of the lane boundaries of the W frame.
- the values may all be around 0.2, such as 0.21, 0.19, 0.23, 0.20, and 0.22, and then updated to obtain the following stabilization boundary information:
- the first distance R L from the vehicle to the left boundary of the road and the second distance R R from the vehicle to the right boundary of the road can be obtained, and the number of lanes in the lane number map is combined.
- N the lane width D is calculated.
- the first target positioning information of the current frame time is calculated as follows:
- the historical frame time is a time when the road boundary information and the road curvature information are acquired before the current frame time;
- the vehicle positioning device may determine the road curvature information according to the road boundary information and the historical road boundary information, wherein the road curvature information is used to indicate the road bending degree at which the vehicle is located, and the reciprocal of the road curvature information corresponds to the turning radius.
- FIG. 9 is a schematic flowchart of constructing a probability raster graph in the embodiment of the present application, as shown in the figure, specifically:
- step 2041 the stationary target information around the vehicle detected by the millimeter wave radar is input.
- the stabilization boundary information is continuously changed during the millimeter wave radar data refresh time, that is, within a few consecutive frames of data, the millimeter wave radar pair
- the positioning of the stationary target does not change drastically.
- the road boundary information of the current frame time is recorded, and in the subsequent process of calculating the fusion boundary information, the road boundary information of the current frame time and the historical road boundary information are weighted and averaged to obtain the current frame time.
- the boundary information is stabilized to improve the stability of the fusion boundary information calculation, wherein the plurality of stabilization boundary information can obtain the fusion boundary information.
- step 2042 it is necessary to define a grid area around the vehicle (ie, the target vehicle), that is, to set a grid area around the vehicle.
- FIG. 10 is a probability grid in the embodiment of the present application.
- a schematic diagram of the figure, as shown in the figure, draws a grid area from the first frame time to the fifth frame time.
- the grid area corresponds to the left and right borders of the vehicle by ⁇ 20 m, corresponding to the front and rear boundaries of the vehicle.
- each grid unit has a size of 0.2m, so that you can get an m ⁇ n grid area around the car (m is the grid area width divided by the grid unit size, n is the grid area length except In the grid cell size), and as the car moves forward, the grid area is always fixed distance from the front, rear, left and right of the vehicle (for example, according to the test experience, the grid area corresponds to the left and right boundaries of the vehicle ⁇ 20 m, corresponding to the front and rear boundaries of the vehicle ⁇ 70m).
- the probability distribution of the stationary target information detected by the millimeter wave radar is assumed to be a Gaussian distribution, and for each grid unit, the static target information of the multi-frame fusion (for example, 20 frames according to the test experience) is (x c , y c ), according to the positional relationship between the millimeter wave radar and the stationary target information, the average value of the stationary target information in the multi-frame is (x c , y c )', for each grid cell, each grid The probability that the unit is occupied by the target is continuously accumulated, and the occupation probability of the number of grid cells is superimposed, and a probability raster map, that is, the probability raster map shown in FIG. 10 is obtained.
- the occupancy probability in each raster cell can be calculated as follows:
- p n (x c , y c ) min(p(x c , y c )+p n-1 (x c , y c ), 1);
- p n (x c , y c ) represents the occupation probability of n-frame raster cells
- p(x c , y c ) represents road boundary information
- p n-1 (x c , y c ) represents n-1 frames
- x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- y c represents the vertical axis coordinate of the stationary target in the vehicle coordinate system
- (x c , y c ) represents the stationary target in the vehicle coordinate system
- the lower position information, (x c , y c )' represents the average value of the position information of the multi-frame stationary target in the vehicle coordinate system
- S represents the covariance of x c and y c .
- FIG. 11 is a schematic diagram of the result of constructing the probability raster map in the embodiment of the present application.
- the road curvature information can be calculated according to the probability raster map, and the road curvature information is calculated as follows:
- Q represents the road curvature information, g ⁇ (x c) represented by fusion boundary information, g ⁇ '(x c) represented by the first derivative of g ⁇ (x c) a, g ⁇ "(x c) represented by g ⁇ (x The second derivative of c ).
- the road curvature information is equal to 0.03.
- the vehicle positioning device outputs the first target positioning information and the road curvature information by means of display and/or voice, thereby alerting the debugger to assist driving.
- a method for positioning a vehicle is provided.
- the vehicle positioning device acquires measurement information within a preset angle range by using a millimeter wave radar, wherein the measurement information includes a plurality of stationary target information, and then the vehicle positioning device according to the measurement
- the information determines the road boundary information corresponding to the current frame time
- the vehicle positioning device determines the first target positioning information according to the road boundary information corresponding to the current frame time, where the first target positioning information is used to indicate the location of the vehicle in the lane
- the vehicle positioning device determines road curvature information according to the road boundary information and the historical road boundary information, wherein the road curvature information is used to indicate the degree of road curvature where the vehicle is located, and the historical road boundary information includes road boundary information corresponding to at least one historical frame time, history
- the frame time is the time at which the road boundary information and the road curvature information are acquired before the current frame time.
- the millimeter-wave radar performs active measurement, it is less affected by the light climate in the visible range. Under the central city, tunnel culvert and non-ideal meteorological conditions, the millimeter-wave radar can be used to obtain the vehicle and the surrounding targets. The positional relationship between the two, thereby determining the positioning information of the vehicle in the road, thereby improving the confidence and reliability of the positioning information. In addition, road curvature information is determined by these positional relationships, which can estimate the curvature of the lane in which the vehicle is located, thereby improving the accuracy of vehicle positioning. Achieve better vehicle planning control in advanced assisted driving or automatic driving lane level positioning.
- determining current road boundary information corresponding to the current frame time according to the measurement information Previously it could also include:
- the candidate stationary target information is removed from the measurement information
- the candidate stationary target information is any one of a plurality of static target information
- the reference stationary target information is static target information in which the distance between the plurality of stationary target information and the candidate stationary target information is less than the distance preset value.
- the vehicle positioning device acquires the measurement information in the preset angle range by the millimeter wave radar, it is also necessary to screen out the static target information that meets the requirements, and eliminate the static target information that does not meet the requirements.
- FIG. 12 is a schematic flowchart of positioning the stationary target information of the millimeter wave radar in the embodiment of the present application, as shown in the figure, specifically:
- the candidate stationary target information is first extracted from the measurement information in the preset angle range, wherein the vehicle speed V car is compared with the speed V xc in the vehicle coordinate system, if the speed is in the vehicle coordinate system.
- the target within a certain range (for example, 2 m / s) can be marked as the candidate stationary target information.
- d denotes the average distance
- M denotes the number of reference still information
- P denotes the position information of the still target information to be selected
- P i denotes the position information of the i-th reference still information
- i is greater than 0 and less than or equal to M Integer.
- FIG. 13 is a schematic diagram of determining the abnormally-selected still target information in the embodiment of the present application, as shown by points A and B in FIG. 13, the distances of the last five reference still information around point A to point A are compared. Nearly, the average distance is relatively small, and the distance between the nearest five reference static information around point B and point B is relatively long, and the average distance is large. By comparing with the preset threshold threshold, point A will not be marked as isolated. For the abnormal target, point B will be marked as an isolated abnormal target, and point B needs to be eliminated.
- the threshold threshold can be set according to the actual radar system parameters, generally about 5 times the radar range resolution
- Figure 13 corresponds to the left road boundary in Figure 6, the dot is the static target information detected by the radar, the straight line 2 is the exact road boundary obtained by the solution, and the straight line or curve is the inaccurate road boundary obtained by the solution. Among them, the curve No. 2 is the stability boundary information. It is to be understood that points A and B are two exemplary objects and are not to be construed as limiting the application.
- step 303 after the vehicle positioning device removes the abnormal orphan target, the polynomial of the road boundary information may be constructed, that is, the road boundary information is solved by using the remaining stationary target information, as described in step 202 in the embodiment corresponding to FIG. 5.
- the relevant content do not repeat here.
- step 304 the position information of the stationary target that is culled with the isolated anomaly is substituted into the road boundary cost function in step 303, and the optimal road boundary polynomial coefficient is solved to determine the optimal road boundary information.
- step 305 the historical road boundary information is input, and the weighted average is performed to obtain the stabilization boundary information, and then the fusion boundary information is determined according to the plurality of stabilization boundary information.
- the specific manner is as described in step 203 in the embodiment corresponding to FIG. Content, do not repeat here.
- the stability of road boundary information can be effectively increased, and the situation of road boundary jumps can be avoided. If the initial frame solves the stabilization boundary information, the weighted average of the road boundary information is not performed, and generally the weighted average is started after 5 frames, and the average is 5 frames to 10 frames.
- step 306 according to the stabilization boundary information calculated in step 305, the distance from the vehicle to the left boundary of the road and the distance from the vehicle to the right boundary of the road can be obtained, and the number of lanes in the lane number map is calculated. Lane width.
- the vehicle positioning device calculates the number of lanes from the vehicle to the left road boundary and to the right side according to the distance from the vehicle to the left side boundary of the road, the distance from the vehicle to the right side boundary of the road, and the calculated lane width.
- the number of lanes on the road boundary determines the lane in which the vehicle is located based on the number of lanes from the car to the left road boundary and the number of lanes to the right road boundary.
- step 308 the vehicle positioning device outputs the first target positioning information, that is, the lane in which the vehicle is located is marked on the lane number map.
- how to remove the abnormal candidate target information from the measurement information in the preset angle range is introduced.
- a feasible way is to select the stationary target information according to the candidate and the M reference stationary target information. The average distance is obtained. If the average distance is greater than the threshold threshold, the step of selecting the stationary target information from the measurement information in the preset angle range is removed.
- Embodiment 2 the vehicle positioning is completed by using multiple static target information and multiple moving target information;
- FIG. 14 is a schematic diagram of another embodiment of a method for locating a vehicle according to an embodiment of the present application.
- Another embodiment of a method for locating a vehicle in an embodiment of the present application includes:
- 401 Acquire, in a current frame time, measurement information in a preset angle range by using a measurement device, where the measurement information includes a plurality of static target information and at least one moving target information, where the plurality of static target information are used to represent multiple stationary targets.
- the plurality of stationary target information and the information of the plurality of stationary targets are in one-to-one correspondence;
- the process of acquiring the plurality of static target information in the preset angle range by the millimeter wave radar may refer to step 201 in the corresponding embodiment of FIG. 5, and details are not described herein.
- the following describes how to determine at least one moving target information.
- the moving target information is target information with displacement relative to the ground, and firstly, the moving target information to be selected is extracted from the measurement information in the preset angle range, wherein, according to the vehicle traveling speed V car and the speed V xc in the vehicle coordinate system In contrast, if the error in the vehicle coordinate system and the vehicle travel speed error
- the moving target information includes not only the label of the target, the position information of the target, and the speed information of the target.
- the process of determining the road boundary information corresponding to the current frame time by the vehicle positioning device according to the measurement information may refer to step 202 in the corresponding embodiment of FIG. 5, and details are not described herein.
- each moving target information carries a target number, and the target number is used to calibrate different moving targets;
- the vehicle positioning device acquires at least one moving target information of the current frame time from the measurement information, wherein each moving target information carries a corresponding target number, and different target numbers are used to calibrate different targets.
- FIG. 15 is a schematic flowchart of the millimeter wave radar positioning motion target information according to an embodiment of the present application. Show, specifically:
- step 4031 the moving target information is input, and it is determined that the vehicle traveling speed V car is compared with the speed V xc of the moving target information in the vehicle coordinate system, if the error in the vehicle coordinate system and the traveling speed of the vehicle
- Targets that exceed a certain range eg 2 m / s
- step 4032 the tracking history of the moving target information is recorded based on the number of the moving target information (the numbering is kept constant from the start of the radar tracking to the end of the tracking).
- step 4033 the lane occupied by the moving target information is marked, and the specific marking manner will be introduced in step 405, which is only a brief description here.
- step 4034 the lane occupancy information is recorded and the lane occupancy state is determined, that is, according to the lane occupancy information flag result, it can be determined that all lanes are occupied, and the lane number map can be combined to determine which lanes are occupied, and the occupied lanes are on the map. Mark in .
- step 4035 according to the information occupied by the marked moving vehicle in the lane number map, the unmarked lane is left as the self-vehicle lane, thereby completing the local positioning of the self-vehicle and outputting the positioning result of the self-vehicle.
- the vehicle positioning device according to the position information (especially the lateral position information) and the lane width prior information corresponding to each moving target information obtained by the millimeter wave radar (the lane width is generally 3.5 meters to 3.75 meters),
- the remaining moving target information can determine the lane L k in which the moving target is located according to the lateral distance, for each moving target For information, combined with the current frame and the previous history frame total K frames, if there are k frames moving targets occupying the lane L k in the K frame, it can be judged that the lane is occupied.
- FIG. 16 FIG.
- the moving target information occupies a schematic diagram of the lane. As shown in the figure, it is assumed that there are three lanes, namely L1, L2 and L3 respectively.
- the L1 lane is in an idle state, the L2 lane is occupied, and the L3 lane is occupied. Is in an idle state.
- the L1 lane is occupied, the L2 lane is occupied, and the L3 lane is idle.
- the L1 lane is occupied, the L2 lane is occupied, and the L3 lane is idle.
- the L1 lane is in an idle state, the L2 lane is occupied, and the L3 lane is in an idle state.
- the case where the L kth lane is occupied can be determined by the following decision formula.
- L k represents the L kth lane
- k represents the k frame is occupied
- k is an integer greater than 0 and less than or equal to K
- K represents a common K frame time
- thres represents a preset ratio
- step 404 if the lane occupancy ratio is greater than or equal to the preset ratio, it is determined that the L k lanes are not occupied, and the unoccupied L k lanes are determined as current.
- the vehicle positioning device may determine the confidence of the first target positioning information according to the second target positioning information, where the confidence is used to indicate the reliability of the first target positioning information. Generally, the confidence is higher. , indicating that the reliability of the result is stronger. Finally, the first target positioning information at the current moment is determined according to the confidence level.
- FIG. 17 is a schematic diagram of the millimeter wave radar combining the stationary target information and the moving target information in the embodiment of the present application, and the millimeter wave is passed in step 4061.
- the positioning result of the plurality of stationary target information acquired by the radar ie, the first target positioning information
- the plurality of moving target information ie, the second target positioning information
- the historical frame time is a time when the road boundary information and the road curvature information are acquired before the current frame time;
- the process of determining the road curvature information by the vehicle positioning device according to the road boundary information and the historical road boundary information may refer to step 204 in the corresponding embodiment of FIG. 5, and details are not described herein.
- the vehicle positioning device outputs the first target positioning information and the road curvature information by means of display and/or voice, thereby alerting the debugger to assist driving.
- a plurality of stationary target information and moving target information are simultaneously acquired by the millimeter wave radar, and the road boundary information is calculated by combining the two to realize the positioning of the vehicle.
- the moving target information can assist the static target information to calculate the road boundary information, so that the vehicle positioning can be accurately completed when the traffic volume is large, thereby improving the feasibility and flexibility of the solution, and increasing the confidence of the positioning. degree.
- the vehicle positioning device 50 in the embodiment of the present application includes:
- the acquiring module 501 is configured to acquire measurement information in a preset angle range by using a measurement device, where the measurement information includes a plurality of static target information, where the plurality of static target information is used to indicate multiple static Information of the target, the plurality of static target information and the information of the plurality of stationary targets are in one-to-one correspondence;
- a determining module 502 configured to determine, according to the measurement information acquired by the acquiring module 501, current road boundary information corresponding to the current frame time;
- the determining module 502 is configured to determine first target positioning information according to the current road boundary information, where the first target positioning information is used to indicate a location where the target vehicle is located in the road;
- the determining module 502 is configured to determine road curvature information according to the current road boundary information and the historical road boundary information, where the road curvature information is used to indicate a degree of bending of the road where the target vehicle is located, and the historical road boundary
- the information includes road boundary information corresponding to at least one historical frame time, where the historical frame time is a time when the road boundary information and the road curvature information are acquired before the current frame time;
- the output module 503 is configured to output the first target positioning information determined by the determining module 502 and the road curvature information determined by the determining module.
- the acquiring module 501 acquires measurement information in a preset angle range by using the measurement device, where the measurement information includes a plurality of static target information, and the multiple static target information is used to indicate multiple The information of the static target, the plurality of static target information and the information of the plurality of stationary targets are in one-to-one correspondence, and the determining module 502 determines, according to the measurement information acquired by the acquiring module 501, the current frame time The current road boundary information, the determining module 502 determines first target positioning information according to the current road boundary information, wherein the first target positioning information is used to indicate a location where the target vehicle is located in the road, and the determining module 502 Determining road curvature information according to the current road boundary information and historical road boundary information, wherein the road curvature information is used to indicate a degree of bending of the road where the target vehicle is located, and the historical road boundary information includes at least one historical frame time Corresponding road boundary information, the historical frame time is before the current frame time
- a vehicle positioning device acquires measurement information in a preset angle range by using a millimeter wave radar, wherein the measurement information includes a plurality of stationary target information, and then the vehicle positioning device according to the measurement information Determining the road boundary information corresponding to the current frame time, and then the vehicle positioning device determines the first target positioning information according to the road boundary information corresponding to the current frame time, where the first target positioning information is used to indicate the location of the vehicle in the lane, and finally the vehicle The positioning device determines the road curvature information according to the road boundary information and the historical road boundary information, wherein the road curvature information is used to indicate the degree of road curvature where the vehicle is located, and the historical road boundary information includes road boundary information corresponding to at least one historical frame time, and the historical frame
- the time is the time at which the road boundary information and the road curvature information are acquired before the current frame time.
- the millimeter-wave radar performs active measurement, it is less affected by the light climate in the visible range. Under the central city, tunnel culvert and non-ideal meteorological conditions, the millimeter-wave radar can be used to obtain the vehicle and the surrounding targets. The positional relationship between the two, thereby determining the positioning information of the vehicle in the road, thereby improving the confidence and reliability of the positioning information. In addition, road curvature information is determined by these positional relationships, which can estimate the curvature of the lane in which the vehicle is located, thereby improving the accuracy of vehicle positioning. Achieve better vehicle planning control in advanced assisted driving or automatic driving lane level positioning.
- the acquiring module 501 is specifically configured to acquire, by using a millimeter wave radar, tracking information of the plurality of stationary targets in the preset angle range, where the tracking information includes the plurality of stationary targets in a radar coordinate system. Location information and speed information;
- the measurement information includes position information and speed information of the plurality of stationary targets in a vehicle coordinate system
- the calibration parameters include The amount of rotation and the amount of translation.
- millimeter wave radar has a very wide frequency band and is suitable for various wideband signal processing. It also has angle resolution and tracking capability, and has wide Doppler broadband, obvious Doppler effect, good Doppler resolution, and millimeter wave.
- the radar wavelength is short, and the scattering characteristics of the target are described accurately, finely and with high speed measurement accuracy.
- the preset angle range includes a first preset angle range and a second. Preset angle range
- the acquiring module 501 is specifically configured to acquire first tracking information of the plurality of first stationary targets in the first preset angle range by using the first millimeter wave radar, and acquire the second pre-prepared by the second millimeter wave radar Second tracking information of a plurality of second stationary targets within an angular range, wherein the tracking information includes the first tracking information and the second tracking information, the plurality of stationary targets including the plurality of first a stationary target and the plurality of second stationary targets, the millimeter wave radar including the first millimeter wave radar and the second millimeter wave radar, a detection distance and a coverage angle of the first millimeter wave radar and the The detection distance and coverage angle of the second millimeter wave radar are different;
- the first millimeter wave radar and the second millimeter wave radar can be used to obtain different measurement information, and the information acquisition manner does not require high-cost real-time dynamic positioning, large data volume image or point cloud information.
- each radar can output up to 32 targets as an example, the data volume is only a few hundred kilobytes (kilobyte, KB) / sec, much smaller than visual image and laser The amount of data in the point cloud.
- the obtaining module 501 is specifically configured to calculate the measurement information by:
- V xc , V yc R ⁇ (V xr , V yr );
- (x c , y c ) represents position information of the stationary target in the vehicle coordinate system
- x c represents horizontal axis coordinates of the stationary target in the vehicle coordinate system
- the y c a vertical axis coordinate indicating the stationary target in the vehicle coordinate system
- the (x r , y r ) indicating position information of the stationary target in the radar coordinate system
- the x r indicating the stationary a horizontal axis coordinate of the target in the radar coordinate system
- the y r represents a vertical axis coordinate of the stationary target in the radar coordinate system
- the R represents the amount of rotation
- the T represents the translation
- (V xc , V yc ) represents speed information of the stationary target in the vehicle coordinate system
- the V xc represents a speed of the stationary target in a horizontal axis direction of the vehicle coordinate system
- V yc represents the velocity of the stationary target in the longitudinal axis direction of the vehicle coordinate system
- the measurement information in the radar coordinate system can be converted into the measurement information in the vehicle coordinate system, and the position information and the speed information are respectively converted, so that the perspective of the vehicle can be taken from the perspective of the vehicle.
- the positioning of the vehicle is completed, which improves the feasibility of the scheme.
- the determining module 502 is specifically configured to calculate an occupation probability of each grid unit in the grid area according to the road boundary information and the historical road boundary information, where the grid area covers the target vehicle.
- the grid area includes a plurality of grid cells;
- the fusion boundary information is determined according to the target grid unit in the probability raster map, wherein the occupancy probability of the target grid unit is greater than a preset probability threshold.
- the road curvature information is calculated according to the fusion boundary information.
- the determining module 502 is specifically configured to calculate an occupation probability of each of the grid cells by:
- p n (x c , y c ) min(p(x c , y c )+p n-1 (x c , y c ), 1);
- the p n (x c , y c ) represents an occupation probability of an n frame raster unit
- the p(x c , y c ) representing the road boundary information
- the p n-1 (x c , y c ) represents the historical road boundary information of the n-1 frame
- the x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the y c represents the stationary target in the vehicle a vertical axis coordinate in a coordinate system
- the (x c , y c ) indicating position information of the stationary target in the vehicle coordinate system
- the (x c , y c )′ represents a plurality of frames of the stationary target
- the S representing a covariance of the x c and the y c .
- the static target information acquired by the millimeter wave radar can be used for local positioning, and the road boundary information solved by the history and the currently solved road boundary information are used for weighted average, thereby obtaining stable road boundary information, so as to obtain stable road boundary information, The reliability of this upgrade program.
- the determining module 502 is specifically configured to calculate the road curvature information by:
- Q represents the road curvature information
- the g ⁇ (x c ) represents the fusion boundary information
- the g ⁇ '(x c ) represents a first derivative of the g ⁇ (x c )
- the g ⁇ "(x c ) represents the second derivative of the g ⁇ (x c ).
- the vehicle positioning device 50 further includes a calculation module 504. And culling module 505;
- the obtaining module 501 is further configured to: after the determining module determines the current road boundary information corresponding to the current frame time according to the measurement information, obtain the to-be-selected still target information and the M reference from the measurement information. Still target information, wherein the M is an integer greater than one;
- the calculating module 504 is configured to calculate an average distance between the M reference stationary target information acquired by the acquiring module 501 and the candidate stationary target information;
- the culling module 505 is configured to remove the candidate static target information from the measurement information if the average distance calculated by the calculation module 504 does not satisfy the preset static target condition;
- the candidate stationary target information is any one of the plurality of static target information
- the reference stationary target information is that the distance between the plurality of stationary target information and the candidate stationary target information is less than a distance The static target information of the preset value.
- the to-be-selected still target information that does not satisfy the preset static target condition can be eliminated, and the static target information that meets the requirement is left for performing subsequent positioning calculation and road boundary information calculation.
- the accuracy of the calculation can be effectively improved.
- the calculating module 504 is specifically configured to calculate the average distance by:
- the d represents the average distance
- the M represents the number of the reference still information
- the P represents the location information of the candidate stationary target information
- the P i represents the ith reference Position information of the still information, the i being an integer greater than 0 and less than or equal to the M.
- the culling module 505 is specifically configured to: if the average distance is greater than a threshold threshold, determine that the average distance does not satisfy the preset static target condition, and remove the candidate static target information from the measurement information.
- the to-be-selected still target information whose average distance is greater than the threshold threshold can be eliminated, and the static target information that meets the requirement is left for performing subsequent positioning calculation and road boundary information calculation. In the above manner, the accuracy of the calculation can be effectively improved.
- the determining module 502 is specifically configured to calculate the road boundary information by:
- f ⁇ (x c ) represents the road boundary information
- the ⁇ 0 represents a first coefficient
- the ⁇ 1 represents a second coefficient
- the ⁇ 2 represents a third coefficient
- the ⁇ 3 represents a a four coefficient
- the x c representing a horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the y c representing a vertical axis coordinate of the stationary target in the vehicle coordinate system
- the (x c , y c ) represents position information of the stationary target in the vehicle coordinate system
- the ⁇ represents a regular term coefficient
- the ⁇ j represents a j-th coefficient
- the j is greater than or equal to 0 and less than or equal to An integer of 3.
- the determining module 502 is specifically configured to calculate, according to the current road boundary information and the historical road boundary information, the stabilization boundary information of the current frame time;
- the fusion boundary information of the current frame time can be calculated according to the road boundary information corresponding to the current frame time and the historical road boundary information, and the vehicle is obtained according to the fusion boundary information of the current frame time to the left boundary of the road.
- the determining module 502 is specifically configured to calculate the stabilization boundary information corresponding to the current frame moment by:
- the f ⁇ ' represents the stabilization boundary information corresponding to the current frame time
- the f ⁇ _w (x c ) represents historical road boundary information corresponding to the wth frame
- the W represents the history The number of road boundary information
- the x c indicating the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the ⁇ indicating the lane boundary average of the W frame.
- a method for calculating the stabilization boundary information is introduced, and the fusion boundary information calculated by the method has good reliability and is operable.
- the determining module 502 is specifically configured to calculate the first target positioning information of the current frame moment by:
- the location represents the first target positioning information of the current frame time
- the ceil represents a rounding calculation manner
- the R L represents the target vehicle to the left side boundary of the road.
- the R R represents a second distance from the target vehicle to the right side boundary of the road
- the D represents the width of the lane
- the N represents the number of lanes.
- a method for calculating the first target positioning information is introduced, and the first target positioning information calculated by the method has good reliability and is operable.
- the measurement information further includes: at least one moving target information
- the obtaining module 501 is further configured to: after the determining module 502 determines the first target positioning information according to the current road boundary information, acquire the at least one moving target information from the measurement information, where each motion The target information carries a target number, and the target number is used to calibrate different moving targets;
- the determining module is further configured to determine lane occupying information according to the at least one moving target information acquired by the acquiring module and the corresponding historical moving target information;
- the determining module is further configured to determine second target positioning information corresponding to the current frame time according to the lane occupying information, where the second target positioning information is used to indicate that the target vehicle is located in a road position.
- a plurality of stationary target information and moving target information are simultaneously acquired by the millimeter wave radar, and the road boundary information is calculated by combining the two to realize the positioning of the vehicle.
- the moving target information can assist the static target information to calculate the road boundary information, so that the vehicle positioning can be accurately completed when the traffic volume is large, thereby improving the feasibility and flexibility of the solution, and increasing the confidence of the positioning. degree.
- the acquiring module 501 is specifically configured to acquire K-frame moving target information data according to the at least one moving target information and the historical moving target information corresponding to the at least one moving target information, where the K is a positive integer;
- the determining module 502 is specifically configured to determine the L k lanes that are not occupied as the second target positioning information corresponding to the current frame moment.
- the K-frame moving target information data is acquired according to the at least one moving target information of the current frame time and the at least one moving target information and the corresponding historical moving target information, and the moving target information and the history according to the current frame time are obtained.
- the moving target information acquires a case where the L kth lane is occupied in the k images.
- the determining module 502 is specifically configured to determine, according to the second target positioning information, a confidence level of the first target positioning information, where the confidence level is used to indicate a credibility level of the first target positioning information;
- the second target positioning information determined by the moving target information can be used to determine the confidence level of the first target positioning information, and the confidence level indicates the degree of the segment estimation, thereby improving the feasibility of the fusion positioning. And practicality.
- the embodiment of the present invention further provides another vehicle positioning device. As shown in FIG. 20, for the convenience of description, only parts related to the embodiment of the present invention are shown. If the specific technical details are not disclosed, please refer to the embodiment of the present invention. Method part.
- the vehicle positioning device may be any terminal device including a mobile phone, a tablet computer, a personal digital assistant (PDA), a point of sales (POS), a vehicle-mounted computer, and the like, and the vehicle positioning device is used as a mobile phone as an example:
- FIG. 20 is a block diagram showing a partial structure of a mobile phone related to a terminal provided by an embodiment of the present invention.
- the mobile phone includes: a radio frequency (RF) circuit 610, a memory 620, an input unit 630, a display unit 640, a sensor 650, an audio circuit 660, a wireless fidelity (WiFi) module 670, and a processor 680. And power supply 690 and other components.
- RF radio frequency
- the structure of the handset shown in FIG. 20 does not constitute a limitation to the handset, and may include more or less components than those illustrated, or some components may be combined, or different components may be arranged.
- the RF circuit 610 can be used for transmitting and receiving information or during a call, and receiving and transmitting the signal. Specifically, after receiving the downlink information of the base station, the processor 680 processes the data. In addition, the uplink data is designed to be sent to the base station. Generally, RF circuit 610 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like. In addition, RF circuitry 610 can also communicate with the network and other devices via wireless communication. The above wireless communication may use any communication standard or protocol, including but not limited to Global System of Mobile communication (GSM), General Packet Radio Service (GPRS), Code Division Multiple Access (Code Division). Multiple Access (CDMA), Wideband Code Division Multiple Access (WCDMA), Long Term Evolution (LTE), E-mail, Short Messaging Service (SMS), and the like.
- GSM Global System of Mobile communication
- GPRS General Packet Radio Service
- the memory 620 can be used to store software programs and modules, and the processor 680 executes various functional applications and data processing of the mobile phone by running software programs and modules stored in the memory 620.
- the memory 620 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application required for at least one function (such as a sound playing function, an image playing function, etc.), and the like; the storage data area may be stored according to Data created by the use of the mobile phone (such as audio data, phone book, etc.).
- memory 620 can include high speed random access memory, and can also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid state storage device.
- the input unit 630 can be configured to receive input numeric or character information and to generate key signal inputs related to user settings and function controls of the handset.
- the input unit 630 may include a touch panel 631 and other input devices 632.
- the touch panel 631 also referred to as a touch screen, can collect touch operations on or near the user (such as the user using a finger, a stylus, or the like on the touch panel 631 or near the touch panel 631. Operation), and drive the corresponding connecting device according to a preset program.
- the touch panel 631 can include two parts: a touch detection device and a touch controller.
- the touch detection device detects the touch orientation of the user, and detects a signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts the touch information into contact coordinates, and sends the touch information.
- the processor 680 is provided and can receive commands from the processor 680 and execute them.
- the touch panel 631 can be implemented in various types such as resistive, capacitive, infrared, and surface acoustic waves.
- the input unit 630 may also include other input devices 632.
- other input devices 632 may include, but are not limited to, one or more of a physical keyboard, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and the like.
- the display unit 640 can be used to display information input by the user or information provided to the user as well as various menus of the mobile phone.
- the display unit 640 can include a display panel 641.
- the display panel 641 can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), or the like.
- the touch panel 631 can cover the display panel 641. When the touch panel 631 detects a touch operation on or near it, the touch panel 631 transmits to the processor 680 to determine the type of the touch event, and then the processor 680 according to the touch event. The type provides a corresponding visual output on display panel 641.
- the touch panel 631 and the display panel 641 are two independent components to implement the input and input functions of the mobile phone, in some embodiments, the touch panel 631 may be integrated with the display panel 641. Realize the input and output functions of the phone.
- the handset can also include at least one type of sensor 650, such as a light sensor, motion sensor, and other sensors.
- the light sensor may include an ambient light sensor and a proximity sensor, wherein the ambient light sensor may adjust the brightness of the display panel 641 according to the brightness of the ambient light, and the proximity sensor may close the display panel 641 and/or when the mobile phone moves to the ear. Or backlight.
- the accelerometer sensor can detect the magnitude of acceleration in all directions (usually three axes). When it is stationary, it can detect the magnitude and direction of gravity.
- the mobile phone can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping), etc.; as for the mobile phone can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, no longer Narration.
- the gesture of the mobile phone such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration
- vibration recognition related functions such as pedometer, tapping
- the mobile phone can also be configured with gyroscopes, barometers, hygrometers, thermometers, infrared sensors and other sensors, no longer Narration.
- Audio circuit 660, speaker 661, and microphone 662 provide an audio interface between the user and the handset.
- the audio circuit 660 can transmit the converted electrical data of the received audio data to the speaker 661 for conversion to the sound signal output by the speaker 661; on the other hand, the microphone 662 converts the collected sound signal into an electrical signal by the audio circuit 660. After receiving, it is converted into audio data, and then processed by the audio data output processor 680, sent to the other mobile phone via the RF circuit 610, or outputted to the memory 620 for further processing.
- WiFi is a short-range wireless transmission technology
- the mobile phone can help users to send and receive emails, browse web pages, and access streaming media through the WiFi module 670, which provides users with wireless broadband Internet access.
- FIG. 20 shows the WiFi module 670, it can be understood that it does not belong to the essential configuration of the mobile phone, and may be omitted as needed within the scope of not changing the essence of the invention.
- the processor 680 is the control center of the handset, and connects various portions of the entire handset using various interfaces and lines, by executing or executing software programs and/or modules stored in the memory 620, and invoking data stored in the memory 620, executing The phone's various functions and processing data, so that the overall monitoring of the phone.
- the processor 680 may include one or more processing units; optionally, the processor 680 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, and an application. Etc.
- the modem processor primarily handles wireless communications. It will be appreciated that the above described modem processor may also not be integrated into the processor 680.
- the handset also includes a power supply 690 (such as a battery) that powers the various components.
- a power supply 690 (such as a battery) that powers the various components.
- the power supply can be logically coupled to the processor 680 through a power management system to manage charging, discharging, and power management functions through the power management system.
- the mobile phone may further include a camera, a Bluetooth module, and the like, and details are not described herein again.
- the processor 680 included in the terminal further has the following functions:
- the measurement information within the preset angle range is acquired by the measurement device, wherein the measurement information includes a plurality of static target information, the plurality of static target information being used to represent information of the plurality of stationary targets,
- the plurality of stationary target information are in one-to-one correspondence with the information of the plurality of stationary targets;
- Determining road curvature information according to the current road boundary information and historical road boundary information wherein the road curvature information is used to indicate a degree of bending of the road where the target vehicle is located, and the historical road boundary information includes at least one historical frame time Corresponding road boundary information, where the historical frame time is a time when the road boundary information and the road curvature information are acquired before the current frame time;
- the first target positioning information and the road curvature information are output.
- processor 680 is specifically configured to perform the following steps:
- the millimeter wave radar Obtaining, by the millimeter wave radar, tracking information of the plurality of stationary targets in the preset angle range, wherein the tracking information includes position information and speed information of the plurality of stationary targets in a radar coordinate system;
- the measurement information includes position information and speed information of the plurality of stationary targets in a vehicle coordinate system
- the calibration parameters include The amount of rotation and the amount of translation.
- processor 680 is specifically configured to perform the following steps:
- the preset angle range includes a first preset angle range and a second preset angle range
- the first millimeter wave radar Obtaining, by the first millimeter wave radar, first tracking information of the plurality of first stationary targets in the first preset angle range, and acquiring, by the second millimeter wave radar, the plurality of second static in the second preset angle range Second tracking information of the target, wherein the tracking information includes the first tracking information and the second tracking information, the plurality of stationary targets including the plurality of first stationary targets and the plurality of second a stationary target, the millimeter wave radar including the first millimeter wave radar and the second millimeter wave radar, a detection distance and a coverage angle of the first millimeter wave radar and a detection distance of the second millimeter wave radar Different coverage angles;
- processor 680 is specifically configured to perform the following steps:
- the measurement information is calculated by:
- V xc , V yc R ⁇ (V xr , V yr );
- (x c , y c ) represents position information of the stationary target in the vehicle coordinate system
- x c represents horizontal axis coordinates of the stationary target in the vehicle coordinate system
- the y c a vertical axis coordinate indicating the stationary target in the vehicle coordinate system
- the (x r , y r ) indicating position information of the stationary target in the radar coordinate system
- the x r indicating the stationary a horizontal axis coordinate of the target in the radar coordinate system
- the y r represents a vertical axis coordinate of the stationary target in the radar coordinate system
- the R represents the amount of rotation
- the T represents the translation
- (V xc , V yc ) represents speed information of the stationary target in the vehicle coordinate system
- the V xc represents a speed of the stationary target in a horizontal axis direction of the vehicle coordinate system
- V yc represents the velocity of the stationary target in the longitudinal axis direction of the vehicle coordinate system
- processor 680 is further configured to perform the following steps:
- the road curvature information is calculated according to the fusion boundary information.
- processor 680 is specifically configured to perform the following steps:
- the occupancy probability of each of the grid cells is calculated as follows:
- p n (x c , y c ) min(p(x c , y c )+p n-1 (x c , y c ), 1);
- the p n (x c , y c ) represents an occupation probability of an n frame raster unit
- the p(x c , y c ) representing the road boundary information
- the p n-1 (x c , y c ) represents the historical road boundary information of the n-1 frame
- the x c represents the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the y c represents the stationary target in the vehicle a vertical axis coordinate in a coordinate system
- the (x c , y c ) indicating position information of the stationary target in the vehicle coordinate system
- the (x c , y c )′ represents a plurality of frames of the stationary target
- the S representing a covariance of the x c and the y c .
- processor 680 is specifically configured to perform the following steps:
- the road curvature information is calculated by:
- Q represents the road curvature information
- the g ⁇ (x c ) represents the fusion boundary information
- the g ⁇ '(x c ) represents a first derivative of the g ⁇ (x c )
- the g ⁇ "(x c ) represents the second derivative of the g ⁇ (x c ).
- processor 680 is further configured to perform the following steps:
- the candidate stationary target information is removed from the measurement information
- the candidate stationary target information is any one of the plurality of static target information
- the reference stationary target information is that the distance between the plurality of stationary target information and the candidate stationary target information is less than a distance The static target information of the preset value.
- processor 680 is specifically configured to perform the following steps:
- the average distance is calculated as follows:
- the d represents the average distance
- the M represents the number of the reference still information
- the P represents the location information of the candidate stationary target information
- the P i represents the ith reference Position information of the still information, the i being an integer greater than 0 and less than or equal to the M.
- processor 680 is specifically configured to perform the following steps:
- the threshold threshold it is determined that the average distance does not satisfy the preset stationary target condition, and the candidate stationary target information is removed from the measurement information.
- processor 680 is specifically configured to perform the following steps:
- the road boundary information is calculated by:
- f ⁇ (x c ) represents the road boundary information
- the ⁇ 0 represents a first coefficient
- the ⁇ 1 represents a second coefficient
- the ⁇ 2 represents a third coefficient
- the ⁇ 3 represents a a four coefficient
- the x c representing a horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the y c representing a vertical axis coordinate of the stationary target in the vehicle coordinate system
- the (x c , y c ) represents position information of the stationary target in the vehicle coordinate system
- the ⁇ represents a regular term coefficient
- the ⁇ j represents a j-th coefficient
- the j is greater than or equal to 0 and less than or equal to An integer of 3.
- processor 680 is specifically configured to perform the following steps:
- processor 680 is specifically configured to perform the following steps:
- the f ⁇ ' represents the stabilization boundary information corresponding to the current frame time
- the f ⁇ _w (x c ) represents historical road boundary information corresponding to the wth frame
- the W represents the history The number of road boundary information
- the x c indicating the horizontal axis coordinate of the stationary target in the vehicle coordinate system
- the ⁇ indicating the lane boundary average of the W frame.
- processor 680 is specifically configured to perform the following steps:
- the location represents the first target positioning information of the current frame time
- the ceil represents a rounding calculation manner
- the R L represents the target vehicle to the left side boundary of the road.
- the R R represents a second distance from the target vehicle to the right side boundary of the road
- the D represents the width of the lane
- the N represents the number of lanes.
- processor 680 is further configured to perform the following steps:
- each moving target information carries a target number, and the target number is used to calibrate different moving targets;
- processor 680 is specifically configured to perform the following steps:
- the L k lanes that are not occupied are determined as the second target positioning information corresponding to the current frame moment.
- processor 680 is specifically configured to perform the following steps:
- the computer program product includes one or more computer instructions.
- the computer can be a general purpose computer, a special purpose computer, a computer network, or other programmable device.
- the computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be from a website site, computer, server or data center Transmission to another website site, computer, server or data center via wired (eg coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (eg infrared, wireless, microwave, etc.).
- wired eg coaxial cable, fiber optic, digital subscriber line (DSL)
- wireless eg infrared, wireless, microwave, etc.
- the computer readable storage medium can be any available media that can be stored by a computer or a data storage device such as a server, data center, or the like that includes one or more available media.
- the usable medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a DVD), or a semiconductor medium (eg, a solid state disk (SSD)) or the like.
- the disclosed system, apparatus, and method may be implemented in other manners.
- the device embodiments described above are merely illustrative.
- the division of the unit is only a logical function division.
- there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
- the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
- the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
- each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
- the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
- the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
- a computer readable storage medium A number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present application.
- the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like, which can store program code. .
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Computer Networks & Wireless Communication (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Health & Medical Sciences (AREA)
- Electromagnetism (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
- Radar Systems Or Details Thereof (AREA)
Abstract
提供了一种车辆定位的方法及装置,车辆定位的方法包括:在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,测量信息包括多个静止目标信息(201);根据测量信息确定当前帧时刻所对应的当前道路边界信息(202);根据当前道路边界信息确定第一目标定位信息,第一目标定位信息用于表示目标车辆在道路中所在的位置(203);根据当前道路边界信息与历史道路边界信息确定道路曲率信息,道路曲率信息用于表示目标车辆所在道路的弯曲程度(204);输出第一目标定位信息和道路曲率信息(205)。该方法可以提升定位信息的置信度和可靠性,且估计出车辆所在车道的弯曲度,从而提升车辆定位的准确性。
Description
本申请要求于2018年1月16日提交中国专利局、申请号为201810040981.0、发明名称为“一种车辆定位的方法以及车辆定位装置”的中国专利申请的优先权,其全部内容通过引用结合在本申请中。
本申请涉及信号处理技术领域,尤其涉及一种车辆定位的方法以及车辆定位装置。
在中心城区、隧道以及非规则道路情况下,为了完成车道级的驾驶规划引导,需要知道车辆相对周围道路环境的信息,即包含车辆相对周围道路环境的局部位置信息以及车辆周围道路的元素信息(如道路曲率等)。
目前,车辆定位主要依靠全球定位系统(global position system,GPS)、实时动态定位(real-time kinematic,RTK)、摄像头及激光雷达等方式来完成。一种常见的车辆定位方式为综合预先存储的地图、GPS位置信息及毫米波测量信息判断车辆可能存在的位置,并计算该车辆可能存在的位置出现概率,以此确定车辆所在的具体位置。
然而,在车辆上安装的前向雷达覆盖视角通常较窄,因此,在非结构化的道路(如曲折小巷等道路)上难以准确地估计车辆与周边目标之间的位置关系,从而会降低车辆定位的准确性。
发明内容
本申请提供了一种车辆定位的方法以及车辆定位装置,可以在中心城区、隧道以及非规则道路定位,提升定位的置信度和可靠性,此外,通过道路曲率信息能够更好的辅助车辆规划控制系统,以规划车辆行驶轨迹。
有鉴于此,本申请第一方面提供一种车辆定位的方法,该方法可以解决在中心城区、隧道以及非规则道路的情况下,高级辅助驾驶以及自动驾驶车道级定位,从而辅助完成更好的车辆规划控制。车辆定位的方法具体可以包括如下几个步骤:
首先,在当前帧时刻,车辆定位装置通过测量设备获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息,多个静止目标信息用于表示多个静止目标的信息,多个静止目标信息与多个静止目标的信息一一对应。通常情况下,静止目标可以是路边的树、护栏或者交通信号灯等不会随意移动的物体。接下来,车辆定位装置根据测量信息确定当前帧时刻所对应的当前道路边界信息,再根据当前道路边界信息确定第一目标定位信息,其中,第一目标定位信息用于表示目标车辆在道路中所在的位置。比如,可以表示成当前时刻自车在六个车道中自左向右的第三个车道。
然后车辆定位装置根据当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示目标车辆所在道路的弯曲程度,历史道路边界信息包括至少一 个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻。结合当前帧时刻和历史帧时刻的信息进行计算,充分地考虑到一段时间内自车的行驶情况,使得得到的结果具有更强的可靠性。
最后,车辆定位装置通过输出设备输出第一目标定位信息和道路曲率信息。
可见,由于测量设备会进行主动测量,因此在可视范围内受光线气候影响很小,在中心城区、隧道涵洞和非理想气象条件下,采用测量设备可以得到车辆与四周目标之间的位置关系,从而确定车辆在道路中的定位信息,由此提升定位信息的置信度和可靠性。此外,通过这些位置关系确定道路曲率信息,该道路曲率信息能够估计出车辆所在车道的弯曲度,从而提升车辆定位的准确性。在高级辅助驾驶或自动驾驶车道级定位中辅助完成更好的车辆规划控制。
在一种可能的设计中,在本申请实施例的第一方面的第一种实现方式中,车辆定位装置通过测量设备获取预置角度范围内的测量信息,可以包括如下的步骤:
首先,由车辆定位装置通过毫米波雷达获取预置角度范围内多个静止目标的跟踪信息,其中,跟踪信息包括多个静止目标在雷达坐标系中的位置信息和速度信息,然后根据跟踪信息以及毫米波雷达的标定参数计算测量信息,其中,测量信息包括多个静止目标在车辆坐标系中的位置信息和速度信息,标定参数包括旋转量和平移量。
雷达坐标系是用于获取跟踪信息的坐标系,而车辆坐标系是以目标车辆为原点建立的坐标。
可见,采用中长距离毫米波雷达以及短距离毫米波雷达,用于获取车辆环向的静止目标信息和运动目标信息。毫米波雷达频带极宽,适用于各种宽带信号处理,还具备角度分辨和跟踪能力,且有较宽的多普勒宽带,多普勒效应明显,具有良好的多普勒分辨力,毫米波雷达波长短,对目标的散射特性描述精准、细密且测速精度较高。
在一种可能的设计中,在本申请实施例的第一方面的第二种实现方式中,预置角度范围包括第一预置角度范围和第二预置角度范围;
其中,车辆定位装置通过毫米波雷达获取预置角度范围内多个静止目标的跟踪信息,可以包括如下的步骤:
车辆定位装置通过第一毫米波雷达获取第一预置角度范围内多个第一静止目标的第一跟踪信息,并通过第二毫米波雷达获取第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,跟踪信息包括第一跟踪信息和第二跟踪信息,多个静止目标包括多个第一静止目标和多个第二静止目标,毫米波雷达包括第一毫米波雷达和第二毫米波雷达,第一毫米波雷达的探测距离和覆盖视角与第二毫米波雷达的探测距离和覆盖视角不同,
如果第一毫米波雷达的探测距离大于第二毫米波的探测距离,那么第二毫米波雷达的覆盖范围大于第一毫米波雷达的覆盖范围,这是因为探测距离越远,覆盖范围越小,反之,如果第一毫米波雷达的探测距离小于第二毫米波的探测距离,那么第二毫米波雷达的覆盖范围小于第一毫米波雷达的覆盖范围,这是因为探测距离越近,覆盖范围越大。
车辆定位装置根据跟踪信息以及毫米波雷达的标定参数计算测量信息,可以包括如下的步骤:
车辆定位装置根据第一跟踪信息以及毫米波雷达的标定参数计算第一预置角度范围内的第一测量信息,并根据第二跟踪信息以及毫米波雷达的标定参数计算第二预置角度范围内的第二测量信息,其中,测量信息包括第一测量信息和第二测量信息。
可见,本申请实施例中,提出可以采用第一毫米波雷达和第二毫米波雷达获取不同的测量信息,这种信息获取的方式无需高成本的实时动态定位、大数据量图像或点云信息,主要依靠毫米波雷达的信息,以5个毫米波雷达,每个雷达最多输出32个目标为例,数据量仅为几百千字节每秒,远小于视觉图像和激光点云的数据量。
在一种可能的设计中,在本申请实施例的第一方面的第三种实现方式中,车辆定位装置可以通过如下方式计算测量信息:
(x
c,y
c)=R×(x
r,y
r)+T;
(V
xc,V
yc)=R×(V
xr,V
yr);
其中,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
r,y
r)表示静止目标在雷达坐标系下的位置信息,x
r表示静止目标在雷达坐标系中的横轴坐标,y
r表示静止目标在雷达坐标系中的纵轴坐标,R表示旋转量,T表示平移量,(V
xc,V
yc)表示静止目标在车辆坐标系下的速度信息,V
xc表示静止目标在车辆坐标系中横轴方向的速度,V
yc表示静止目标在车辆坐标系中纵轴方向的速度,(V
xr,V
yr)表示静止目标在雷达坐标系中下的速度信息,V
xr表示静止目标在雷达坐标系中横轴方向的速度,V
yr表示静止目标在雷达坐标系中纵轴方向的速度。
可见,本申请实施例中,可以将雷达坐标系下的测量信息转换为车辆坐标系下的测量信息,并且在位置信息和速度信息上均进行了相应的转换,从而能够以自车的视角来完成车辆的定位,提升了方案的可行性。
在一种可能的设计中,在本申请实施例的第一方面的第四种实现方式中,车辆定位装置根据道路边界信息与历史道路边界信息确定道路曲率信息,可以包括如下的步骤:
首先,车辆定位装置根据道路边界信息以及历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,栅格区域覆盖于目标车辆,栅格区域会跟踪目标车辆,栅格区域包含多个栅格单元。然后,车辆定位装置根据栅格区域中每个栅格单元的占据概率获取概率栅格图,再通过概率栅格图中的目标栅格单元确定融合边界信息,其中,目标栅格单元的占据概率大于预设概率门限,通常情况下,目标栅格单元的占据概率趋近于1。最后,车辆定位装置根据融合边界信息计算道路曲率信息。
可见,本申请实施例中,通过融合多帧测量信息、道路边界信息以及历史道路边界信息,可以得到车辆的局部概率栅格图,并且可以从概率栅格图中计算道路曲率信息,从而有利于提升方案的可行性。
在一种可能的设计中,在本申请实施例的第一方面的第五种实现方式中,车辆定位装置可以通过如下方式计算每个栅格单元的占据概率:
p
n(x
c,y
c)=min(p(x
c,y
c)+p
n-1(x
c,y
c),1);
其中,p
n(x
c,y
c)表示n帧栅格单元的占据概率,p(x
c,y
c)表示道路边界信息,p
n-1(x
c,y
c)表示n-1帧的历史道路边界信息,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,(x
c,y
c)'表示多帧静止目标在车辆坐标系下的位置信息的平均值,S表示x
c和y
c的协方差。
可见,本申请实施例中,可以利用毫米波雷达获取到的静止目标信息进行局部定位,利用历史求解的道路边界信息和当前求解的道路边界信息进行加权平均,从而得到稳定的道路边界信息,以此提升方案的可靠性。
在一种可能的设计中,在本申请实施例的第一方面的第六种实现方式中,车辆定位装置可以通过如下方式计算道路曲率信息:
其中,Q表示道路曲率信息,g
θ(x
c)表示融合边界信息,g
θ'(x
c)表示g
θ(x
c)的一阶导数,g
θ″(x
c)表示g
θ(x
c)的二阶导数。
可见,本申请实施例中,提供了一种计算道路曲率信息的实现方式,通过具体的计算方式能够得到所需的定位信息,从而提升了方案的可操作性。
在一种可能的设计中,在本申请实施例的第一方面的第七种实现方式中,车辆定位装置在根据测量信息确定当前帧时刻所对应的当前道路边界信息之前,还可以执行如下步骤:
首先,车辆定位装置从测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,M为大于1的整数,通常情况下可以选择5个参考静止目标信息。然后计算M个参考静止目标信息到待选静止目标信息之间的平均距离,假设有5个参考静止目标,根据每个参考静止目标到待选静止目标的距离计算平均后的距离。
如果计算得到的平均距离不满足预设静止目标条件,则车辆定位装置会从测量信息中剔除待选静止目标信息。其中,待选静止目标信息为多个静止目标信息中的任一个,参考静止目标信息为多个静止目标信息中与待选静止目标信息之间距离小于距离预设值的静止目标信息。
可见,本申请实施例中,可以将不满足预设静止目标条件的待选静止目标信息进行剔除,剩下满足要求的静止目标信息,用于进行后续的定位计算和道路边界信息的计算。通过上述方式,能够有效地提升计算的准确性。
在一种可能的设计中,在本申请实施例的第一方面的第八种实现方式中,车辆定位装置可以通过如下方式计算平均距离:
其中,d表示平均距离,M表示参考静止信息的个数,P表示待选静止目标信息的位置信息,P
i表示第i个参考静止信息的位置信息,i为大于0且小于或等于M的整数。
可见,本申请实施例中,介绍了一种计算平均距离的方式,通过该方式计算得到的平 均距离具有较好的可靠性,且具有可操作性。
在一种可能的设计中,在本申请实施例的第一方面的第九种实现方式中,若平均距离不满足预设静止目标条件,则车辆定位装置从测量信息中剔除待选静止目标信息,可以包括如下的步骤:
如果计算得到的平均距离大于阈值门限,则车辆定位装置确定平均距离不满足预设静止目标条件,于是将从测量信息中剔除待选静止目标信息。
可见,本申请实施例中,可以将平均距离大于阈值门限的待选静止目标信息进行剔除,剩下满足要求的静止目标信息,用于进行后续的定位计算和道路边界信息的计算。通过上述方式,能够有效地提升计算的准确性。
在一种可能的设计中,在本申请实施例的第一方面的第十种实现方式中,车辆定位装置可以通过如下方式计算道路边界信息:
f
θ(x
c)=θ
0+θ
1×x
c+θ
2×x
c
2+θ
3×x
c
3;
其中,f
θ(x
c)表示道路边界信息,θ
0表示第一系数,θ
1表示第二系数,θ
2表示第三系数,θ
3表示第四系数,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,λ表示正则项系数,θ
j表示第j个系数,j为大于或等于0且小于或等于3的整数。
可见,本申请实施例中,介绍了一种计算道路边界信息的方式,通过该方式计算得到的道路边界信息具有较好的可靠性,且具有可操作性。
在一种可能的设计中,在本申请实施例的第一方面的第十一种实现方式中,车辆定位装置根据当前帧时刻所对应的道路边界信息确定第一目标定位信息,可以包括如下的步骤:
首先,车辆定位装置根据当前道路边界信息以及历史道路边界信息计算当前帧时刻的增稳边界信息,然后根据当前帧时刻的增稳边界信息获取目标车辆到至道路左侧边界的第一距离,以及目标车辆至道路右侧边界的第二距离,最后车辆定位装置根据第一距离和第二距离计算得到当前帧时刻的第一目标定位信息。
其中,增稳边界信息与融合边界信息之间的关系好比是“线”和“面”的关系,多个增稳边界信息能够得到一个融合边界信息。
可见,本申请实施例中,可以根据当前帧时刻所对应的道路边界信息以及历史道路边界信息计算当前帧时刻的融合边界信息,根据当前帧时刻的融合边界信息获取车辆到至道路左侧边界的第一距离,以及车辆至道路右侧边界的第二距离,最后根据第一距离和第二距离计算得到当前帧时刻的第一目标定位信息。通过上述方式,能够提升第一目标定位信息的可靠性,也为方案的实行提供了一种可行的方式,从而增强方案的灵活性。
在一种可能的设计中,在本申请实施例的第一方面的第十二种实现方式中,车辆定位装可以通过如下方式计算当前帧时刻所对应的增稳边界信息:
其中,f
θ'表示当前帧时刻所对应的增稳边界信息,f
θ_w(x
c)表示第w帧所对应的历史道路边界信息,W表示历史道路边界信息的个数,x
c表示静止目标在车辆坐标系中的横轴坐标,μ表示W帧的车道边界平均值。
可见,本申请实施例中,介绍了一种计算增稳边界信息的方式,通过该方式计算得到的融合边界信息具有较好的可靠性,且具有可操作性。
在一种可能的设计中,在本申请实施例的第一方面的第十三种实现方式中,车辆定位装置可以通过如下方式计算当前帧时刻所的第一目标定位信息:
Location=(ceil(R
R-D),ceil(R
L-D));
D=(R
L+R
R)/N;
其中,Location表示当前帧时刻的第一目标定位信息,ceil表示向上取整的计算方式,R
L表示目标车辆到至道路左侧边界的第一距离,R
R表示目标车辆至道路右侧边界的第二距离,D表示车道的宽度,N表示车道的数量。
可见,本申请实施例中,介绍了一种计算第一目标定位信息的方式,通过该方式计算得到的第一目标定位信息具有较好的可靠性,且具有可操作性。
在一种可能的设计中,在本申请实施例的第一方面的第十四种实现方式中,测量信息还可以包括至少一个运动目标信息,在车辆定位装置根据当前道路边界信息确定第一目标定位信息之前,还可以包括如下步骤:
首先,车辆定位装置从测量信息中获取至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,目标编号用于标定不同的运动目标,运动目标通常是指在道路上运动的车辆,当然,也可以是自行车、摩托车或者其他类型的机车。
然后,车辆定位装置根据至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息,最后根据车道占据信息确定当前帧时刻所对应的第二目标定位信息,其中,第二目标定位信息用于表示目标车辆在道路中所在的位置。
可见,本申请实施例中,通过毫米波雷达同时获取多个静止目标信息和运动目标信息,结合两者进行道路边界信息的计算,以实现车辆的定位。采用运动目标信息可以辅助静止目标信息进行道路边界信息的计算,从而能够在车流量较大的时候,也能准确地完成车辆定位,以此提升方案的可行性和灵活性,并增加定位的置信度。
在一种可能的设计中,在本申请实施例的第一方面的第十五种实现方式中,车辆定位装置根据当前帧时刻的至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息,可以包括如下步骤:
首先,车辆定位装置根据至少一个运动目标信息以及至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,K为正整数,然后根据至少一个运动目标信息以及至少一个运动目标信息对应的历史运动目标信息获取k帧中第L
k个车道被占据的情况,其中,k为大于0且小于或等于K的整数;
如果车道占据比值小于预设比值,那么车辆定位装置可以确定第L
k个车道被占据,其中,车道占据比值为k个帧与K个帧的比值。反之,如果车道占据比值大于或等于预设比值,则车辆定位装置可以确定第L
k个车道未被占据,还可以将未被占据的第L
k个车道确定 为当前帧时刻所对应的第二目标定位信息。
可见,本申请实施例中,根据当前帧时刻的至少一个运动目标信息以及至少一个运动目标信息以及对应的历史运动目标信息获取K帧运动目标信息数据,并根据当前帧时刻的运动目标信息以及历史运动目标信息获取k个图像中第L
k个车道被占据的情况。通过上述方式,可以更准确地确定车道被占据的情况,从而提升方案的实用性和可靠性。
在一种可能的设计中,在本申请实施例的第一方面的第十六种实现方式中,车辆定位装置根据当前帧时刻所对应的道路边界信息确定第一目标定位信息,可以包括如下的步骤:
车辆定位装置首先根据第二目标定位信息确定第一目标定位信息的置信度,其中,置信度用于表示第一目标定位信息的可信程度,置信度可以表示为百分数。然后车辆定位装置根据置信度确定当前时刻的第一目标定位信息。
如果置信度特别低,很可能定位出现故障,这种情况下可以再次进行定位,或者触发报警通知。
可见,本申请实施例中,由运动目标信息确定的第二目标定位信息可用于确定第一目标定位信息的置信水平,置信水平表示区间估计的把握程度,由此,提升了融合定位的可行性和实用性。
本申请第二方面提供一种车辆定位装置,可以包括:
获取模块,用于在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息,多个静止目标信息用于表示多个静止目标的信息,多个静止目标信息与多个静止目标的信息一一对应;
确定模块,用于根据获取模块获取的测量信息确定当前帧时刻所对应的当前道路边界信息;
确定模块,用于根据当前道路边界信息确定第一目标定位信息,其中,第一目标定位信息用于表示目标车辆在道路中所在的位置;
确定模块,用于根据当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示目标车辆所在道路的弯曲程度,历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;
输出模块,用于输出确定模块确定的第一目标定位信息和确定模块确定的道路曲率信息。
在一种可能的设计中,在本申请实施例的第二方面的第一种实现方式中,
获取模块,具体用于通过毫米波雷达获取预置角度范围内多个静止目标的跟踪信息,其中,跟踪信息包括多个静止目标在雷达坐标系中的位置信息和速度信息;
根据跟踪信息以及毫米波雷达的标定参数计算测量信息,其中,测量信息包括多个静止目标在车辆坐标系中的位置信息和速度信息,标定参数包括旋转量和平移量。
在一种可能的设计中,在本申请实施例的第二方面的第二种实现方式中,
预置角度范围包括第一预置角度范围和第二预置角度范围;
获取模块,具体用于通过第一毫米波雷达获取第一预置角度范围内多个第一静止目标 的第一跟踪信息,并通过第二毫米波雷达获取第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,跟踪信息包括第一跟踪信息和第二跟踪信息,多个静止目标包括多个第一静止目标和多个第二静止目标,毫米波雷达包括第一毫米波雷达和第二毫米波雷达,第一毫米波雷达的探测距离和覆盖视角与第二毫米波雷达的探测距离和覆盖视角不同;
根据跟踪信息以及毫米波雷达的标定参数计算测量信息,包括:
根据第一跟踪信息以及毫米波雷达的标定参数计算第一预置角度范围内的第一测量信息,并根据第二跟踪信息以及毫米波雷达的标定参数计算第二预置角度范围内的第二测量信息,其中,测量信息包括第一测量信息和第二测量信息。
在一种可能的设计中,在本申请实施例的第二方面的第三种实现方式中,
获取模块,具体用于通过如下方式计算测量信息:
(x
c,y
c)=R×(x
r,y
r)+T
;
(V
xc,V
yc)=R×(V
xr,V
yr);
其中,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
r,y
r)表示静止目标在雷达坐标系下的位置信息,x
r表示静止目标在雷达坐标系中的横轴坐标,y
r表示静止目标在雷达坐标系中的纵轴坐标,R表示旋转量,T表示平移量,(V
xc,V
yc)表示静止目标在车辆坐标系下的速度信息,V
xc表示静止目标在车辆坐标系中横轴方向的速度,V
yc表示静止目标在车辆坐标系中纵轴方向的速度,(V
xr,V
yr)表示静止目标在雷达坐标系中下的速度信息,V
xr表示静止目标在雷达坐标系中横轴方向的速度,V
yr表示静止目标在雷达坐标系中纵轴方向的速度。
在一种可能的设计中,在本申请实施例的第二方面的第四种实现方式中,
确定模块,具体用于根据道路边界信息以及历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,栅格区域覆盖于目标车辆,栅格区域包含多个栅格单元;
根据栅格区域中每个栅格单元的占据概率获取概率栅格图;
根据概率栅格图中的目标栅格单元确定融合边界信息,其中,目标栅格单元的占据概率大于预设概率门限。
根据融合边界信息计算道路曲率信息。
在一种可能的设计中,在本申请实施例的第二方面的第五种实现方式中,
确定模块,具体用于通过如下方式计算每个栅格单元的占据概率:
p
n(x
c,y
c)=min(p(x
c,y
c)+p
n-1(x
c,y
c),1);
其中,p
n(x
c,y
c)表示n帧栅格单元的占据概率,p(x
c,y
c)表示道路边界信息,p
n-1(x
c,y
c)表示n-1帧的历史道路边界信息,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,(x
c,y
c)'表示多帧静止目标在车辆坐标系下的位置信息的平均值,S表示x
c和y
c的协方差。
在一种可能的设计中,在本申请实施例的第二方面的第六种实现方式中,
确定模块,具体用于通过如下方式计算道路曲率信息:
其中,Q表示道路曲率信息,g
θ(x
c)表示融合边界信息,g
θ'(x
c)表示g
θ(x
c)的一阶导数,g
θ″(x
c)表示g
θ(x
c)的二阶导数。
在一种可能的设计中,在本申请实施例的第二方面的第七种实现方式中,车辆定位装置还包括计算模块和剔除模块;
获取模块,还用于在确定模块根据测量信息确定当前帧时刻所对应的当前道路边界信息之前,从测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,M为大于1的整数;
计算模块,用于计算获取模块获取的M个参考静止目标信息到待选静止目标信息之间的平均距离;
剔除模块,用于若计算模块计算得到的平均距离不满足预设静止目标条件,则从测量信息中剔除待选静止目标信息;
其中,待选静止目标信息为多个静止目标信息中的任一个,参考静止目标信息为多个静止目标信息中与待选静止目标信息之间距离小于距离预设值的静止目标信息。
在一种可能的设计中,在本申请实施例的第二方面的第八种实现方式中,
计算模块,具体用于通过如下方式计算平均距离:
其中,d表示平均距离,M表示参考静止信息的个数,P表示待选静止目标信息的位置信息,P
i表示第i个参考静止信息的位置信息,i为大于0且小于或等于M的整数。
在一种可能的设计中,在本申请实施例的第二方面的第九种实现方式中,
剔除模块,具体用于若平均距离大于阈值门限,则确定平均距离不满足预设静止目标条件,并从测量信息中剔除待选静止目标信息。
在一种可能的设计中,在本申请实施例的第二方面的第十种实现方式中,
确定模块,具体用于通过如下方式计算道路边界信息:
f
θ(x
c)=θ
0+θ
1×x
c+θ
2×x
c
2+θ
3×x
c
3;
其中,f
θ(x
c)表示道路边界信息,θ
0表示第一系数,θ
1表示第二系数,θ
2表示第三系数,θ
3表示第四系数,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,λ表示正则项系数,θ
j表示第j个系数,j为大于或等于0且小于或等于3的整数。
在一种可能的设计中,在本申请实施例的第二方面的第十一种实现方式中,
确定模块,具体用于根据当前道路边界信息以及历史道路边界信息计算当前帧时刻的增稳边界信息;
根据当前帧时刻的增稳边界信息获取目标车辆到至道路左侧边界的第一距离,以及目标车辆至道路右侧边界的第二距离;
根据第一距离和第二距离计算得到当前帧时刻的第一目标定位信息。
在一种可能的设计中,在本申请实施例的第二方面的第十二种实现方式中,
确定模块,具体用于通过如下方式计算当前帧时刻所对应的增稳边界信息:
其中,f
θ'表示当前帧时刻所对应的增稳边界信息,f
θ_w(x
c)表示第w帧所对应的历史道路边界信息,W表示历史道路边界信息的个数,x
c表示静止目标在车辆坐标系中的横轴坐标,μ表示W帧的车道边界平均值。
在一种可能的设计中,在本申请实施例的第二方面的第十三种实现方式中,
确定模块,具体用于通过如下方式计算当前帧时刻所的第一目标定位信息:
Location=(ceil(R
R-D),ceil(R
L-D));
D=(R
L+R
R)/N;
其中,Location表示当前帧时刻的第一目标定位信息,ceil表示向上取整的计算方式,R
L表示目标车辆到至道路左侧边界的第一距离,R
R表示目标车辆至道路右侧边界的第二距离,D表示车道的宽度,N表示车道的数量。
在一种可能的设计中,在本申请实施例的第二方面的第十四种实现方式中,测量信息还包括:至少一个运动目标信息;
获取模块,还用于在确定模块根据当前道路边界信息确定第一目标定位信息之前,从测量信息中获取至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,目标编号用于标定不同的运动目标;
确定模块,还用于根据获取模块获取到的至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;
确定模块,还用于根据车道占据信息确定当前帧时刻所对应的第二目标定位信息,其中,第二目标定位信息用于表示目标车辆在道路中所在的位置。
在一种可能的设计中,在本申请实施例的第二方面的第十五种实现方式中,
获取模块,具体用于根据至少一个运动目标信息以及至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,K为正整数;
根据至少一个运动目标信息以及至少一个运动目标信息对应的历史运动目标信息获取k帧中第L
k个车道被占据的情况,其中,k为大于0且小于或等于K的整数;
若车道占据比值小于预设比值,则确定第L
k个车道被占据,其中,车道占据比值为k个帧与K个帧的比值;
若车道占据比值大于或等于预设比值,则确定第L
k个车道未被占据;
确定模块,具体用于将未被占据的第L
k个车道确定为当前帧时刻所对应的第二目标定位信息。
在一种可能的设计中,在本申请实施例的第二方面的第十六种实现方式中,
确定模块,具体用于根据第二目标定位信息确定第一目标定位信息的置信度,其中,置信度用于表示第一目标定位信息的可信程度;
根据置信度确定当前时刻的第一目标定位信息。
本申请第三方面提供一种车辆定位装置,可以包括:存储器、收发器、处理器以及总线系统;
其中,所述存储器用于存储程序和指令;
所述收发器用于在所述处理器的控制下接收或发送信息;
所述处理器用于执行所述存储器中的程序;
所述总线系统用于连接所述存储器、所述收发器以及所述处理器,以使所述存储器、所述收发器以及所述处理器进行通信;
所述处理器用于调用所述存储器中的程序指令,所述处理器用于执行如下步骤:
在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,所述测量信息包括多个静止目标信息,所述多个静止目标信息用于表示多个静止目标的信息,所述多个静止目标信息与所述多个静止目标的信息一一对应;
根据所述测量信息确定所述当前帧时刻所对应的当前道路边界信息;
根据所述当前道路边界信息确定第一目标定位信息,其中,所述第一目标定位信息用于表示目标车辆在道路中所在的位置;
根据所述当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,所述道路曲率信息用于表示所述目标车辆所在道路的弯曲程度,所述历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,所述历史帧时刻为所述当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;
输出所述第一目标定位信息和所述道路曲率信息。
在一种可能的设计中,在本申请实施例的第三方面的第一种实现方式中,
所述处理器具体用于执行如下步骤:
通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,其中,所述跟踪信息包括所述多个静止目标在雷达坐标系中的位置信息和速度信息;
根据所述跟踪信息以及所述毫米波雷达的标定参数计算所述测量信息,其中,所述测量信息包括所述多个静止目标在车辆坐标系中的位置信息和速度信息,所述标定参数包括旋转量和平移量。
在一种可能的设计中,在本申请实施例的第三方面的第二种实现方式中,所述预置角度范围包括第一预置角度范围和第二预置角度范围;
所述处理器具体用于执行如下步骤:
通过第一毫米波雷达获取所述第一预置角度范围内多个第一静止目标的第一跟踪信息,并通过第二毫米波雷达获取所述第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,所述跟踪信息包括所述第一跟踪信息和所述第二跟踪信息,所述多个静止目标包括所述多个第一静止目标和所述多个第二静止目标,所述毫米波雷达包括所述第一毫米波雷达和所述第二毫米波雷达,所述第一毫米波雷达的探测距离和覆盖视角与所述第二毫 米波雷达的探测距离和覆盖视角不同;
根据所述第一跟踪信息以及所述毫米波雷达的标定参数计算所述第一预置角度范围内的第一测量信息,并根据所述第二跟踪信息以及所述毫米波雷达的标定参数计算所述第二预置角度范围内的第二测量信息,其中,所述测量信息包括所述第一测量信息和所述第二测量信息。
在一种可能的设计中,在本申请实施例的第三方面的第三种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述测量信息:
(x
c,y
c)=R×(x
r,y
r)+T;
(V
xc,V
yc)=R×(V
xr,V
yr);
其中,所述(x
c,y
c)表示静止目标在所述车辆坐标系下的位置信息,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
r,y
r)表示所述静止目标在所述雷达坐标系下的位置信息,所述x
r表示所述静止目标在所述雷达坐标系中的横轴坐标,所述y
r表示所述静止目标在所述雷达坐标系中的纵轴坐标,所述R表示所述旋转量,所述T表示所述平移量,所述(V
xc,V
yc)表示所述静止目标在所述车辆坐标系下的速度信息,所述V
xc表示所述静止目标在所述车辆坐标系中横轴方向的速度,所述V
yc表示所述静止目标在所述车辆坐标系中纵轴方向的速度,所述(V
xr,V
yr)表示所述静止目标在所述雷达坐标系中下的速度信息,所述V
xr表示所述静止目标在所述雷达坐标系中横轴方向的速度,所述V
yr表示所述静止目标在所述雷达坐标系中纵轴方向的速度。
在一种可能的设计中,在本申请实施例的第三方面的第四种实现方式中,
所述处理器具体用于执行如下步骤:
根据所述道路边界信息以及所述历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,所述栅格区域覆盖于所述目标车辆,所述栅格区域包含多个栅格单元;
根据所述所述栅格区域中每个栅格单元的占据概率获取概率栅格图;
根据所述概率栅格图中的目标栅格单元确定融合边界信息,其中,所述目标栅格单元的占据概率大于预设概率门限。
根据所述融合边界信息计算所述道路曲率信息。
在一种可能的设计中,在本申请实施例的第三方面的第五种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述每个栅格单元的占据概率:
p
n(x
c,y
c)=min(p(x
c,y
c)+p
n-1(x
c,y
c),1);
其中,所述p
n(x
c,y
c)表示n帧栅格单元的占据概率,所述p(x
c,y
c)表示所述道路边界信息,所述p
n-1(x
c,y
c)表示n-1帧的所述历史道路边界信息,所述x
c表示所述静止目标在 所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
c,y
c)表示所述静止目标在所述车辆坐标系下的位置信息,所述(x
c,y
c)'表示多帧所述静止目标在所述车辆坐标系下的位置信息的平均值,所述S表示所述x
c和所述y
c的协方差。
在一种可能的设计中,在本申请实施例的第三方面的第六种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述道路曲率信息:
其中,所述Q表示所述道路曲率信息,所述g
θ(x
c)表示所述融合边界信息,所述g
θ'(x
c)表示所述g
θ(x
c)的一阶导数,所述g
θ″(x
c)表示所述g
θ(x
c)的二阶导数。
在一种可能的设计中,在本申请实施例的第三方面的第七种实现方式中,
所述处理器还用于执行如下步骤:
从所述测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,所述M为大于1的整数;
计算所述M个参考静止目标信息到所述待选静止目标信息之间的平均距离;
若所述平均距离不满足所述预设静止目标条件,则从所述测量信息中剔除所述待选静止目标信息;
其中,所述待选静止目标信息为所述多个静止目标信息中的任一个,所述参考静止目标信息为所述多个静止目标信息中与所述待选静止目标信息之间距离小于距离预设值的静止目标信息。
在一种可能的设计中,在本申请实施例的第三方面的第八种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述平均距离:
其中,所述d表示所述平均距离,所述M表示所述参考静止信息的个数,所述P表示所述待选静止目标信息的位置信息,所述P
i表示所述第i个参考静止信息的位置信息,所述i为大于0且小于或等于所述M的整数。
在一种可能的设计中,在本申请实施例的第三方面的第九种实现方式中,
所述处理器具体用于执行如下步骤:
若所述平均距离大于阈值门限,则确定所述平均距离不满足所述预设静止目标条件,并从所述测量信息中剔除所述待选静止目标信息。
在一种可能的设计中,在本申请实施例的第三方面的第十种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述道路边界信息:
f
θ(x
c)=θ
0+θ
1×x
c+θ
2×x
c
2+θ
3×x
c
3;
其中,所述f
θ(x
c)表示所述道路边界信息,所述θ
0表示第一系数,所述θ
1表示第二系数,所述θ
2表示第三系数,所述θ
3表示第四系数,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
c,y
c)表示所述静止目标在所述车辆坐标系下的位置信息,所述λ表示正则项系数,所述θ
j表示第j个系数,所述j为大于或等于0且小于或等于3的整数。
在一种可能的设计中,在本申请实施例的第三方面的第十一种实现方式中,
所述处理器具体用于执行如下步骤:
根据所述当前道路边界信息以及历史道路边界信息计算所述当前帧时刻的增稳边界信息;
根据所述当前帧时刻的所述增稳边界信息获取所述目标车辆到至道路左侧边界的第一距离,以及所述目标车辆至道路右侧边界的第二距离;
根据所述第一距离和所述第二距离计算得到所述当前帧时刻的所述第一目标定位信息。
在一种可能的设计中,在本申请实施例的第三方面的第十二种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述当前帧时刻所对应的所述增稳边界信息:
其中,所述f
θ'表示所述当前帧时刻所对应的所述增稳边界信息,所述f
θ_w(x
c)表示第w帧所对应的历史道路边界信息,所述W表示所述历史道路边界信息的个数,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述μ表示所述W帧的车道边界平均值。
在一种可能的设计中,在本申请实施例的第三方面的第十三种实现方式中,
所述处理器具体用于执行如下步骤:
通过如下方式计算所述当前帧时刻所的所述第一目标定位信息:
Location=(ceil(R
R-D),ceil(R
L-D));
D=(R
L+R
R)/N;
其中,所述Location表示所述当前帧时刻的所述第一目标定位信息,所述ceil表示向上取整的计算方式,所述R
L表示所述目标车辆到至所述道路左侧边界的第一距离,所述R
R表示所述目标车辆至所述道路右侧边界的第二距离,所述D表示所述车道的宽度,所述N表示所述车道的数量。
在一种可能的设计中,在本申请实施例的第三方面的第十四种实现方式中,
所述处理器还用于执行如下步骤:
通过如下方式计算所述当前帧时刻所的所述第一目标定位信息:
从所述测量信息中获取所述至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,所述目标编号用于标定不同的运动目标;
根据所述至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;
根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,其中,所述第二目标定位信息用于表示所述目标车辆在道路中所在的位置。
在一种可能的设计中,在本申请实施例的第三方面的第十五种实现方式中,
所述处理器具体用于执行如下步骤:
根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,所述K为正整数;
根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取k帧中第L
k个车道被占据的情况,其中,所述k为大于0且小于或等于K的整数;
若车道占据比值小于预设比值,则确定所述第L
k个车道被占据,其中,所述车道占据比值为所述k个帧与所述K个帧的比值;
若所述车道占据比值大于或等于所述预设比值,则确定所述第L
k个车道未被占据;
所述根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,包括:
将未被占据的所述第L
k个车道确定为所述当前帧时刻所对应的所述第二目标定位信息。
在一种可能的设计中,在本申请实施例的第三方面的第十六种实现方式中,
根据所述第二目标定位信息确定所述第一目标定位信息的置信度,其中,所述置信度用于表示所述第一目标定位信息的可信程度;
根据所述置信度确定所述当前时刻的所述第一目标定位信息。
第四方面,本申请实施例提供一种计算机设备,包括:处理器、存储器、总线和通信接口;该存储器用于存储计算机执行指令,该处理器与该存储器通过该总线连接,当该服务器运行时,该处理器执行该存储器存储的该计算机执行指令,以使该服务器执行如上述任一方面的方法。
第五方面,本申请实施例提供了一种计算机可读存储介质,用于储存为上述方法所用的计算机软件指令,当其在计算机上运行时,使得计算机可以执行上述中任一方面的方法。
第六方面,本申请实施例提供了一种包含指令的计算机程序产品,当其在计算机上运行时,使得计算机可以执行上述任一方面的方法。
另外,第二方面至第六方面任一种设计方式所带来的技术效果可参见第一方面中不同设计方式所带来的技术效果,此处不再赘述。
从以上技术方案可以看出,本申请具有以下优点:
本申请实施例中,提供了一种车辆定位的方法,首先车辆定位装置通过毫米波雷达获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息,然后车辆定位装置根据测量信息确定当前帧时刻所对应的道路边界信息,再车辆定位装置根据当前帧时刻所对应的道路边界信息确定第一目标定位信息,第一目标定位信息用于表示车辆在车道中所在的位置,最后车辆定位装置根据道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示车辆所在的道路弯曲程度,历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻。通过上述方式,由于毫米波雷达会进行主动测量,因此在可视范围 内受光线气候影响很小,在中心城区、隧道涵洞和非理想气象条件下,采用毫米波雷达可以得到车辆与四周目标之间的位置关系,从而确定车辆在道路中的定位信息,由此提升定位信息的置信度和可靠性。此外,通过这些位置关系确定道路曲率信息,该道路曲率信息能够估计出车辆所在车道的弯曲度,从而提升车辆定位的准确性。
为了更清楚地说明本申请实施例的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本申请的一些实施例。
图1为本申请实施例中车辆定位系统的一个架构示意图;
图2为本申请实施例中车辆定位装置的一个产品实现示意图;
图3为本申请实施例中车辆定位的方法一个核心流程示意图;
图4为本申请实施例中车辆定位场景的一个实施例示意图;
图5为本申请实施例中车辆定位的方法一个实施例示意图;
图6为本申请实施例中毫米波雷达获取目标的一个场景示意图;
图7为本申请实施例中毫米波雷达坐标系和车辆坐标系的一个示意图;
图8为本申请实施例中获取预置角度范围内测量信息的一个流程示意图;
图9为本申请实施例中构建概率栅格图的一个流程示意图;
图10为本申请实施例中概率栅格图的一个示意图;
图11为本申请实施例中概率栅格图构建结果的一个示意图;
图12为本申请实施例中毫米波雷达定位静止目标信息的一个流程示意图;
图13为本申请实施例中对确定异常待选静止目标信息的一个示意图;
图14为本申请实施例中车辆定位的方法另一个实施例示意图;
图15为本申请实施例中毫米波雷达定位运动目标信息的一个流程示意图;
图16为本申请实施例中运动目标信息占据车道的一个示意图;
图17为本申请实施例中毫米波雷达融合静止目标信息和运动目标信息的一个示意图;
图18为本申请实施例中车辆定位装置一个实施例示意图;
图19为本申请实施例中车辆定位装置另一个实施例示意图;
图20为本申请实施例中车辆定位装置一个结构示意图。
本申请提供了一种车辆定位的方法以及车辆定位装置,可以在中心城区、隧道以及非规则道路定位,提升定位的置信度和可靠性,此外,通过道路曲率信息能够更好的辅助车辆规划控制系统,以规划车辆行驶轨迹。
本申请的说明书和权利要求书及上述附图中的术语“第一”、“第二”、“第三”、“第四”等(如果存在)是用于区别类似的对象,而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换,以便这里描述的本申请的实施例例如能够以除了在这里图示或描述的那些以外的顺序实施。此外,术语“包括”和“具有”以及他们的 任何变形,意图在于覆盖不排他的包含,例如,包含了一系列步骤或单元的过程、方法、系统、产品或设备不必限于清楚地列出的那些步骤或单元,而是可包括没有清楚地列出的或对于这些过程、方法、产品或设备固有的其它步骤或单元。
应理解,本申请可以应用于中心城区、隧道以及非规则道路情况,为了完成车道级的驾驶规划引导,车辆需要知道自身相对周围道路环境的信息,即包含自车相对周围道路环境的局部位置信息以及车辆周围道路的元素信息(如道路曲率等)。车辆可以车载传感器来感知车辆周围环境,并根据感知所获得的道路、车辆位置和障碍物信息,控制车辆的转向和速度,从而使车辆能够安全、可靠地在道路上行驶。
可以理解的是,在实际应用中,除了可以应用于车辆的驾驶,也可以用于飞机驾驶或者船舶驾驶,使得飞机或者船舶也能在航道上行驶,通过毫米波雷达获取到的测量信息实现定位和曲率的计算,提升定位的准确性。本申请主要以车辆定位为主进行介绍,然而这并不应理解为对本申请应用范围的限定。下面将介绍车辆定位系统的架构。
请参阅图1,图1为本申请实施例中车辆定位系统的一个架构示意图,如图所示,定位传感和同步硬件系统S1中包含了本申请定位需要用到的传感器和同步单元,其中,传感器具体包括初始化全球定位系统(global positioning system,GPS)接收机以及毫米波雷达传感器。定位数据采集系统S2采集定位传感和同步硬件系统S1的定位传感器数据和同步数据,并将该定位传感器数据和同步数据送入至车辆端的毫米波雷达定位处理系统S3。车辆端的处理器可以结合车载地图系统S4完成本申请中的局部定位和概率栅格图的构建,并将定位结果送入至车辆计算机S5做后续的行驶规划和使用。
可选地,车辆端的处理器也可以将定位传感器数据和同步数据通过车辆网关传到云端计算中心S6,云端计算中心S6综合云端地图完成车辆局部定位和概率栅格图的构建,并通过车辆网关将信息传递给毫米波雷达定位处理系统S3,再继续传给车辆计算机S5,以用于行驶规划。
结合上述图1介绍的车辆定位系统,请参阅图2,图2为本申请实施例中车辆定位装置的一个产品实现示意图,如图所示,本申请在定位过程中需要GPS接收机提供初始化的参考位置,局部定位过程中需要中中长距离毫米波雷达、短距离毫米波雷达、车道数量地图以及定位算法处理设备,即如图2所示的产品实现示意图。
具体地,该产品实现主要包括以下部件:
(1)GPS接收机,用于接收GPS信号,给车辆的定位提供初始化的参考位。其中,GPS接收机是接收GPS卫星信号并确定地面空间位置的仪器,GPS卫星发送的导航定位信号是一种可供大量用户共享的信息资源。对于陆地、海洋和空间的广大用户拥有能够接收、跟踪、变换和测量GPS信号的接收设备,即GPS信号接收机,通过对接收到的GPS信号进行解算可以得到粗精度(几米到十几米精度不等)定位结果。
(2)中长距离毫米波雷达以及短距离毫米波雷达,用于获取车辆环向的静止目标信息和运动目标信息。其中,毫米波雷达还具有以下特性:
频带极宽,适用于各种宽带信号处理;
宽波束双/多通道角度测量,具备角度分辨和跟踪能力;
有较宽的多普勒宽带,多普勒效应明显,具有良好的多普勒分辨力,毫米波雷达波长短,对目标的散射特性描述精准、细密且测速精度较高;
(3)车道数量地图,用于提供道路拥有的车道数量信息。
(4)数据同步单元,用于为中长距离毫米波雷达、短距离毫米波雷达和车道数量地图提供同步信息,使得信息保持完整性和统一性。
(5)数据采集设备,用于采集前向中长距离毫米波雷达的目标信息、四个角度方向的短距离毫米波雷达的目标信息、GPS接收机信息和同步时间戳信息;
(6)雷达定位处理板,用于完成环向毫米波雷达局部定位和概率栅格图构建,雷达定位处理板包括但不限于满足车规等级的数字信号处理器,比如数字信号处理(digital signal processing,DSP)、现场可编程逻辑门阵列(field programmable gate array,FPGA)以及微控制单元(micro control unit,MCU)等。
(7)车辆计算机或自动驾驶计算平台,用于接收雷达定位处理板传输来的定位信息,并进行行驶规划,此外,在雷达处理板处理能力受限时还可以分担部分定位处理的计算,如针对自动驾驶计算平台。
(8)云端地图,用于云端存储的道路地图信息。
(9)车辆网关,用于为雷达定位信息和云端交互提供信息传递通道。
(10)云端计算中心,用于在云端完成毫米波雷达局部定位和概率栅格图构建计算处理。
(11)定位结果显示或语音提醒,用于把车辆端定位结果通过车辆计算机传递给导航,在导航中以显示的方式和/或语音的方式提醒驾驶员,可以应用于辅助驾驶场景。
基于上述的车辆定位系统架构以及车辆定位装置的产品实现,本申请所提供的车辆定位的方法如图3所示,请参阅图3,图3为本申请实施例中车辆定位的方法一个核心流程示意图,具体地:
在步骤101中,在开始进行车辆定位时,通过输入GPS初始位置和车道数量地图,可以完成车辆局部定位初始化。
在步骤102中,开启安装在车辆上的中长距离毫米波雷达和短距离毫米波雷达,将中长距雷达和短距雷达帧间隔采集到的数据由雷达坐标系转换到车辆坐标系,从而得到环向毫米波雷达目标信息。
步骤103至步骤105为本申请中的核心步骤,在步骤103中,利用环向毫米波雷达目标中的静止目标信息,经过孤立异常目标剔除、最优的道路边界信息求解和历史道路边界信息加权后,并结合车道数量地图实现静止目标定位;利用环向毫米波雷达目标中的运动目标信息与历史运动目标信息确定车道占据情况,综合车道数量地图和车道占据信息,可以完成运动目标定位。将静止目标定位结果和运动目标定位结果进行融合,得到车辆局部定位结果。
在步骤104中,根据步骤103中得到的定位结果,判断车辆局部定位是否成功,若定位成功,则进入步骤105,反之,若定位失败,则跳转至步骤101,并重新开始进行定位。
在步骤105中,定位成功后,融合多帧的静止目标信息和定位确定的道路边界信息, 根据雷达的测量目标信息和预测计算栅格占据概率,构造出自车周围的栅格概率图,计算出道路栅格概率图中的道路边界曲率信息。
为了便于理解,请参阅图4,图4为本申请实施例中车辆定位场景的一个实施例示意图,如图所示,对于需要进行定位的车辆而言,安装在该车辆前方的中长距离毫米波雷达和安装在四角的短距离毫米波雷达为车辆提供环向毫米波测量信息输入。其中,中长距离毫米波雷达即为中距离毫米波雷达(medium range radar,MRR)和长距离毫米波雷达(long range radar,LRR)的合称,短距离毫米波雷达(short range radar,SRR)测得车辆周边目标的位置信息。
下面将结合实施例和附图介绍本申请中车辆定位的方法,本申请所提供的车辆定位的方法可以包括以下两个实施例,具体地:
实施例一,通过多个静止目标信息完成车辆定位;
请参阅图5,图5为本申请实施例中车辆定位的方法一个实施例示意图,本申请实施例中车辆定位的方法一个实施例包括:
201、在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息,多个静止目标信息用于表示多个静止目标的信息,多个静止目标信息与多个静止目标的信息一一对应;
本实施例中,在局部定位开始后,车辆定位装置可以先响应局部定位开始指令,然后获取GPS接收机的信号、车道数量地图和同步单元信号,同步后送入车辆数据采集单元,车辆定位装置从数据采集单元采集初始局部定位信息。
车辆定位装置通过测量设备获取预置角度范围内的测量信息,该测量信息中可以包括多个静止目标信息,静止目标信息相对于地面参照系的速度为零,每个静止目标信息各自对应一个静止目标的信息。
具体地,测量设备可以是毫米波雷达,预置角度范围可以包括第一预置角度范围和第二预置角度范围,第一预置角度范围和第二预置角度范围不同,比如,第一预置角度范围为120度,第二预置角度范围为60度,可以理解的是,第一预置角度范围和第二预置角度范围还可以是其他的度数,此处不做限定。
为了便于介绍,请参阅图6,图6为本申请实施例中毫米波雷达获取目标的一个场景示意图,如图所示,短距离毫米波雷达的波束覆盖范围为虚线小扇形区域,中长距离毫米波雷达的波束覆盖范围为虚线大扇形区域,圆点表示毫米波雷达探测到的静止目标,方框表示毫米波雷达探测到的运动目标。
车辆定位装置通过第一毫米波雷达获取第一预置角度范围内多个静止目标和/或运动目标的跟踪信息,并通过第二毫米波雷达获取第二预置角度范围内多个静止目标和/或运动目标的跟踪信息,其中,第一毫米波雷达的探测距离和覆盖视角与第二毫米波雷达的探测距离和覆盖视角不同。若第一毫米波雷达是短距离毫米波雷达,第二毫米波雷达是中长距离毫米波雷达,则第一毫米波雷达的探测距离大于第二毫米波的探测距离,第二毫米波雷达的覆盖范围大于第一毫米波雷达的覆盖范围,其中,探测距离越远,覆盖范围越小(覆盖范围通常是指覆盖的视角)。若第一毫米波雷达是中长距离毫米波雷达,第二毫米波雷达 是短距离毫米波雷达,则第一毫米波雷达的探测距离小于第二毫米波的探测距离,第二毫米波雷达的覆盖范围小于第一毫米波雷达的覆盖范围,其中,探测距离越近,覆盖范围越大(覆盖范围通常是指覆盖的视角)。而多个目标包括静止目标和/或运动目标,静止目标可以是路边的树木或者护栏等固定的物件,而运动目标通常是指运动的车辆。
车辆定位装置获取到多个目标的跟踪信息,该跟踪信息包括目标在雷达坐标系中的位置信息和速度信息。毫米波雷达检测的静止目标可能存在一定数量的虚警目标,虚警目标的在前后帧没有关联。而毫米波雷达检测的运动目标相对数量相对较少,前后帧目标信息存在关联,并且有每个目标对应有唯一的编号。
车辆定位装置可以根据跟踪信息以及毫米波雷达的标定参数计算预置角度范围内的测量信息,其中,跟踪信息属于雷达坐标系中的信息,预置角度范围内的测量信息属于车辆坐标系中的信息,标定参数包括旋转量和平移量,预置角度范围内的测量信息包括目标在车辆坐标系中的位置信息和速度信息。下面将对车辆坐标系和雷达坐标系进行介绍,请参阅图7,图7为本申请实施例中毫米波雷达坐标系和车辆坐标系的一个示意图,如图所示,雷达坐标系是以雷达的几何中心为原点,以传感器右侧方向为X轴,以传感器前向方向为Y轴。而车体坐标系是以车辆后轴中心为原点O,以车辆行驶方向为X轴,后轴指向右侧为Y轴。
为了便于介绍,请参阅图8,图8为本申请实施例中获取预置角度范围内测量信息的一个流程示意图,如图所示,具体地:
在步骤2011中,在毫米波雷达获取到多个目标的跟踪信息之后,还需要输入毫米波雷达的标定参数,其中,标定参数包含了从雷达坐标系转换到车辆坐标系的旋转量R和平移量T,而目标的跟踪信息包括了位置信息(x
r,y
r)和速度信息(V
xr,V
yr)。
步骤2012中,读取每一个毫米波雷达对车辆坐标系的标定参数,将上述步骤2011中的位置信息(x
r,y
r)和速度信息(V
xr,V
yr)根据下面的转换关系,从雷达坐标系转换到车辆坐标系,车辆坐标系中的位置信息表示为(x
c,y
c),速度信息表示为(V
xc,V
yc),转换关系为:
(x
c,y
c)=R×(x
r,y
r)+T;
(V
xc,V
yc)=R×(V
xr,V
yr);
其中,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
r,y
r)表示静止目标在雷达坐标系下的位置信息,x
r表示静止目标在雷达坐标系中的横轴坐标,y
r表示静止目标在雷达坐标系中的纵轴坐标,R表示旋转量,T表示平移量,(V
xc,V
yc)表示静止目标在车辆坐标系下的速度信息,V
xc表示静止目标在车辆坐标系中横轴方向的速度,V
yc表示静止目标在车辆坐标系中纵轴方向的速度,(V
xr,V
yr)表示静止目标在雷达坐标系中下的速度信息,V
xr表示静止目标在雷达坐标系中横轴方向的速度,V
yr表示静止目标在雷达坐标系中纵轴方向的速度。
举个例子,比如(x
c,y
c)=(0.46,3.90),(x
r,y
r)=(0.20,1.80),代入上述关系表达式可得:
步骤2013中,输出车辆坐标系下预置角度范围内的测量信息。
202、根据测量信息确定当前帧时刻所对应的当前道路边界信息;
本实施例中,车辆定位装置根据车辆坐标系下的测量信息确定当前帧时刻所对应的道路边界信息,道路边界信息用于表示道路行驶区域的边界。其中,该道路边界信息可以表示为一个多项式:
f
θ(x
c)=θ
0+θ
1×x
c+θ
2×x
c
2+θ
3×x
c
3;
为了求解三次多项式中的第一系数θ
0、第二系数θ
1,第三系数θ
2和第四系数θ
3,还可以构建一个含有拟合均方误差和多项式参数正则项的代价函数:
其中,f
θ(x
c)表示道路边界信息,θ
0表示第一系数,θ
1表示第二系数,θ
2表示第三系数,θ
3表示第四系数,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,λ表示正则项系数,θ
j表示第j个系数,j为大于或等于0且小于或等于3的整数。
举个例子,假设λ=0.1,θ
0、θ
1,θ
2和θ
3可以通过最小值求出来,比如求出以下的表达式:
f
θ(x
c)=0.39+2.62x
c+0.23x
c
2+0.05x
c
3;
203、根据当前道路边界信息确定第一目标定位信息,其中,第一目标定位信息用于表示目标车辆在道路中所在的位置;
本实施例中,车辆定位装置可以根据当前帧时刻所对应的道路边界信息确定第一目标定位信息,这里的第一目标定位信息是根据静止目标信息确定的,且第一目标定位信息用于表示车辆在车道中所在的位置,比如车辆在五个车道中的第二个车道。
具体地,车辆定位装置确定第一目标定位信息的过程为,首先,车辆定位装置根据当前帧时刻所对应的道路边界信息以及历史道路边界信息计算当前帧时刻的增稳边界信息,增稳边界信息是将之前的历史道路边界信息与当前的道路边界信息进行加权平均,从而提高当前定位结果稳定性。然后根据当前帧时刻的增稳边界信息获取车辆到至道路左侧边界的第一距离,以及车辆至道路右侧边界的第二距离,最后根据第一距离和第二距离计算得到当前帧时刻的第一目标定位信息。
可以通过如下方式计算当前帧时刻所对应的增稳边界信息:
其中,f
θ'表示当前帧时刻所对应的增稳边界信息,f
θ_w(x
c)表示第w帧所对应的历史 道路边界信息,W表示历史道路边界信息的个数,x
c表示静止目标在车辆坐标系中的横轴坐标,μ表示W帧的车道边界平均值。
根据上述步骤中计算得到的增稳边界信息,可以得到自车到道路左侧边界的第一距离R
L以及自车到道路右侧边界的第二距离R
R,结合车道数量地图中的车道数量N,计算得到车道宽度D。计算自车到左侧道路边界的车道数ceil(R
L-D)(向上取整)和自车到到右侧道路边界的车道数ceil(R
R-D)(向上取整),根据自车到左侧道路边界的车道数和到右侧道路边界的车道数确定第一目标定位信息,也就确定自车所处的车道。
通过如下方式计算当前帧时刻所的第一目标定位信息:
Location=(ceil(R
R-D),ceil(R
L-D));
D=(R
L+R
R)/N;
其中,Location表示当前帧时刻所的第一目标定位信息,ceil表示向上取整的计算方式,R
L表示车辆到至道路左侧边界的第一距离,R
R表示车辆至道路右侧边界的第二距离,D表示车道的宽度,N表示车道的数量。
204、根据当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示目标车辆所在道路的弯曲程度,历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;
本实施例中,车辆定位装置可以根据道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示车辆所在的道路弯曲程度,道路曲率信息的倒数对应转弯半径。
可选地,在车辆定位装置确定道路曲率信息之前,还需要构建概率栅格图,通过概率栅格图直观地确定融合边界信息,其中,多个增稳边界信息被用来生成概率栅格图,以得到融合边界信息。为了便于介绍,请参阅图9,图9为本申请实施例中构建概率栅格图的一个流程示意图,如图所示,具体地:
在步骤2041中,输入毫米波雷达检测到的自车周围的静止目标信息。考虑到毫米波雷达的数据刷新时间极短(通常为50毫秒),在毫米波雷达数据刷新时间内增稳边界信息是连续变化的,也就是说在连续的几帧数据内,毫米波雷达对静止目标的定位是不会急剧变化的。静止目标在定位成功后,将当前帧时刻的道路边界信息记录下来,在后续计算融合边界信息的过程中,对当前帧时刻的道路边界信息和历史道路边界信息进行加权平均,得到当前帧时刻的增稳边界信息,以提高融合边界信息计算的稳定性,其中,多个增稳边界 信息可以得到融合边界信息。
在步骤2042中,需要划定自车(即目标车辆)周围的栅格区域,也就是在自车周围设定一个栅格区域,请参阅图10,图10为本申请实施例中概率栅格图的一个示意图,如图所示,在第一帧时刻至第五帧时刻都划出了一个栅格区域,比如,根据测试经验得到栅格区域对应车辆左右边界±20m,对应车辆前后边界±70m,每一个栅格单元的尺寸为0.2米,这样就能得到自车周围的一个m×n的栅格区域(m为栅格区域宽度除以栅格单元尺寸,n为栅格区域长度除以栅格单元尺寸),并且随着自车往前运动过程中,栅格区域始终距离自车前后左右固定的距离(例如根据测试经验得到栅格区域对应车辆左右边界±20m,对应车辆前后边界±70m)。
在步骤2043中,毫米波雷达检测到的静止目标信息的概率分布假设为高斯分布,对每一个栅格单元,融合多帧(比如根据测试经验选择20帧)的静止目标信息为(x
c,y
c),根据毫米波雷达与静止目标信息之间的位置关系,多帧中静止目标信息的平均值为(x
c,y
c)',对于每一个栅格单元而言,每一个栅格单元被目标占据的概率不断累积,叠加数帧栅格单元的占据概率,得到概率栅格图,即图10所示的概率栅格图。
通过如下方式即可计算每一个栅格单元中的占据概率:
p
n(x
c,y
c)=min(p(x
c,y
c)+p
n-1(x
c,y
c),1);
其中,p
n(x
c,y
c)表示n帧栅格单元的占据概率,p(x
c,y
c)表示道路边界信息,p
n-1(x
c,y
c)表示n-1帧的历史道路边界信息,x
c表示静止目标在车辆坐标系中的横轴坐标,y
c表示静止目标在车辆坐标系中的纵轴坐标,(x
c,y
c)表示静止目标在车辆坐标系下的位置信息,(x
c,y
c)'表示多帧静止目标在车辆坐标系下的位置信息的平均值,S表示x
c和y
c的协方差。
计算完可以得到自车周围的概率栅格图构建结果,具体如图11所示,图11为本申请实施例中概率栅格图构建结果的一个示意图,黑色越深代表占据概率越高,通常情况下融合边界信息的占据概率接近1。
举个例子,假设(x
c,y
c)=(0.51,3.51),(x
c,y
c)'=(0.50,3.50),S=[0.9,0.1;0.1,0.9]代入上述公式后得到如下结果:
其中,inv表示矩阵求逆,exp表示指数运算。
在步骤2044中,最后可以根据概率栅格图计算得到道路曲率信息,通过如下方式计算道路曲率信息:
其中,Q表示道路曲率信息,g
θ(x
c)表示融合边界信息,g
θ'(x
c)表示g
θ(x
c)的一阶导数,g
θ″(x
c)表示g
θ(x
c)的二阶导数。
举个例子,假设g
θ'(x
c)=0.5,g
θ″(x
c)=0.05,于是得到:
即道路曲率信息等于0.03。
205、输出第一目标定位信息和道路曲率信息。
本实施例中,车辆定位装置通过显示的方式和/或语音的方式输出第一目标定位信息和道路曲率信息,以此可以提醒调试员用于辅助驾驶。
本申请实施例中,提供了一种车辆定位的方法,首先车辆定位装置通过毫米波雷达获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息,然后车辆定位装置根据测量信息确定当前帧时刻所对应的道路边界信息,再车辆定位装置根据当前帧时刻所对应的道路边界信息确定第一目标定位信息,第一目标定位信息用于表示车辆在车道中所在的位置,最后车辆定位装置根据道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示车辆所在的道路弯曲程度,历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻。通过上述方式,由于毫米波雷达会进行主动测量,因此在可视范围内受光线气候影响很小,在中心城区、隧道涵洞和非理想气象条件下,采用毫米波雷达可以得到车辆与四周目标之间的位置关系,从而确定车辆在道路中的定位信息,由此提升定位信息的置信度和可靠性。此外,通过这些位置关系确定道路曲率信息,该道路曲率信息能够估计出车辆所在车道的弯曲度,从而提升车辆定位的准确性。在高级辅助驾驶或自动驾驶车道级定位中辅助完成更好的车辆规划控制。
可选地,在上述图5对应的实施例的基础上,本申请实施例提供的车辆定位的方法第一个可选实施例中,在根据测量信息确定当前帧时刻所对应的当前道路边界信息之前,还可以包括:
从测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,M为大于1的整数;
计算M个参考静止目标信息到待选静止目标信息之间的平均距离;
若平均距离不满足预设静止目标条件,则从测量信息中剔除待选静止目标信息;
其中,待选静止目标信息为多个静止目标信息中的任一个,参考静止目标信息为多个静止目标信息中与待选静止目标信息之间距离小于距离预设值的静止目标信息。
本实施例中,在车辆定位装置通过毫米波雷达获取预置角度范围内的测量信息之后, 还需要筛选出符合要求的静止目标信息,并剔除不符合要求的静止目标信息。
为了便于介绍,请参阅图12,图12为本申请实施例中毫米波雷达定位静止目标信息的一个流程示意图,如图所示,具体地:
在步骤301中,首先从预置角度范围内的测量信息中提取待选静止目标信息,其中,根据车辆行驶速度V
car与车辆坐标系下的速度V
xc进行对比,如果车辆坐标系下的速度与车辆行驶速度的误差|V
car-V
xc|在一定范围内(比如2米/秒)的目标即可标记为待选静止目标信息。
在步骤302中,可以剔除异常孤立的待选静止目标信息,对于待选静止目标信息P而言,可以寻找其最近的M个参考静止目标信息P
i(i=1,...,M),并计算P到各个P
i的平均距离,即通过如下方式可以计算平均距离:
其中,d表示平均距离,M表示参考静止信息的个数,P表示待选静止目标信息的位置信息,P
i表示第i个参考静止信息的位置信息,i为大于0且小于或等于M的整数。
如果P到P
i的平均距离d大于阈值门限(该阈值门限可以根据实际的雷达系统参数调试设定,一般为雷达距离分辨率的5倍左右),则确定P为异常孤立目标,请参阅图13,13为本申请实施例中对确定异常待选静止目标信息的一个示意图,如图13中A点和B点所示,A点周围最近的5个参考静止信息到A点的距离都比较近,平均距离比较小,而B点周围最近的5个参考静止信息到B点的距离都比较远,平均距离很大,通过与预先设定的阈值门限比较,A点不会被标记为孤立异常目标,B点会被标记为孤立异常目标,需剔除B点。
图13对应于图6中的左侧道路边界,圆点表示为雷达探测到的静止目标信息,2号直线为求解得到的准确道路边界,1号直线或曲线为求解得到的不准确道路边界,其中,2号曲线为增稳边界信息。可以理解的是,A点和B点为两个示例性的目标,不应理解为对本申请的限定。
在步骤303中,在车辆定位装置去除异常孤立目标后之后,可以构造道路边界信息的多项式,即利用剩余的静止目标信息求解道路边界信息,具体方式如图5对应的实施例中步骤202所描述的相关内容,此处不做赘述。
在步骤304中,将剔除孤立异常的静止目标的位置信息代入到步骤303中的道路边界代价函数中,求解最优的道路边界多项式系数,确定最优的道路边界信息。
在步骤305中,输入历史道路边界信息后进行加权平均,得到增稳边界信息,再根据多个增稳边界信息确定融合边界信息,具体方式如图5对应的实施例中步骤203所描述的相关内容,此处不做赘述。
通过历史道路边界加权平均,可以有效增加道路边界信息的稳定性,避免出现道路边界跳变的情况。如果是初始帧求解增稳边界信息,则不进行道路边界信息的加权平均,一般是5帧以后开始加权平均,一般平均5帧至10帧。
在步骤306中,根据步骤305中计算得到的增稳边界信息,可以得到自车到道路左侧边界的距离以及自车到道路右侧边界的距离,结合车道数量地图中的车道数量,计算得到 车道宽度。
在步骤307中,车辆定位装置根据自车到道路左侧边界的距离、自车到道路右侧边界的距离以及计算得到的车道宽度,计算自车到左侧道路边界的车道数和到右侧道路边界的车道数,根据自车到左侧道路边界的车道数和到右侧道路边界的车道数,确定自车所处的车道。
在步骤308中,车辆定位装置输出第一目标定位信息,也就是将自车所处的车道标记在车道数量地图上。
其次,本申请实施例中,介绍了如何从预置角度范围内的测量信息中剔除异常的待选静止目标信息,一种可行的方式是,根据待选静止目标信息以及M个参考静止目标信息获取平均距离,若平均距离大于阈值门限,则从预置角度范围内的测量信息中剔除待选静止目标信息的步骤。通过上述方式,可以将一些异常点进行剔除,从而提升道路边界信息计算的准确性,使得结果更加贴近于实际情况,增加方案的可行性。
实施例二,通过多个静止目标信息和多个运动目标信息完成车辆定位;
请参阅图14,图14为本申请实施例中车辆定位的方法另一个实施例示意图,本申请实施例中车辆定位的方法另一个实施例包括:
401、在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息以及至少一个运动目标信息,多个静止目标信息用于表示多个静止目标的信息,多个静止目标信息与多个静止目标的信息一一对应;
本实施例中,通过毫米波雷达获取预置角度范围内的多个静止目标信息的过程可参阅图5对应实施例中的步骤201,此处不作赘述。
下面将介绍如何确定至少一个运动目标信息。
运动目标信息即为相对于地面具有位移的目标信息,首先从预置角度范围内的测量信息中提取待选运动目标信息,其中,根据车辆行驶速度V
car与车辆坐标系下的速度V
xc进行对比,如果车辆坐标系下的速度与车辆行驶速度的误差|V
car-V
xc|超过一定范围内(比如2米/秒)的目标即可标记为运动目标信息。
可以理解的是,运动目标信息包括当不仅限于目标的标号、目标的位置信息和目标的速度信息。
402、根据测量信息确定当前帧时刻所对应的当前道路边界信息;
本实施例中,车辆定位装置根据测量信息确定当前帧时刻所对应的道路边界信息的过程可参阅图5对应实施例中的步骤202,此处不作赘述。
403、从测量信息中获取至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,目标编号用于标定不同的运动目标;
本实施例中,车辆定位装置从测量信息中获取当前帧时刻的至少一个运动目标信息,其中,每一运动目标信息中携带对应的目标编号,不同的目标编号用于标定不同的目标。
当车辆处于车流较大的行驶场景时,此时安装在车辆上的毫米波雷达会被车辆在一定程度上遮挡,导致获取的静止目标信息减少,静止目标信息的减少会影响道路边界信息的提取。此时,由于车辆是行驶在路面车道上的,所有可以根据运动目标信息和过去一段时 间内(比如过去M帧,根据实际测试经验,M一般取5)的历史运动目标信息,以及车道数量地图和车道占据情况,确定自车所处的车道信息,具体流程如下图15所示,请参阅图15,图15为本申请实施例中毫米波雷达定位运动目标信息的一个流程示意图,如图所示,具体地:
在步骤4031中,输入运动目标信息,并判断车辆行驶速度V
car与车辆坐标系下的运动目标信息的速度V
xc进行对比,如果车辆坐标系下的速度与车辆行驶速度的误差|V
car-V
xc|超过一定范围内(比如2米/秒)的目标即可标记为运动目标信息。
在步骤4032中,根据运动目标信息的编号(编号从雷达跟踪开始到跟踪结束是保持不变的),将运动目标信息的跟踪历史记录下来。
在步骤4033中,标记运动目标信息占据的车道,具体的标记方式将在步骤405中进行介绍,此处仅为简述。
在步骤4034中,记录车道占据信息并判断车道占据状态,即根据车道占据信息标记结果,可以确定所有车道被占据的情况,结合车道数量地图可以确定哪些车道被占据,将被占据的车道在地图中进行标记。
在步骤4035中,根据车道数量地图中被标记的被运动车辆占据的信息,留下未被标记的车道即为自车车道,进而完成自车的局部定位,输出自车的定位结果。
404、根据至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;
本实施例中,车辆定位装置根据毫米波雷达获得的每一个运动目标信息所对应的位置信息(特别是横向的位置信息)和车道宽度先验信息(车道宽度一般为3.5米至3.75米),除了和自车在同一车道内(与自车横向距离小于半个车道)的运动目标信息之外,其余的运动目标信息根据横向距离可以确定运动目标所处的车道L
k,对于每一个运动目标信息而言,结合当前帧以及之前历史帧共计K帧,如果K帧中有k帧运动目标占据了车道L
k,可以判断车道被占据,为了便于理解,请参阅图16,图16为本申请实施例中运动目标信息占据车道的一个示意图,如图所示,假设共有三个车道,分别为L1、L2和L3,在第T帧时,L1车道处于空闲状态,L2车道被占据,L3车道处于空闲状态。在T-△T帧时,L1车道被占据,L2车道被占据,L3车道处于空闲状态。在T-2△T帧时,L1车道被占据,L2车道被占据,L3车道处于空闲状态。在T-3△T帧时,L1车道处于空闲状态,L2车道被占据,L3车道处于空闲状态。通过如下判决式,即可确定第L
k个车道被占据的情况。
其中,L
k表示第L
k个车道,k表示k帧被占据,k为大于0且小于或等于K的整数,K表示共有K帧时刻,thres表示预设比值。
405、根据车道占据信息确定当前帧时刻所对应的第二目标定位信息,其中,第二目标定位信息用于表示目标车辆在道路中所在的位置;
本实施例中,根据步骤404所描述的内容可知,若车道占据比值大于或等于预设比值,则确定第L
k个车道未被占据,并将未被占据的第L
k个车道确定为当前帧时刻所对应的第二 目标定位信息,其中,第二目标定位信息用于表示车辆在车道中所在的位置,比如,三个车道中第二个车道。
406、根据当前道路边界信息确定第一目标定位信息,其中,第一目标定位信息用于表示目标车辆在道路中所在的位置;
本实施例中,车辆定位装置可以根据第二目标定位信息确定第一目标定位信息的置信度,其中,置信度用于表示第一目标定位信息的可信程度,通常情况下,置信度越高,表示结果的可靠性越强。最后根据置信度确定当前时刻的第一目标定位信息。
为了便于理解,整个融合定位的过程如图17所示,请参阅图17,图17为本申请实施例中毫米波雷达融合静止目标信息和运动目标信息的一个示意图,将步骤4061中通过毫米波雷达获取的多个静止目标信息的定位结果(即第一目标定位信息),与步骤4062中通过毫米波雷达获取的多个运动目标信息(即第二目标定位信息)在道路数量地图上进行综合,综合自车到车道两侧边界的距离和车道被运动跟踪目标的占据情况,以及综合确定自车所处的车道信息。
407、根据当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示目标车辆所在道路的弯曲程度,历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;
本实施例中,车辆定位装置根据道路边界信息与历史道路边界信息确定道路曲率信息的过程可参阅图5对应实施例中的步骤204,此处不作赘述。
408、输出第一目标定位信息和道路曲率信息。
本实施例中,车辆定位装置通过显示的方式和/或语音的方式输出第一目标定位信息和道路曲率信息,以此可以提醒调试员用于辅助驾驶。
本申请实施例中,通过毫米波雷达同时获取多个静止目标信息和运动目标信息,结合两者进行道路边界信息的计算,以实现车辆的定位。采用运动目标信息可以辅助静止目标信息进行道路边界信息的计算,从而能够在车流量较大的时候,也能准确地完成车辆定位,以此提升方案的可行性和灵活性,并增加定位的置信度。
下面对本申请中一个实施例对应的车辆定位装置进行详细描述,请参阅图18,本申请实施例中的车辆定位装置50包括:
获取模块501,用于在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,所述测量信息包括多个静止目标信息,所述多个静止目标信息用于表示多个静止目标的信息,所述多个静止目标信息与所述多个静止目标的信息一一对应;
确定模块502,用于根据所述获取模块501获取的所述测量信息确定所述当前帧时刻所对应的当前道路边界信息;
所述确定模块502,用于根据所述当前道路边界信息确定第一目标定位信息,其中,所述第一目标定位信息用于表示目标车辆在道路中所在的位置;
所述确定模块502,用于根据所述当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,所述道路曲率信息用于表示所述目标车辆所在道路的弯曲程度,所述历史 道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,所述历史帧时刻为所述当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;
输出模块503,用于输出所述确定模块502确定的所述第一目标定位信息和所述确定模块确定的所述道路曲率信息。
本实施例中,在当前帧时刻,获取模块501通过测量设备获取预置角度范围内的测量信息,其中,所述测量信息包括多个静止目标信息,所述多个静止目标信息用于表示多个静止目标的信息,所述多个静止目标信息与所述多个静止目标的信息一一对应,确定模块502根据所述获取模块501获取的所述测量信息确定所述当前帧时刻所对应的当前道路边界信息,所述确定模块502根据所述当前道路边界信息确定第一目标定位信息,其中,所述第一目标定位信息用于表示目标车辆在道路中所在的位置,所述确定模块502根据所述当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,所述道路曲率信息用于表示所述目标车辆所在道路的弯曲程度,所述历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,所述历史帧时刻为所述当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻,输出模块503输出所述确定模块502确定的所述第一目标定位信息和所述确定模块确定的所述道路曲率信息。
本申请实施例中,提供了一种车辆定位装置,首先车辆定位装置通过毫米波雷达获取预置角度范围内的测量信息,其中,测量信息包括多个静止目标信息,然后车辆定位装置根据测量信息确定当前帧时刻所对应的道路边界信息,再车辆定位装置根据当前帧时刻所对应的道路边界信息确定第一目标定位信息,第一目标定位信息用于表示车辆在车道中所在的位置,最后车辆定位装置根据道路边界信息与历史道路边界信息确定道路曲率信息,其中,道路曲率信息用于表示车辆所在的道路弯曲程度,历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,历史帧时刻为当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻。通过上述方式,由于毫米波雷达会进行主动测量,因此在可视范围内受光线气候影响很小,在中心城区、隧道涵洞和非理想气象条件下,采用毫米波雷达可以得到车辆与四周目标之间的位置关系,从而确定车辆在道路中的定位信息,由此提升定位信息的置信度和可靠性。此外,通过这些位置关系确定道路曲率信息,该道路曲率信息能够估计出车辆所在车道的弯曲度,从而提升车辆定位的准确性。在高级辅助驾驶或自动驾驶车道级定位中辅助完成更好的车辆规划控制。
可选地,在上述图18所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述获取模块501,具体用于通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,其中,所述跟踪信息包括所述多个静止目标在雷达坐标系中的位置信息和速度信息;
根据所述跟踪信息以及所述毫米波雷达的标定参数计算所述测量信息,其中,所述测量信息包括所述多个静止目标在车辆坐标系中的位置信息和速度信息,所述标定参数包括旋转量和平移量。
可见,采用中长距离毫米波雷达以及短距离毫米波雷达,用于获取车辆环向的静止目 标信息和运动目标信息。毫米波雷达频带极宽,适用于各种宽带信号处理,还具备角度分辨和跟踪能力,且有较宽的多普勒宽带,多普勒效应明显,具有良好的多普勒分辨力,毫米波雷达波长短,对目标的散射特性描述精准、细密且测速精度较高。
可选地,在上述图18所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,所述预置角度范围包括第一预置角度范围和第二预置角度范围;
所述获取模块501,具体用于通过第一毫米波雷达获取所述第一预置角度范围内多个第一静止目标的第一跟踪信息,并通过第二毫米波雷达获取所述第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,所述跟踪信息包括所述第一跟踪信息和所述第二跟踪信息,所述多个静止目标包括所述多个第一静止目标和所述多个第二静止目标,所述毫米波雷达包括所述第一毫米波雷达和所述第二毫米波雷达,所述第一毫米波雷达的探测距离和覆盖视角与所述第二毫米波雷达的探测距离和覆盖视角不同;
根据所述第一跟踪信息以及所述毫米波雷达的标定参数计算所述第一预置角度范围内的第一测量信息,并根据所述第二跟踪信息以及所述毫米波雷达的标定参数计算所述第二预置角度范围内的第二测量信息,其中,所述测量信息包括所述第一测量信息和所述第二测量信息。
可见,本申请实施例中,提出可以采用第一毫米波雷达和第二毫米波雷达获取不同的测量信息,这种信息获取的方式无需高成本的实时动态定位、大数据量图像或点云信息,主要依靠毫米波雷达的信息,以5个毫米波雷达,每个雷达最多输出32个目标为例,数据量仅为几百千字节(kilobyte,KB)/秒,远小于视觉图像和激光点云的数据量。
可选地,在上述图18所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述获取模块501,具体用于通过如下方式计算所述测量信息:
(x
c,y
c)=R×(x
r,y
r)+T;
(V
xc,V
yc)=R×(V
xr,V
yr);
其中,所述(x
c,y
c)表示静止目标在所述车辆坐标系下的位置信息,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
r,y
r)表示所述静止目标在所述雷达坐标系下的位置信息,所述x
r表示所述静止目标在所述雷达坐标系中的横轴坐标,所述y
r表示所述静止目标在所述雷达坐标系中的纵轴坐标,所述R表示所述旋转量,所述T表示所述平移量,所述(V
xc,V
yc)表示所述静止目标在所述车辆坐标系下的速度信息,所述V
xc表示所述静止目标在所述车辆坐标系中横轴方向的速度,所述V
yc表示所述静止目标在所述车辆坐标系中纵轴方向的速度,所述(V
xr,V
yr)表示所述静止目标在所述雷达坐标系中下的速度信息,所述V
xr表示所述静止目标在所述雷达坐标系中横轴方向的速度,所述V
yr表示所述静止目标在所述雷达坐标系中纵轴方向的速度。
可见,本申请实施例中,可以将雷达坐标系下的测量信息转换为车辆坐标系下的测量信息,并且在位置信息和速度信息上均进行了相应的转换,从而能够以自车的视角来完成 车辆的定位,提升了方案的可行性。
可选地,在上述图18所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于根据所述道路边界信息以及所述历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,所述栅格区域覆盖于所述目标车辆,所述栅格区域包含多个栅格单元;
根据所述所述栅格区域中每个栅格单元的占据概率获取概率栅格图;
根据所述概率栅格图中的目标栅格单元确定融合边界信息,其中,所述目标栅格单元的占据概率大于预设概率门限。
根据所述融合边界信息计算所述道路曲率信息。
可见,本申请实施例中,通过融合多帧测量信息、道路边界信息以及历史道路边界信息,可以得到车辆的局部概率栅格图,并且可以从概率栅格图中计算道路曲率信息,从而有利于提升方案的可行性。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于通过如下方式计算所述每个栅格单元的占据概率:
p
n(x
c,y
c)=min(p(x
c,y
c)+p
n-1(x
c,y
c),1);
其中,所述p
n(x
c,y
c)表示n帧栅格单元的占据概率,所述p(x
c,y
c)表示所述道路边界信息,所述p
n-1(x
c,y
c)表示n-1帧的所述历史道路边界信息,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
c,y
c)表示所述静止目标在所述车辆坐标系下的位置信息,所述(x
c,y
c)'表示多帧所述静止目标在所述车辆坐标系下的位置信息的平均值,所述S表示所述x
c和所述y
c的协方差。
可见,本申请实施例中,可以利用毫米波雷达获取到的静止目标信息进行局部定位,利用历史求解的道路边界信息和当前求解的道路边界信息进行加权平均,从而得到稳定的道路边界信息,以此提升方案的可靠性。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于通过如下方式计算所述道路曲率信息:
其中,所述Q表示所述道路曲率信息,所述g
θ(x
c)表示所述融合边界信息,所述g
θ'(x
c)表示所述g
θ(x
c)的一阶导数,所述g
θ″(x
c)表示所述g
θ(x
c)的二阶导数。
可见,本申请实施例中,提供了一种计算道路曲率信息的实现方式,通过具体的计算方式能够得到所需的定位信息,从而提升了方案的可操作性。
可选地,在上述图18所对应的实施例的基础上,请参阅图19,本申请实施例提供的 车辆定位装置50的另一实施例中,所述车辆定位装置50还包括计算模块504和剔除模块505;
所述获取模块501,还用于在所述确定模块根据所述测量信息确定所述当前帧时刻所对应的当前道路边界信息之前,从所述测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,所述M为大于1的整数;
所述计算模块504,用于计算所述获取模块501获取的所述M个参考静止目标信息到所述待选静止目标信息之间的平均距离;
所述剔除模块505,用于若所述计算模块504计算得到的所述平均距离不满足所述预设静止目标条件,则从所述测量信息中剔除所述待选静止目标信息;
其中,所述待选静止目标信息为所述多个静止目标信息中的任一个,所述参考静止目标信息为所述多个静止目标信息中与所述待选静止目标信息之间距离小于距离预设值的静止目标信息。
可见,本申请实施例中,可以将不满足预设静止目标条件的待选静止目标信息进行剔除,剩下满足要求的静止目标信息,用于进行后续的定位计算和道路边界信息的计算。通过上述方式,能够有效地提升计算的准确性。
可选地,在上述图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述计算模块504,具体用于通过如下方式计算所述平均距离:
其中,所述d表示所述平均距离,所述M表示所述参考静止信息的个数,所述P表示所述待选静止目标信息的位置信息,所述P
i表示所述第i个参考静止信息的位置信息,所述i为大于0且小于或等于所述M的整数。
可见,本申请实施例中,介绍了一种计算平均距离的方式,通过该方式计算得到的平均距离具有较好的可靠性,且具有可操作性。
可选地,在上述图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述剔除模块505,具体用于若所述平均距离大于阈值门限,则确定所述平均距离不满足所述预设静止目标条件,并从所述测量信息中剔除所述待选静止目标信息。
可见,本申请实施例中,可以将平均距离大于阈值门限的待选静止目标信息进行剔除,剩下满足要求的静止目标信息,用于进行后续的定位计算和道路边界信息的计算。通过上述方式,能够有效地提升计算的准确性。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于通过如下方式计算所述道路边界信息:
f
θ(x
c)=θ
0+θ
1×x
c+θ
2×x
c
2+θ
3×x
c
3;
其中,所述f
θ(x
c)表示所述道路边界信息,所述θ
0表示第一系数,所述θ
1表示第二系数,所述θ
2表示第三系数,所述θ
3表示第四系数,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
c,y
c)表示所述静止目标在所述车辆坐标系下的位置信息,所述λ表示正则项系数,所述θ
j表示第j个系数,所述j为大于或等于0且小于或等于3的整数。
可见,本申请实施例中,介绍了一种计算道路边界信息的方式,通过该方式计算得到的道路边界信息具有较好的可靠性,且具有可操作性。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于根据所述当前道路边界信息以及历史道路边界信息计算所述当前帧时刻的增稳边界信息;
根据所述当前帧时刻的所述增稳边界信息获取所述目标车辆到至道路左侧边界的第一距离,以及所述目标车辆至道路右侧边界的第二距离;
根据所述第一距离和所述第二距离计算得到所述当前帧时刻的所述第一目标定位信息。
可见,本申请实施例中,可以根据当前帧时刻所对应的道路边界信息以及历史道路边界信息计算当前帧时刻的融合边界信息,根据当前帧时刻的融合边界信息获取车辆到至道路左侧边界的第一距离,以及车辆至道路右侧边界的第二距离,最后根据第一距离和第二距离计算得到当前帧时刻的第一目标定位信息。通过上述方式,能够提升第一目标定位信息的可靠性,也为方案的实行提供了一种可行的方式,从而增强方案的灵活性。
可选地,在上述图18、图19或图20所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于通过如下方式计算所述当前帧时刻所对应的所述增稳边界信息:
其中,所述f
θ'表示所述当前帧时刻所对应的所述增稳边界信息,所述f
θ_w(x
c)表示第w帧所对应的历史道路边界信息,所述W表示所述历史道路边界信息的个数,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述μ表示所述W帧的车道边界平均值。
可见,本申请实施例中,介绍了一种计算增稳边界信息的方式,通过该方式计算得到的融合边界信息具有较好的可靠性,且具有可操作性。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于通过如下方式计算所述当前帧时刻所的所述第一目标定位信息:
Location=(ceil(R
R-D),ceil(R
L-D));
D=(R
L+R
R)/N;
其中,所述Location表示所述当前帧时刻的所述第一目标定位信息,所述ceil表示向上取整的计算方式,所述R
L表示所述目标车辆到至所述道路左侧边界的第一距离,所述R
R表示所述目标车辆至所述道路右侧边界的第二距离,所述D表示所述车道的宽度,所述N表示所述车道的数量。
可见,本申请实施例中,介绍了一种计算第一目标定位信息的方式,通过该方式计算得到的第一目标定位信息具有较好的可靠性,且具有可操作性。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,所述测量信息还包括:至少一个运动目标信息;
所述获取模块501,还用于在所述确定模块502根据所述当前道路边界信息确定第一目标定位信息之前,从所述测量信息中获取所述至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,所述目标编号用于标定不同的运动目标;
所述确定模块,还用于根据所述获取模块获取到的所述至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;
所述确定模块,还用于根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,其中,所述第二目标定位信息用于表示所述目标车辆在道路中所在的位置。
可见,本申请实施例中,通过毫米波雷达同时获取多个静止目标信息和运动目标信息,结合两者进行道路边界信息的计算,以实现车辆的定位。采用运动目标信息可以辅助静止目标信息进行道路边界信息的计算,从而能够在车流量较大的时候,也能准确地完成车辆定位,以此提升方案的可行性和灵活性,并增加定位的置信度。
可选地,在上述图18或图19所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述获取模块501,具体用于根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,所述K为正整数;
根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取k帧中第L
k个车道被占据的情况,其中,所述k为大于0且小于或等于K的整数;
若车道占据比值小于预设比值,则确定所述第L
k个车道被占据,其中,所述车道占据比值为所述k个帧与所述K个帧的比值;
若所述车道占据比值大于或等于所述预设比值,则确定所述第L
k个车道未被占据;
所述确定模块502,具体用于将未被占据的所述第L
k个车道确定为所述当前帧时刻所对应的所述第二目标定位信息。
可见,本申请实施例中,根据当前帧时刻的至少一个运动目标信息以及至少一个运动目标信息以及对应的历史运动目标信息获取K帧运动目标信息数据,并根据当前帧时刻的运动目标信息以及历史运动目标信息获取k个图像中第L
k个车道被占据的情况。通过上述方式,可以更准确地确定车道被占据的情况,从而提升方案的实用性和可靠性。
可选地,在上述图18、图19或图20所对应的实施例的基础上,本申请实施例提供的车辆定位装置50的另一实施例中,
所述确定模块502,具体用于根据所述第二目标定位信息确定所述第一目标定位信息的置信度,其中,所述置信度用于表示所述第一目标定位信息的可信程度;
根据所述置信度确定所述当前时刻的所述第一目标定位信息。
可见,本申请实施例中,由运动目标信息确定的第二目标定位信息可用于确定第一目标定位信息的置信水平,置信水平表示区间估计的把握程度,由此,提升了融合定位的可行性和实用性。
本发明实施例还提供了另一种车辆定位装置,如图20所示,为了便于说明,仅示出了与本发明实施例相关的部分,具体技术细节未揭示的,请参照本发明实施例方法部分。该车辆定位装置可以为包括手机、平板电脑、个人数字助理(Personal Digital Assistant,PDA)、销售终端(Point of Sales,POS)、车载电脑等任意终端设备,以车辆定位装置为手机为例:
图20示出的是与本发明实施例提供的终端相关的手机的部分结构的框图。参考图20,手机包括:射频(Radio Frequency,RF)电路610、存储器620、输入单元630、显示单元640、传感器650、音频电路660、无线保真(wireless fidelity,WiFi)模块670、处理器680、以及电源690等部件。本领域技术人员可以理解,图20中示出的手机结构并不构成对手机的限定,可以包括比图示更多或更少的部件,或者组合某些部件,或者不同的部件布置。
下面结合图20对手机的各个构成部件进行具体的介绍:
RF电路610可用于收发信息或通话过程中,信号的接收和发送,特别地,将基站的下行信息接收后,给处理器680处理;另外,将设计上行的数据发送给基站。通常,RF电路610包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器(Low Noise Amplifier,LNA)、双工器等。此外,RF电路610还可以通过无线通信与网络和其他设备通信。上述无线通信可以使用任一通信标准或协议,包括但不限于全球移动通讯系统(Global System of Mobile communication,GSM)、通用分组无线服务(General Packet Radio Service,GPRS)、码分多址(Code Division Multiple Access,CDMA)、宽带码分多址(Wideband Code Division Multiple Access,WCDMA)、长期演进(Long Term Evolution,LTE)、电子邮件、短消息服务(Short Messaging Service,SMS)等。
存储器620可用于存储软件程序以及模块,处理器680通过运行存储在存储器620的软件程序以及模块,从而执行手机的各种功能应用以及数据处理。存储器620可主要包括存储程序区和存储数据区,其中,存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图像播放功能等)等;存储数据区可存储根据手机的使用所创建的数据(比如音频数据、电话本等)等。此外,存储器620可以包括高速随机存取存储器,还可以包括非易失性存储器,例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
输入单元630可用于接收输入的数字或字符信息,以及产生与手机的用户设置以及功能控制有关的键信号输入。具体地,输入单元630可包括触控面板631以及其他输入设备632。触控面板631,也称为触摸屏,可收集用户在其上或附近的触摸操作(比如用户使用 手指、触笔等任何适合的物体或附件在触控面板631上或在触控面板631附近的操作),并根据预先设定的程式驱动相应的连接装置。可选的,触控面板631可包括触摸检测装置和触摸控制器两个部分。其中,触摸检测装置检测用户的触摸方位,并检测触摸操作带来的信号,将信号传送给触摸控制器;触摸控制器从触摸检测装置上接收触摸信息,并将它转换成触点坐标,再送给处理器680,并能接收处理器680发来的命令并加以执行。此外,可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板631。除了触控面板631,输入单元630还可以包括其他输入设备632。具体地,其他输入设备632可以包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆等中的一种或多种。
显示单元640可用于显示由用户输入的信息或提供给用户的信息以及手机的各种菜单。显示单元640可包括显示面板641,可选的,可以采用液晶显示器(Liquid Crystal Display,LCD)、有机发光二极管(Organic Light-Emitting Diode,OLED)等形式来配置显示面板641。进一步的,触控面板631可覆盖显示面板641,当触控面板631检测到在其上或附近的触摸操作后,传送给处理器680以确定触摸事件的类型,随后处理器680根据触摸事件的类型在显示面板641上提供相应的视觉输出。虽然在图20中,触控面板631与显示面板641是作为两个独立的部件来实现手机的输入和输入功能,但是在某些实施例中,可以将触控面板631与显示面板641集成而实现手机的输入和输出功能。
手机还可包括至少一种传感器650,比如光传感器、运动传感器以及其他传感器。具体地,光传感器可包括环境光传感器及接近传感器,其中,环境光传感器可根据环境光线的明暗来调节显示面板641的亮度,接近传感器可在手机移动到耳边时,关闭显示面板641和/或背光。作为运动传感器的一种,加速计传感器可检测各个方向上(一般为三轴)加速度的大小,静止时可检测出重力的大小及方向,可用于识别手机姿态的应用(比如横竖屏切换、相关游戏、磁力计姿态校准)、振动识别相关功能(比如计步器、敲击)等;至于手机还可配置的陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器,在此不再赘述。
音频电路660、扬声器661,传声器662可提供用户与手机之间的音频接口。音频电路660可将接收到的音频数据转换后的电信号,传输到扬声器661,由扬声器661转换为声音信号输出;另一方面,传声器662将收集的声音信号转换为电信号,由音频电路660接收后转换为音频数据,再将音频数据输出处理器680处理后,经RF电路610以发送给比如另一手机,或者将音频数据输出至存储器620以便进一步处理。
WiFi属于短距离无线传输技术,手机通过WiFi模块670可以帮助用户收发电子邮件、浏览网页和访问流式媒体等,它为用户提供了无线的宽带互联网访问。虽然图20示出了WiFi模块670,但是可以理解的是,其并不属于手机的必须构成,完全可以根据需要在不改变发明的本质的范围内而省略。
处理器680是手机的控制中心,利用各种接口和线路连接整个手机的各个部分,通过运行或执行存储在存储器620内的软件程序和/或模块,以及调用存储在存储器620内的数据,执行手机的各种功能和处理数据,从而对手机进行整体监控。可选的,处理器680可 包括一个或多个处理单元;可选的,处理器680可集成应用处理器和调制解调处理器,其中,应用处理器主要处理操作系统、用户界面和应用程序等,调制解调处理器主要处理无线通信。可以理解的是,上述调制解调处理器也可以不集成到处理器680中。
手机还包括给各个部件供电的电源690(比如电池),可选的,电源可以通过电源管理系统与处理器680逻辑相连,从而通过电源管理系统实现管理充电、放电、以及功耗管理等功能。
尽管未示出,手机还可以包括摄像头、蓝牙模块等,在此不再赘述。
在本发明实施例中,该终端所包括的处理器680还具有以下功能:
在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,所述测量信息包括多个静止目标信息,所述多个静止目标信息用于表示多个静止目标的信息,所述多个静止目标信息与所述多个静止目标的信息一一对应;
根据所述测量信息确定所述当前帧时刻所对应的当前道路边界信息;
根据所述当前道路边界信息确定第一目标定位信息,其中,所述第一目标定位信息用于表示目标车辆在道路中所在的位置;
根据所述当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,所述道路曲率信息用于表示所述目标车辆所在道路的弯曲程度,所述历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,所述历史帧时刻为所述当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;
输出所述第一目标定位信息和所述道路曲率信息。
可选地,处理器680具体用于执行如下步骤:
通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,其中,所述跟踪信息包括所述多个静止目标在雷达坐标系中的位置信息和速度信息;
根据所述跟踪信息以及所述毫米波雷达的标定参数计算所述测量信息,其中,所述测量信息包括所述多个静止目标在车辆坐标系中的位置信息和速度信息,所述标定参数包括旋转量和平移量。
可选地,处理器680具体用于执行如下步骤:
所述预置角度范围包括第一预置角度范围和第二预置角度范围;
其中,所述通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,包括:
通过第一毫米波雷达获取所述第一预置角度范围内多个第一静止目标的第一跟踪信息,并通过第二毫米波雷达获取所述第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,所述跟踪信息包括所述第一跟踪信息和所述第二跟踪信息,所述多个静止目标包括所述多个第一静止目标和所述多个第二静止目标,所述毫米波雷达包括所述第一毫米波雷达和所述第二毫米波雷达,所述第一毫米波雷达的探测距离和覆盖视角与所述第二毫米波雷达的探测距离和覆盖视角不同;
根据所述第一跟踪信息以及所述毫米波雷达的标定参数计算所述第一预置角度范围内的第一测量信息,并根据所述第二跟踪信息以及所述毫米波雷达的标定参数计算所述第二 预置角度范围内的第二测量信息,其中,所述测量信息包括所述第一测量信息和所述第二测量信息。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述测量信息:
(x
c,y
c)=R×(x
r,y
r)+T;
(V
xc,V
yc)=R×(V
xr,V
yr);
其中,所述(x
c,y
c)表示静止目标在所述车辆坐标系下的位置信息,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
r,y
r)表示所述静止目标在所述雷达坐标系下的位置信息,所述x
r表示所述静止目标在所述雷达坐标系中的横轴坐标,所述y
r表示所述静止目标在所述雷达坐标系中的纵轴坐标,所述R表示所述旋转量,所述T表示所述平移量,所述(V
xc,V
yc)表示所述静止目标在所述车辆坐标系下的速度信息,所述V
xc表示所述静止目标在所述车辆坐标系中横轴方向的速度,所述V
yc表示所述静止目标在所述车辆坐标系中纵轴方向的速度,所述(V
xr,V
yr)表示所述静止目标在所述雷达坐标系中下的速度信息,所述V
xr表示所述静止目标在所述雷达坐标系中横轴方向的速度,所述V
yr表示所述静止目标在所述雷达坐标系中纵轴方向的速度。
可选地,处理器680还用于执行如下步骤:
根据所述道路边界信息以及所述历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,所述栅格区域覆盖于所述目标车辆,所述栅格区域包含多个栅格单元;
根据所述所述栅格区域中每个栅格单元的占据概率获取概率栅格图;
根据所述概率栅格图中的目标栅格单元确定融合边界信息,其中,所述目标栅格单元的占据概率大于预设概率门限;
根据所述融合边界信息计算所述道路曲率信息。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述每个栅格单元的占据概率:
p
n(x
c,y
c)=min(p(x
c,y
c)+p
n-1(x
c,y
c),1);
其中,所述p
n(x
c,y
c)表示n帧栅格单元的占据概率,所述p(x
c,y
c)表示所述道路边界信息,所述p
n-1(x
c,y
c)表示n-1帧的所述历史道路边界信息,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
c,y
c)表示所述静止目标在所述车辆坐标系下的位置信息,所述(x
c,y
c)'表示多帧所述静止目标在所述车辆坐标系下的位置信息的平均值,所述S表示所述x
c和所述y
c的协方差。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述道路曲率信息:
其中,所述Q表示所述道路曲率信息,所述g
θ(x
c)表示所述融合边界信息,所述g
θ'(x
c)表示所述g
θ(x
c)的一阶导数,所述g
θ″(x
c)表示所述g
θ(x
c)的二阶导数。
可选地,处理器680还用于执行如下步骤:
从所述测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,所述M为大于1的整数;
计算所述M个参考静止目标信息到所述待选静止目标信息之间的平均距离;
若所述平均距离不满足所述预设静止目标条件,则从所述测量信息中剔除所述待选静止目标信息;
其中,所述待选静止目标信息为所述多个静止目标信息中的任一个,所述参考静止目标信息为所述多个静止目标信息中与所述待选静止目标信息之间距离小于距离预设值的静止目标信息。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述平均距离:
其中,所述d表示所述平均距离,所述M表示所述参考静止信息的个数,所述P表示所述待选静止目标信息的位置信息,所述P
i表示所述第i个参考静止信息的位置信息,所述i为大于0且小于或等于所述M的整数。
可选地,处理器680具体用于执行如下步骤:
若所述平均距离大于阈值门限,则确定所述平均距离不满足所述预设静止目标条件,并从所述测量信息中剔除所述待选静止目标信息。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述道路边界信息:
f
θ(x
c)=θ
0+θ
1×x
c+θ
2×x
c
2+θ
3×x
c
3;
其中,所述f
θ(x
c)表示所述道路边界信息,所述θ
0表示第一系数,所述θ
1表示第二系数,所述θ
2表示第三系数,所述θ
3表示第四系数,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y
c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x
c,y
c)表示所述静止目标在所述车辆坐标系下的位置信息,所述λ表示正则项系数,所述θ
j表示第j个系数,所述j为大于或等于0且小于或等于3的整数。
可选地,处理器680具体用于执行如下步骤:
根据所述当前道路边界信息以及历史道路边界信息计算所述当前帧时刻的增稳边界信息;
根据所述当前帧时刻的所述增稳边界信息获取所述目标车辆到至道路左侧边界的第一距离,以及所述目标车辆至道路右侧边界的第二距离;
根据所述第一距离和所述第二距离计算得到所述当前帧时刻的所述第一目标定位信息。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述当前帧时刻所对应的所述增稳边界信息:
其中,所述f
θ'表示所述当前帧时刻所对应的所述增稳边界信息,所述f
θ_w(x
c)表示第w帧所对应的历史道路边界信息,所述W表示所述历史道路边界信息的个数,所述x
c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述μ表示所述W帧的车道边界平均值。
可选地,处理器680具体用于执行如下步骤:
通过如下方式计算所述当前帧时刻所的所述第一目标定位信息:
Location=(ceil(R
R-D),ceil(R
L-D));
D=(R
L+R
R)/N;
其中,所述Location表示所述当前帧时刻的所述第一目标定位信息,所述ceil表示向上取整的计算方式,所述R
L表示所述目标车辆到至所述道路左侧边界的第一距离,所述R
R表示所述目标车辆至所述道路右侧边界的第二距离,所述D表示所述车道的宽度,所述N表示所述车道的数量。
可选地,处理器680还用于执行如下步骤:
从所述测量信息中获取所述至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,所述目标编号用于标定不同的运动目标;
根据所述至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;
根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,其中,所述第二目标定位信息用于表示所述目标车辆在道路中所在的位置。
可选地,处理器680具体用于执行如下步骤:
根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,所述K为正整数;
根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取k帧中第L
k个车道被占据的情况,其中,所述k为大于0且小于或等于K的整数;
若车道占据比值小于预设比值,则确定所述第L
k个车道被占据,其中,所述车道占据比值为所述k个帧与所述K个帧的比值;
若所述车道占据比值大于或等于所述预设比值,则确定所述第L
k个车道未被占据;
将未被占据的所述第L
k个车道确定为所述当前帧时刻所对应的所述第二目标定位信息。
可选地,处理器680具体用于执行如下步骤:
根据所述第二目标定位信息确定所述第一目标定位信息的置信度,其中,所述置信度用于表示所述第一目标定位信息的可信程度;
根据所述置信度确定所述当前时刻的所述第一目标定位信息。
在上述实施例中,可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时,可以全部或部分地以计算机程序产品的形式实现。
所述计算机程序产品包括一个或多个计算机指令。在计算机上加载和执行所述计算机程序指令时,全部或部分地产生按照本发明实施例所述的流程或功能。所述计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。所述计算机指令可以存储在计算机可读存储介质中,或者从一个计算机可读存储介质向另一计算机可读存储介质传输,例如,所述计算机指令可以从一个网站站点、计算机、服务器或数据中心通过有线(例如同轴电缆、光纤、数字用户线(digital subscriber line,DSL))或无线(例如红外、无线、微波等)方式向另一个网站站点、计算机、服务器或数据中心进行传输。所述计算机可读存储介质可以是计算机能够存储的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。所述可用介质可以是磁性介质,(例如,软盘、硬盘、磁带)、光介质(例如,DVD)、或者半导体介质(例如固态硬盘solid state disk(SSD))等。
所属领域的技术人员可以清楚地了解到,为描述的方便和简洁,上述描述的系统,装置和单元的具体工作过程,可以参考前述方法实施例中的对应过程,在此不再赘述。
在本申请所提供的几个实施例中,应该理解到,所揭露的系统,装置和方法,可以通过其它的方式实现。例如,以上所描述的装置实施例仅仅是示意性的,例如,所述单元的划分,仅仅为一种逻辑功能划分,实际实现时可以有另外的划分方式,例如多个单元或组件可以结合或者可以集成到另一个系统,或一些特征可以忽略,或不执行。另一点,所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口,装置或单元的间接耦合或通信连接,可以是电性,机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的,作为单元显示的部件可以是或者也可以不是物理单元,即可以位于一个地方,或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外,在本申请各个实施例中的各功能单元可以集成在一个处理单元中,也可以是各个单元单独物理存在,也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现,也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时,可以存储在一个计算机可读取存储介质中。基于这样的理解,本申请的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来,该计算机软件产品存储在一个存储介质中,包括若干指令用以使得一台计算机设备(可以是个人计算机,服务器,或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括:U盘、移动硬盘、只读存储器(read-only memory,ROM)、随机存取存储器(random access memory,RAM)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述,以上实施例仅用以说明本申请的技术方案,而非对其限制;尽管参照前述实施例对本申请进行了详细的说明,本领域的普通技术人员应当理解:其依然可以对前述 各实施例所记载的技术方案进行修改,或者对其中部分技术特征进行等同替换;而这些修改或者替换,并不使相应技术方案的本质脱离本申请各实施例技术方案的精神和范围。
Claims (36)
- 一种车辆定位的方法,其特征在于,包括:在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,所述测量信息包括多个静止目标信息,所述多个静止目标信息用于表示多个静止目标的信息,所述多个静止目标信息与所述多个静止目标的信息一一对应;根据所述测量信息确定所述当前帧时刻所对应的当前道路边界信息;根据所述当前道路边界信息确定第一目标定位信息,其中,所述第一目标定位信息用于表示目标车辆在道路中所在的位置;根据所述当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,所述道路曲率信息用于表示所述目标车辆所在道路的弯曲程度,所述历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,所述历史帧时刻为所述当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;输出所述第一目标定位信息和所述道路曲率信息。
- 根据权利要求1所述的方法,其特征在于,所述通过测量设备获取预置角度范围内的测量信息,包括:通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,其中,所述跟踪信息包括所述多个静止目标在雷达坐标系中的位置信息和速度信息;根据所述跟踪信息以及所述毫米波雷达的标定参数计算所述测量信息,其中,所述测量信息包括所述多个静止目标在车辆坐标系中的位置信息和速度信息,所述标定参数包括旋转量和平移量。
- 根据权利要求2所述的方法,其特征在于,所述预置角度范围包括第一预置角度范围和第二预置角度范围;其中,所述通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,包括:通过第一毫米波雷达获取所述第一预置角度范围内多个第一静止目标的第一跟踪信息,并通过第二毫米波雷达获取所述第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,所述跟踪信息包括所述第一跟踪信息和所述第二跟踪信息,所述多个静止目标包括所述多个第一静止目标和所述多个第二静止目标,所述毫米波雷达包括所述第一毫米波雷达和所述第二毫米波雷达,所述第一毫米波雷达的探测距离和覆盖视角与所述第二毫米波雷达的探测距离和覆盖视角不同;所述根据所述跟踪信息以及所述毫米波雷达的标定参数计算所述测量信息,包括:根据所述第一跟踪信息以及所述毫米波雷达的标定参数计算所述第一预置角度范围内的第一测量信息,并根据所述第二跟踪信息以及所述毫米波雷达的标定参数计算所述第二预置角度范围内的第二测量信息,其中,所述测量信息包括所述第一测量信息和所述第二测量信息。
- 根据权利要求2或3所述的方法,其特征在于,通过如下方式计算所述测量信息:(x c,y c)=R×(x r,y r)+T;(V xc,V yc)=R×(V xr,V yr);其中,所述(x c,y c)表示静止目标在所述车辆坐标系下的位置信息,所述x c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x r,y r)表示所述静止目标在所述雷达坐标系下的位置信息,所述x r表示所述静止目标在所述雷达坐标系中的横轴坐标,所述y r表示所述静止目标在所述雷达坐标系中的纵轴坐标,所述R表示所述旋转量,所述T表示所述平移量,所述(V xc,V yc)表示所述静止目标在所述车辆坐标系下的速度信息,所述V xc表示所述静止目标在所述车辆坐标系中横轴方向的速度,所述V yc表示所述静止目标在所述车辆坐标系中纵轴方向的速度,所述(V xr,V yr)表示所述静止目标在所述雷达坐标系中下的速度信息,所述V xr表示所述静止目标在所述雷达坐标系中横轴方向的速度,所述V yr表示所述静止目标在所述雷达坐标系中纵轴方向的速度。
- 根据权利要求1至4中任一项所述的方法,其特征在于,所述根据所述道路边界信息与历史道路边界信息确定道路曲率信息,包括:根据所述道路边界信息以及所述历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,所述栅格区域覆盖于所述目标车辆,所述栅格区域包含多个栅格单元;根据所述所述栅格区域中每个栅格单元的占据概率获取概率栅格图;根据所述概率栅格图中的目标栅格单元确定融合边界信息,其中,所述目标栅格单元的占据概率大于预设概率门限;根据所述融合边界信息计算所述道路曲率信息。
- 根据权利要求5所述的方法,其特征在于,通过如下方式计算所述每个栅格单元的占据概率:p n(x c,y c)=min(p(x c,y c)+p n-1(x c,y c),1);其中,所述p n(x c,y c)表示n帧栅格单元的占据概率,所述p(x c,y c)表示所述道路边界信息,所述p n-1(x c,y c)表示n-1帧的所述历史道路边界信息,所述x c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x c,y c)表示所述静止目标在所述车辆坐标系下的位置信息,所述(x c,y c)'表示多帧所述静止目标在所述车辆坐标系下的位置信息的平均值,所述S表示所述x c和所述y c的协方差。
- 根据权利要求1至7中任一项所述的方法,其特征在于,在所述根据所述测量信息 确定所述当前帧时刻所对应的当前道路边界信息之前,所述方法还包括:从所述测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,所述M为大于1的整数;计算所述M个参考静止目标信息到所述待选静止目标信息之间的平均距离;若所述平均距离不满足所述预设静止目标条件,则从所述测量信息中剔除所述待选静止目标信息;其中,所述待选静止目标信息为所述多个静止目标信息中的任一个,所述参考静止目标信息为所述多个静止目标信息中与所述待选静止目标信息之间距离小于距离预设值的静止目标信息。
- 根据权利要求8或9所述的方法,其特征在于,所述若所述平均距离不满足预设静止目标条件,则从所述测量信息中剔除所述待选静止目标信息,包括:若所述平均距离大于阈值门限,则确定所述平均距离不满足所述预设静止目标条件,并从所述测量信息中剔除所述待选静止目标信息。
- 根据权利要求1至11中任一项所述的方法所述的方法,其特征在于,所述根据所述当前帧时刻所对应的道路边界信息确定第一目标定位信息,包括:根据所述当前道路边界信息以及历史道路边界信息计算所述当前帧时刻的增稳边界信息;根据所述当前帧时刻的所述增稳边界信息获取所述目标车辆到至道路左侧边界的第一距离,以及所述目标车辆至道路右侧边界的第二距离;根据所述第一距离和所述第二距离计算得到所述当前帧时刻的所述第一目标定位信息。
- 根据权利要求12或13所述的方法,其特征在于,通过如下方式计算所述当前帧时刻所的所述第一目标定位信息:Location=(ceil(R R-D),ceil(R L-D));D=(R L+R R)/N;其中,所述Location表示所述当前帧时刻的所述第一目标定位信息,所述ceil表示向上取整的计算方式,所述R L表示所述目标车辆到至所述道路左侧边界的第一距离,所述R R表示所述目标车辆至所述道路右侧边界的第二距离,所述D表示所述车道的宽度,所述N表示所述车道的数量。
- 根据权利要求1至14中任一项所述的方法,其特征在于,所述测量信息还包括:至少一个运动目标信息,在所述根据所述当前道路边界信息确定第一目标定位信息之前,所述方法还包括:从所述测量信息中获取所述至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,所述目标编号用于标定不同的运动目标;根据所述至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,其中,所述第二目标定位信息用于表示所述目标车辆在道路中所在的位置。
- 根据权利要求15所述的方法,其特征在于,所述根据所述当前帧时刻的所述至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息,包括:根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,所述K为正整数;根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取k帧中第L k个车道被占据的情况,其中,所述k为大于0且小于或等于K的整数;若车道占据比值小于预设比值,则确定所述第L k个车道被占据,其中,所述车道占据比值为所述k个帧与所述K个帧的比值;若所述车道占据比值大于或等于所述预设比值,则确定所述第L k个车道未被占据;所述根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,包括:将未被占据的所述第L k个车道确定为所述当前帧时刻所对应的所述第二目标定位信息。
- 根据权利要求1至16中任一项所述的方法,其特征在于,所述根据所述当前帧时刻所对应的道路边界信息确定第一目标定位信息,包括:根据所述第二目标定位信息确定所述第一目标定位信息的置信度,其中,所述置信度用于表示所述第一目标定位信息的可信程度;根据所述置信度确定所述当前时刻的所述第一目标定位信息。
- 一种车辆定位装置,其特征在于,包括:获取模块,用于在当前帧时刻,通过测量设备获取预置角度范围内的测量信息,其中,所述测量信息包括多个静止目标信息,所述多个静止目标信息用于表示多个静止目标的信息,所述多个静止目标信息与所述多个静止目标的信息一一对应;确定模块,用于根据所述获取模块获取的所述测量信息确定所述当前帧时刻所对应的当前道路边界信息;所述确定模块,用于根据所述当前道路边界信息确定第一目标定位信息,其中,所述第一目标定位信息用于表示目标车辆在道路中所在的位置;所述确定模块,用于根据所述当前道路边界信息与历史道路边界信息确定道路曲率信息,其中,所述道路曲率信息用于表示所述目标车辆所在道路的弯曲程度,所述历史道路边界信息包括至少一个历史帧时刻所对应的道路边界信息,所述历史帧时刻为所述当前帧时刻之前获取到道路边界信息和道路曲率信息的时刻;输出模块,用于输出所述确定模块确定的所述第一目标定位信息和所述确定模块确定的所述道路曲率信息。
- 根据权利要求18所述的车辆定位装置,其特征在于,所述获取模块,具体用于通过毫米波雷达获取所述预置角度范围内所述多个静止目标的跟踪信息,其中,所述跟踪信息包括所述多个静止目标在雷达坐标系中的位置信息和速度信息;根据所述跟踪信息以及所述毫米波雷达的标定参数计算所述测量信息,其中,所述测量信息包括所述多个静止目标在车辆坐标系中的位置信息和速度信息,所述标定参数包括旋转量和平移量。
- 根据权利要求19所述的车辆定位装置,其特征在于,所述预置角度范围包括第一预置角度范围和第二预置角度范围;所述获取模块,具体用于通过第一毫米波雷达获取所述第一预置角度范围内多个第一静止目标的第一跟踪信息,并通过第二毫米波雷达获取所述第二预置角度范围内多个第二静止目标的第二跟踪信息,其中,所述跟踪信息包括所述第一跟踪信息和所述第二跟踪信息,所述多个静止目标包括所述多个第一静止目标和所述多个第二静止目标,所述毫米波雷达包括所述第一毫米波雷达和所述第二毫米波雷达,所述第一毫米波雷达的探测距离和覆盖视角与所述第二毫米波雷达的探测距离和覆盖视角不同;根据所述第一跟踪信息以及所述毫米波雷达的标定参数计算所述第一预置角度范围内的第一测量信息,并根据所述第二跟踪信息以及所述毫米波雷达的标定参数计算所述第二预置角度范围内的第二测量信息,其中,所述测量信息包括所述第一测量信息和所述第二测量信息。
- 根据权利要求19或20所述的车辆定位装置,其特征在于,所述获取模块,具体用于通过如下方式计算所述测量信息:(x c,y c)=R×(x r,y r)+T;(V xc,V yc)=R×(V xr,V yr);其中,所述(x c,y c)表示静止目标在所述车辆坐标系下的位置信息,所述x c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x r,y r)表示所述静止目标在所述雷达坐标系下的位置信息,所述x r表示所述静止目标在所述雷达坐标系中的横轴坐标,所述y r表示所述静止目标在所述雷达坐标系中的纵轴坐标,所述R表示所述旋转量,所述T表示所述平移量,所述(V xc,V yc)表示所述静止目标在所述车辆坐标系下的速度信息,所述V xc表示所述静止目标在所述车辆坐标系中横轴方向的速度,所述V yc表示所述静止目标在所述车辆坐标系中纵轴方向的速度,所述(V xr,V yr)表示所述静止目标在所述雷达坐标系中下的速度信息,所述V xr表示所述静止目标在所述雷达坐标系中横轴方向的速度,所述V yr表示所述静止目标在所述雷达坐标系中纵轴方向的速度。
- 根据权利要求18至21中任一项所述的车辆定位装置,其特征在于,所述确定模块,具体用于根据所述道路边界信息以及所述历史道路边界信息计算栅格区域中每个栅格单元的占据概率,其中,所述栅格区域覆盖于所述目标车辆,所述栅格区域包含多个栅格单元;根据所述所述栅格区域中每个栅格单元的占据概率获取概率栅格图;根据所述概率栅格图中的目标栅格单元确定融合边界信息,其中,所述目标栅格单元的占据概率大于预设概率门限;根据所述融合边界信息计算所述道路曲率信息。
- 根据权利要求22所述的车辆定位装置,其特征在于,所述确定模块,具体用于通过如下方式计算所述每个栅格单元的占据概率:p n(x c,y c)=min(p(x c,y c)+p n-1(x c,y c),1);其中,所述p n(x c,y c)表示n帧栅格单元的占据概率,所述p(x c,y c)表示所述道路边界信息,所述p n-1(x c,y c)表示n-1帧的所述历史道路边界信息,所述x c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x c,y c)表示所述静止目标在所述车辆坐标系下的位置信息,所述(x c,y c)'表示多帧所述静止目标在所述车辆坐标系下的位置信息的平均值,所述S表示所述x c和所述y c的协方差。
- 根据权利要求18至24中任一项所述的车辆定位装置,其特征在于,所述车辆定 位装置还包括计算模块和剔除模块;所述获取模块,还用于在所述确定模块根据所述测量信息确定所述当前帧时刻所对应的当前道路边界信息之前,从所述测量信息中获取待选静止目标信息以及M个参考静止目标信息,其中,所述M为大于1的整数;所述计算模块,用于计算所述获取模块获取的所述M个参考静止目标信息到所述待选静止目标信息之间的平均距离;所述剔除模块,用于若所述计算模块计算得到的所述平均距离不满足所述预设静止目标条件,则从所述测量信息中剔除所述待选静止目标信息;其中,所述待选静止目标信息为所述多个静止目标信息中的任一个,所述参考静止目标信息为所述多个静止目标信息中与所述待选静止目标信息之间距离小于距离预设值的静止目标信息。
- 根据权利要求25或26所述的车辆定位装置,其特征在于,所述剔除模块,具体用于若所述平均距离大于阈值门限,则确定所述平均距离不满足所述预设静止目标条件,并从所述测量信息中剔除所述待选静止目标信息。
- 根据权利要求18至27中任一项所述的车辆定位装置,其特征在于,所述确定模块,具体用于通过如下方式计算所述道路边界信息:f θ(x c)=θ 0+θ 1×x c+θ 2×x c 2+θ 3×x c 3;其中,所述f θ(x c)表示所述道路边界信息,所述θ 0表示第一系数,所述θ 1表示第二系数,所述θ 2表示第三系数,所述θ 3表示第四系数,所述x c表示所述静止目标在所述车辆坐标系中的横轴坐标,所述y c表示所述静止目标在所述车辆坐标系中的纵轴坐标,所述(x c,y c)表示所述静止目标在所述车辆坐标系下的位置信息,所述λ表示正则项系数,所述θ j表示第j个系数,所述j为大于或等于0且小于或等于3的整数。
- 根据权利要求18至28中任一项所述的车辆定位装置,其特征在于,所述确定模块,具体用于根据所述当前道路边界信息以及历史道路边界信息计算所述当前帧时刻的增稳边界信息;根据所述当前帧时刻的所述增稳边界信息获取所述目标车辆到至道路左侧边界的第一距离,以及所述目标车辆至道路右侧边界的第二距离;根据所述第一距离和所述第二距离计算得到所述当前帧时刻的所述第一目标定位信息。
- 根据权利要求29或30所述的车辆定位装置,其特征在于,所述确定模块,具体用于通过如下方式计算所述当前帧时刻所的所述第一目标定位信息:Location=(ceil(R R-D),ceil(R L-D));D=(R L+R R)/N;其中,所述Location表示所述当前帧时刻的所述第一目标定位信息,所述ceil表示向上取整的计算方式,所述R L表示所述目标车辆到至所述道路左侧边界的第一距离,所述R R表示所述目标车辆至所述道路右侧边界的第二距离,所述D表示所述车道的宽度,所述N表示所述车道的数量。
- 根据权利要求18至31中任一项所述的车辆定位装置,其特征在于,所述测量信息还包括:至少一个运动目标信息;所述获取模块,还用于在所述确定模块根据所述当前道路边界信息确定第一目标定位信息之前,从所述测量信息中获取所述至少一个运动目标信息,其中,每一运动目标信息中携带目标编号,所述目标编号用于标定不同的运动目标;所述确定模块,还用于根据所述获取模块获取到的所述至少一个运动目标信息以及对应的历史运动目标信息确定车道占据信息;所述确定模块,还用于根据所述车道占据信息确定所述当前帧时刻所对应的第二目标定位信息,其中,所述第二目标定位信息用于表示所述目标车辆在道路中所在的位置。
- 根据权利要求32所述的车辆定位装置,其特征在于,所述获取模块,具体用于根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取K帧运动目标信息数据,其中,所述K为正整数;根据所述至少一个运动目标信息以及所述至少一个运动目标信息对应的历史运动目标信息获取k帧中第L k个车道被占据的情况,其中,所述k为大于0且小于或等于K的整数;若车道占据比值小于预设比值,则确定所述第L k个车道被占据,其中,所述车道占据比值为所述k个帧与所述K个帧的比值;若所述车道占据比值大于或等于所述预设比值,则确定所述第L k个车道未被占据;所述确定模块,具体用于将未被占据的所述第L k个车道确定为所述当前帧时刻所对应的所述第二目标定位信息。
- 根据权利要求18至33中任一项所述的车辆定位装置,其特征在于,所述确定模块,具体用于根据所述第二目标定位信息确定所述第一目标定位信息的置信度,其中,所述置信度用于表示所述第一目标定位信息的可信程度;根据所述置信度确定所述当前时刻的所述第一目标定位信息。
- 一种车辆定位装置,其特征在于,包括:存储器、收发器、处理器以及总线系统;其中,所述存储器用于存储程序和指令;所述收发器用于在所述处理器的控制下接收或发送信息;所述处理器用于执行所述存储器中的程序;所述总线系统用于连接所述存储器、所述收发器以及所述处理器,以使所述存储器、所述收发器以及所述处理器进行通信;所述处理器用于调用所述存储器中的程序指令,执行如权利要求1至17中任一项所述的方法。
- 一种计算机可读存储介质,包括指令,当其在计算机上运行时,使得计算机执行如权利要求1-17中任一项所述的方法。
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP18900778.4A EP3734389B1 (en) | 2018-01-16 | 2018-09-28 | Vehicle positioning method and apparatus |
US16/929,432 US20200348408A1 (en) | 2018-01-16 | 2020-07-15 | Vehicle Positioning Method and Vehicle Positioning Apparatus |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810040981.0 | 2018-01-16 | ||
CN201810040981.0A CN110044371A (zh) | 2018-01-16 | 2018-01-16 | 一种车辆定位的方法以及车辆定位装置 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/929,432 Continuation US20200348408A1 (en) | 2018-01-16 | 2020-07-15 | Vehicle Positioning Method and Vehicle Positioning Apparatus |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019140950A1 true WO2019140950A1 (zh) | 2019-07-25 |
Family
ID=67272971
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2018/108329 WO2019140950A1 (zh) | 2018-01-16 | 2018-09-28 | 一种车辆定位的方法以及车辆定位装置 |
Country Status (4)
Country | Link |
---|---|
US (1) | US20200348408A1 (zh) |
EP (1) | EP3734389B1 (zh) |
CN (1) | CN110044371A (zh) |
WO (1) | WO2019140950A1 (zh) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10690654B2 (en) | 2017-01-30 | 2020-06-23 | Vivebio Scientific, Llc | Plasma separation device |
CN111812601A (zh) * | 2020-07-06 | 2020-10-23 | 南京隼眼电子科技有限公司 | 雷达性能的评估方法及存储介质 |
CN112558072A (zh) * | 2020-12-22 | 2021-03-26 | 北京百度网讯科技有限公司 | 车辆定位方法、装置、系统、电子设备及存储介质 |
CN112859062A (zh) * | 2021-01-19 | 2021-05-28 | 巍泰技术(武汉)有限公司 | 一种基于雷达的车辆排队长度检测方法及系统 |
CN113156451A (zh) * | 2021-03-23 | 2021-07-23 | 北京易控智驾科技有限公司 | 非结构化道路边界检测方法、装置、存储介质和电子设备 |
CN113791414A (zh) * | 2021-08-25 | 2021-12-14 | 南京市德赛西威汽车电子有限公司 | 一种基于毫米波车载雷达视图的场景识别方法 |
CN113970725A (zh) * | 2020-07-24 | 2022-01-25 | 北京万集科技股份有限公司 | 雷达检测区域的标定方法、装置、设备及存储介质 |
CN114047501A (zh) * | 2021-09-30 | 2022-02-15 | 苏州豪米波技术有限公司 | 一种基于毫米波雷达的室内定位系统 |
CN114296450A (zh) * | 2021-12-15 | 2022-04-08 | 北京爱笔科技有限公司 | 路径规划方法、装置、计算机设备和存储介质 |
Families Citing this family (46)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP7223629B2 (ja) * | 2019-05-13 | 2023-02-16 | 日立Astemo株式会社 | 車載システム、外界認識センサ、電子制御装置 |
CN212737906U (zh) * | 2019-08-15 | 2021-03-19 | 株式会社小糸制作所 | 车辆用灯具及车辆 |
KR102628027B1 (ko) * | 2019-09-10 | 2024-01-24 | 주식회사 에이치엘클레무브 | 객체 인식 장치 및 그 방법 |
CN112630798B (zh) * | 2019-09-24 | 2022-11-29 | 北京百度网讯科技有限公司 | 用于估计地面的方法和装置 |
CN110780288A (zh) * | 2019-09-29 | 2020-02-11 | 深圳市元征科技股份有限公司 | 道路危险提示方法、装置、车载设备和存储介质 |
US11262208B2 (en) * | 2019-09-30 | 2022-03-01 | Here Global B.V. | Lane level routing and navigation using lane level dynamic profiles |
CN110794392B (zh) * | 2019-10-15 | 2024-03-19 | 上海创昂智能技术有限公司 | 车辆定位方法、装置、车辆及存储介质 |
CN110941003B (zh) * | 2019-10-25 | 2022-02-25 | 北京汽车集团有限公司 | 车辆识别方法,装置,存储介质及电子设备 |
CN111121714B (zh) * | 2019-12-25 | 2021-10-26 | 中公高科养护科技股份有限公司 | 一种行车视距的测量方法及系统 |
CN111221000B (zh) * | 2020-01-16 | 2022-11-18 | 中电科(宁波)海洋电子研究院有限公司 | 基于激光雷达的船舶边界探测方法 |
CN112639522B (zh) * | 2020-02-21 | 2021-10-26 | 华为技术有限公司 | 一种车辆行驶速度、加速度的测量方法、装置及存储介质 |
CN111323038B (zh) * | 2020-03-27 | 2021-10-26 | 新石器慧通(北京)科技有限公司 | 隧道内无人驾驶车辆的定位方法、系统和电子设备 |
CN111708014A (zh) * | 2020-05-26 | 2020-09-25 | 烟台陆地智能科技有限公司 | 一种毫米波雷达的封闭空间内部非合作目标定位及测量方法 |
CN111830969B (zh) * | 2020-06-12 | 2024-03-26 | 北京布科思科技有限公司 | 一种基于反光板及二维码的融合对接方法 |
CN112099042B (zh) * | 2020-08-07 | 2024-04-12 | 武汉万集信息技术有限公司 | 车辆跟踪方法以及系统 |
CN113126077B (zh) * | 2020-08-13 | 2024-03-22 | 纵目科技(上海)股份有限公司 | 盲点区域的目标检测系统、方法及介质 |
CN111959515B (zh) * | 2020-08-19 | 2023-11-03 | 无锡威孚高科技集团股份有限公司 | 一种基于视觉检测的前向目标选择方法、装置及系统 |
CN111968405A (zh) * | 2020-08-26 | 2020-11-20 | 北京小马慧行科技有限公司 | 确定自动驾驶车辆的行驶车道的方法及装置 |
CN112489495B (zh) * | 2020-10-26 | 2023-01-17 | 浙江吉利控股集团有限公司 | 一种车辆预警方法、装置、电子设备及存储介质 |
US20220179039A1 (en) * | 2020-12-08 | 2022-06-09 | Aptiv Technologies Limited | Facia Supporting an Ultra-Wide Radar Field-of-View |
CN112597839B (zh) * | 2020-12-14 | 2022-07-08 | 上海宏景智驾信息科技有限公司 | 基于车载毫米波雷达的道路边界检测方法 |
US12105192B2 (en) | 2020-12-17 | 2024-10-01 | Aptiv Technologies AG | Radar reference map generation |
US20220196829A1 (en) * | 2020-12-17 | 2022-06-23 | Aptiv Technologies Limited | Radar Reference Map Generation |
US11988741B2 (en) | 2020-12-17 | 2024-05-21 | Aptiv Technologies AG | Vehicle routing based on availability of radar-localization objects |
CN112763995B (zh) * | 2020-12-24 | 2023-09-01 | 阿波罗智联(北京)科技有限公司 | 雷达标定方法、装置、电子设备和路侧设备 |
CN112738764B (zh) * | 2020-12-28 | 2021-12-24 | 北京邮电大学 | 一种基于车辆运动轨迹认知的宽带毫米波波束追踪方法 |
US12099962B2 (en) | 2020-12-31 | 2024-09-24 | Yum Connect, LLC | Methods and systems for detecting delivery trip events and improving delivery driver safety |
CN114858119B (zh) * | 2021-02-04 | 2024-04-02 | 长沙智能驾驶研究院有限公司 | 边距测量方法、装置、设备及计算机存储介质 |
CN112505671B (zh) * | 2021-02-07 | 2021-05-25 | 北方工业大学 | Gnss信号缺失环境下毫米波雷达目标定位方法及装置 |
CN113075716B (zh) * | 2021-03-19 | 2024-10-22 | 地平线(上海)人工智能技术有限公司 | 基于图像的车辆定位方法和装置、存储介质以及电子设备 |
CN113479191B (zh) * | 2021-06-30 | 2023-04-07 | 重庆长安汽车股份有限公司 | 用于泊车的无车道线的车道边界检测系统、方法及车辆 |
CN113465608B (zh) * | 2021-07-22 | 2024-05-03 | 清华大学苏州汽车研究院(吴江) | 一种路侧传感器标定方法及系统 |
CN113740836A (zh) * | 2021-07-31 | 2021-12-03 | 南京市德赛西威汽车电子有限公司 | 一种基于毫米波雷达的静止目标跟踪优化方法 |
CN113639782B (zh) * | 2021-08-13 | 2024-10-29 | 北京地平线信息技术有限公司 | 车载传感器的外参标定方法和装置、设备和介质 |
CN113702929B (zh) * | 2021-08-16 | 2024-07-05 | 中汽创智科技有限公司 | 一种车载雷达安装角度校准方法、装置、设备及存储介质 |
CN113759377B (zh) * | 2021-08-26 | 2023-09-01 | 追觅创新科技(苏州)有限公司 | 自移动设备定位方法、装置、存储介质、设备及系统 |
CN113963551B (zh) * | 2021-10-18 | 2022-09-27 | 中国电力科学研究院有限公司 | 基于协作定位的车辆定位方法、系统、设备及介质 |
CN114115230B (zh) * | 2021-10-25 | 2023-10-03 | 武汉理工大学 | 人机协同的船舶远程驾驶控制方法、系统、装置及介质 |
CN114333298B (zh) * | 2021-12-02 | 2024-02-23 | 河北雄安京德高速公路有限公司 | 一种基于交通雷达的车辆归属车道估计方法 |
CN114331966B (zh) * | 2021-12-02 | 2024-02-13 | 北京斯年智驾科技有限公司 | 基于高斯过程占位图估计辅助的港口锁站方法及其系统 |
US12092726B2 (en) | 2021-12-10 | 2024-09-17 | Honeywell International Inc. | Methods and systems for millimeter wave assisted vehicle navigation |
CN114509751A (zh) * | 2022-02-11 | 2022-05-17 | 海信集团控股股份有限公司 | 一种基于雷达的目标跟踪方法及装置 |
US11810459B1 (en) | 2022-05-09 | 2023-11-07 | Aptiv Technologies Limited | Vehicle localization based on radar detections in garages |
CN114906154B (zh) * | 2022-05-26 | 2024-10-01 | 重庆长安汽车股份有限公司 | 车辆行驶道路类别判断方法、系统、电子设备及存储介质 |
CN115166654B (zh) * | 2022-06-24 | 2024-10-01 | 海信集团控股股份有限公司 | 一种多毫米波雷达标定方法、装置及存储介质 |
CN118411382B (zh) * | 2024-07-02 | 2024-09-24 | 杭州百子尖科技股份有限公司 | 边界点检测方法、装置、电子设备及存储介质 |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6191704B1 (en) * | 1996-12-19 | 2001-02-20 | Hitachi, Ltd, | Run environment recognizing apparatus |
CN102481931A (zh) * | 2009-09-30 | 2012-05-30 | 日立汽车系统株式会社 | 车辆控制装置 |
CN102591332A (zh) * | 2011-01-13 | 2012-07-18 | 同济大学 | 用于无人驾驶汽车局部路径规划的装置及方法 |
CN104029676A (zh) * | 2013-03-05 | 2014-09-10 | 通用汽车环球科技运作有限责任公司 | 车辆车道确定 |
CN105197008A (zh) * | 2014-06-23 | 2015-12-30 | 丰田自动车株式会社 | 报警装置和行驶控制装置 |
CN105279958A (zh) * | 2015-11-13 | 2016-01-27 | 奇瑞汽车股份有限公司 | 车队管理系统及方法 |
CN106708040A (zh) * | 2016-12-09 | 2017-05-24 | 重庆长安汽车股份有限公司 | 自动驾驶系统的传感器模块、自动驾驶系统及方法 |
CN107031600A (zh) * | 2016-10-19 | 2017-08-11 | 东风汽车公司 | 基于高速公路的自动驾驶系统 |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3427809B2 (ja) * | 2000-03-09 | 2003-07-22 | 株式会社デンソー | 車両用道路形状認識方法及び装置、記録媒体 |
DE10218924A1 (de) * | 2002-04-27 | 2003-11-06 | Bosch Gmbh Robert | Verfahren und Vorrichtung zur Kursprädiktion bei Kraftfahrzeugen |
US7043342B1 (en) * | 2003-11-10 | 2006-05-09 | Thomas Gerret Dewees | Vehicle tracking driver assistance system |
JP2011517632A (ja) * | 2008-02-20 | 2011-06-16 | コンチネンタル・テーヴエス・アクチエンゲゼルシヤフト・ウント・コンパニー・オツフエネハンデルスゲゼルシヤフト | 車両の周辺にある物体を検出する方法及び援助システム |
JP5206752B2 (ja) * | 2010-08-30 | 2013-06-12 | 株式会社デンソー | 走行環境認識装置 |
US8452535B2 (en) * | 2010-12-13 | 2013-05-28 | GM Global Technology Operations LLC | Systems and methods for precise sub-lane vehicle positioning |
KR101144193B1 (ko) * | 2012-02-07 | 2012-05-10 | 뉴비전엔지니어링(주) | 영상도화정보와 지피에스정보를 이용한 영상도화의 데이터 수집시스템 |
WO2015037173A1 (ja) * | 2013-09-12 | 2015-03-19 | パナソニック株式会社 | レーダ装置、車両及び移動体速度検出方法 |
DE102014221888A1 (de) * | 2014-10-28 | 2016-04-28 | Robert Bosch Gmbh | Verfahren und Vorrichtung zur Lokalisierung eines Fahrzeugs in seinem Umfeld |
DE102015002155A1 (de) * | 2015-02-18 | 2016-08-18 | Audi Ag | Verfahren zur Ermittlung einer Ortsinformation eines Kraftfahrzeugs bezüglich eines Fahrkorridors und Kraftfahrzeug |
KR20160147491A (ko) * | 2015-06-15 | 2016-12-23 | 한국전자통신연구원 | 3차원 모델 생성 장치 및 방법 |
EP3358368A4 (en) * | 2015-09-30 | 2019-03-13 | Sony Corporation | SIGNAL PROCESSING APPARATUS, SIGNAL PROCESSING METHOD, AND PROGRAM |
US9802599B2 (en) * | 2016-03-08 | 2017-10-31 | Ford Global Technologies, Llc | Vehicle lane placement |
CN106203341B (zh) * | 2016-07-11 | 2019-05-21 | 百度在线网络技术(北京)有限公司 | 一种无人车的车道线识别方法及装置 |
CN106500705A (zh) * | 2016-10-20 | 2017-03-15 | 上海智驾电子科技有限公司 | 基于车道线检测的定位系统及定位方法 |
CN106780524B (zh) * | 2016-11-11 | 2020-03-06 | 厦门大学 | 一种三维点云道路边界自动提取方法 |
CN106767853B (zh) * | 2016-12-30 | 2020-01-21 | 中国科学院合肥物质科学研究院 | 一种基于多信息融合的无人驾驶车辆高精度定位方法 |
CN106918342B (zh) * | 2017-03-10 | 2020-01-03 | 广州汽车集团股份有限公司 | 无人驾驶车辆行驶路径定位方法及定位系统 |
-
2018
- 2018-01-16 CN CN201810040981.0A patent/CN110044371A/zh active Pending
- 2018-09-28 WO PCT/CN2018/108329 patent/WO2019140950A1/zh unknown
- 2018-09-28 EP EP18900778.4A patent/EP3734389B1/en active Active
-
2020
- 2020-07-15 US US16/929,432 patent/US20200348408A1/en not_active Abandoned
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6191704B1 (en) * | 1996-12-19 | 2001-02-20 | Hitachi, Ltd, | Run environment recognizing apparatus |
CN102481931A (zh) * | 2009-09-30 | 2012-05-30 | 日立汽车系统株式会社 | 车辆控制装置 |
CN102591332A (zh) * | 2011-01-13 | 2012-07-18 | 同济大学 | 用于无人驾驶汽车局部路径规划的装置及方法 |
CN104029676A (zh) * | 2013-03-05 | 2014-09-10 | 通用汽车环球科技运作有限责任公司 | 车辆车道确定 |
CN105197008A (zh) * | 2014-06-23 | 2015-12-30 | 丰田自动车株式会社 | 报警装置和行驶控制装置 |
CN105279958A (zh) * | 2015-11-13 | 2016-01-27 | 奇瑞汽车股份有限公司 | 车队管理系统及方法 |
CN107031600A (zh) * | 2016-10-19 | 2017-08-11 | 东风汽车公司 | 基于高速公路的自动驾驶系统 |
CN106708040A (zh) * | 2016-12-09 | 2017-05-24 | 重庆长安汽车股份有限公司 | 自动驾驶系统的传感器模块、自动驾驶系统及方法 |
Non-Patent Citations (1)
Title |
---|
See also references of EP3734389A4 |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10690654B2 (en) | 2017-01-30 | 2020-06-23 | Vivebio Scientific, Llc | Plasma separation device |
US11650198B2 (en) | 2017-01-30 | 2023-05-16 | Vivebio Scientific, Llc | Plasma separation device |
CN111812601A (zh) * | 2020-07-06 | 2020-10-23 | 南京隼眼电子科技有限公司 | 雷达性能的评估方法及存储介质 |
CN113970725A (zh) * | 2020-07-24 | 2022-01-25 | 北京万集科技股份有限公司 | 雷达检测区域的标定方法、装置、设备及存储介质 |
CN112558072A (zh) * | 2020-12-22 | 2021-03-26 | 北京百度网讯科技有限公司 | 车辆定位方法、装置、系统、电子设备及存储介质 |
CN112558072B (zh) * | 2020-12-22 | 2024-05-28 | 阿波罗智联(北京)科技有限公司 | 车辆定位方法、装置、系统、电子设备及存储介质 |
CN112859062A (zh) * | 2021-01-19 | 2021-05-28 | 巍泰技术(武汉)有限公司 | 一种基于雷达的车辆排队长度检测方法及系统 |
CN112859062B (zh) * | 2021-01-19 | 2023-11-24 | 巍泰技术(武汉)有限公司 | 一种基于雷达的车辆排队长度检测方法及系统 |
CN113156451A (zh) * | 2021-03-23 | 2021-07-23 | 北京易控智驾科技有限公司 | 非结构化道路边界检测方法、装置、存储介质和电子设备 |
CN113791414A (zh) * | 2021-08-25 | 2021-12-14 | 南京市德赛西威汽车电子有限公司 | 一种基于毫米波车载雷达视图的场景识别方法 |
CN113791414B (zh) * | 2021-08-25 | 2023-12-29 | 南京市德赛西威汽车电子有限公司 | 一种基于毫米波车载雷达视图的场景识别方法 |
CN114047501A (zh) * | 2021-09-30 | 2022-02-15 | 苏州豪米波技术有限公司 | 一种基于毫米波雷达的室内定位系统 |
CN114047501B (zh) * | 2021-09-30 | 2024-05-14 | 苏州豪米波技术有限公司 | 一种基于毫米波雷达的室内定位系统 |
CN114296450A (zh) * | 2021-12-15 | 2022-04-08 | 北京爱笔科技有限公司 | 路径规划方法、装置、计算机设备和存储介质 |
Also Published As
Publication number | Publication date |
---|---|
US20200348408A1 (en) | 2020-11-05 |
CN110044371A (zh) | 2019-07-23 |
EP3734389A1 (en) | 2020-11-04 |
EP3734389A4 (en) | 2021-02-24 |
EP3734389B1 (en) | 2022-06-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2019140950A1 (zh) | 一种车辆定位的方法以及车辆定位装置 | |
CN110147705B (zh) | 一种基于视觉感知的车辆定位方法及电子设备 | |
WO2021128777A1 (en) | Method, apparatus, device, and storage medium for detecting travelable region | |
US11320836B2 (en) | Algorithm and infrastructure for robust and efficient vehicle localization | |
WO2020147485A1 (zh) | 一种信息处理方法、系统、设备和计算机存储介质 | |
CN110795523B (zh) | 车辆定位方法、装置以及智能车辆 | |
CN108762245B (zh) | 数据融合方法以及相关设备 | |
US10262234B2 (en) | Automatically collecting training data for object recognition with 3D lidar and localization | |
CN108253975B (zh) | 一种建立地图信息及车辆定位的方法与设备 | |
KR102103170B1 (ko) | 모바일 디바이스의 위치정보 제공 방법 및 장치 | |
CN110926484B (zh) | 车辆位置的获取方法、装置以及智能车辆 | |
CN111366161B (zh) | 车辆定位方法及电子设备 | |
US20230278563A1 (en) | Positioning method and related apparatus | |
US20170307400A1 (en) | Device for providing electric-moving-body information and method for providing electric-moving-body information | |
US11269048B2 (en) | Radar sensor array for interference hunting and detection | |
CN107645702B (zh) | 位置标定方法、装置和系统 | |
US10694485B2 (en) | Method and apparatus for correcting multipath offset and determining wireless station locations | |
CN109451578A (zh) | 一种定位方法及装置 | |
CN113807470A (zh) | 一种车辆行驶状态确定方法和相关装置 | |
CN113820694A (zh) | 一种仿真测距的方法、相关装置、设备以及存储介质 | |
CN113993071B (zh) | 定位方法、装置、设备和存储介质 | |
CN113516870B (zh) | 待泊车位确定方法、装置、自动泊车设备和存储介质 | |
CN116674540A (zh) | 车辆通过控制方法、装置、电子设备及可读存储介质 | |
CN111862682A (zh) | 一种模型确定方法和相关装置 | |
CN114625828A (zh) | 一种车道级数据匹配方法、装置、电子设备和存储介质 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 18900778 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
ENP | Entry into the national phase |
Ref document number: 2018900778 Country of ref document: EP Effective date: 20200728 |