CN116295473A - Unmanned vehicle path planning method, unmanned vehicle path planning device, unmanned vehicle path planning equipment and storage medium - Google Patents
Unmanned vehicle path planning method, unmanned vehicle path planning device, unmanned vehicle path planning equipment and storage medium Download PDFInfo
- Publication number
- CN116295473A CN116295473A CN202211529575.3A CN202211529575A CN116295473A CN 116295473 A CN116295473 A CN 116295473A CN 202211529575 A CN202211529575 A CN 202211529575A CN 116295473 A CN116295473 A CN 116295473A
- Authority
- CN
- China
- Prior art keywords
- path
- unmanned vehicle
- cost
- distance
- dynamic obstacle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 61
- 230000003068 static effect Effects 0.000 claims abstract description 57
- 238000005070 sampling Methods 0.000 claims abstract description 34
- 238000004590 computer program Methods 0.000 claims description 19
- 230000007423 decrease Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 abstract description 5
- 230000004888 barrier function Effects 0.000 description 17
- 230000000875 corresponding effect Effects 0.000 description 13
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 8
- 230000007613 environmental effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 230000000670 limiting effect Effects 0.000 description 4
- 238000013507 mapping Methods 0.000 description 4
- 238000004364 calculation method 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
- 238000004458 analytical method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 235000012054 meals Nutrition 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 238000004659 sterilization and disinfection 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
- G01C21/3407—Route searching; Route guidance specially adapted for specific applications
- G01C21/343—Calculating itineraries, i.e. routes leading from a starting point to a series of categorical destinations using a global route restraint, round trips, touristic trips
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The disclosure relates to the technical field of unmanned vehicles, and provides a path planning method, device and equipment for an unmanned vehicle and a storage medium. The method can be used for unmanned vehicles, namely unmanned equipment or automatic driving equipment, aiming at a road area in front of the unmanned vehicles, sampling can be conducted at intervals along the length direction or the width direction of the road area to obtain a path point array, then the cost of each path point is determined based on collision risks of the unmanned vehicles with dynamic obstacles and static obstacle areas in the road area and risks of crossing road boundaries when the unmanned vehicles are located at each path point, and target path points are selected from rows of the path point array based on the cost to generate a planned path. By the path planning method, collision of the unmanned vehicle can be avoided, and meanwhile, the problem of low communication efficiency caused by the fact that the unmanned vehicle always runs behind the dynamic obstacle can be avoided as the dynamic obstacle is bypassed when the path point is determined.
Description
Technical Field
The disclosure relates to the technical field of automatic driving, and in particular relates to a method, a device, equipment and a storage medium for unmanned vehicle path planning.
Background
Path planning is a key element in the unmanned process. The path planning refers to that a driving path meeting various constraint conditions (such as safety, path smoothness, dynamic constraint of the vehicle and the like) is planned for the unmanned vehicle based on analysis and processing of environment information, vehicle driving information, barrier information and the like acquired by sensors on the unmanned vehicle. The current path planning method only considers partial environment information, so that the planned path is not ideal enough, and the passing efficiency of unmanned vehicles can be seriously affected in certain scenes.
Disclosure of Invention
In view of this, the embodiments of the present disclosure provide a method, apparatus, device and storage medium for unmanned vehicle path planning.
In a first aspect of an embodiment of the present disclosure, a method for planning a path of an unmanned vehicle is provided, where the method includes:
the method comprises the steps that a road area in front of an unmanned aerial vehicle is sampled at intervals to obtain a path point array, wherein each row of path points in the path point array are distributed along the width direction of the road area, and each column of path points in the path point array are distributed along the length direction of the road area;
determining a cost corresponding to each waypoint in the waypoint array, the cost determined based at least on a collision risk with a dynamic obstacle in a road area, a collision risk with a static obstacle in the road area, and a risk of crossing a road boundary when an unmanned vehicle is located at each waypoint;
And selecting a target path point from a plurality of path points in each row of the path point array based on the cost, and generating a planning path according to the selected target path point in each row.
A second aspect of an embodiment of the present disclosure provides a path planning apparatus for an unmanned vehicle, the apparatus including:
the sampling module is used for performing interval sampling on a road area in front of the unmanned aerial vehicle to obtain a path point array, wherein each row of path points in the path point array are distributed along the width direction of the road area, and each column of path points in the path point array are distributed along the length direction of the road area;
a cost determination module configured to determine a cost corresponding to each waypoint in the waypoint array, the cost being determined based at least on a collision risk with a dynamic obstacle in a road area, a collision risk with a static obstacle in the road area, and a risk of crossing a road boundary when an unmanned vehicle is located at each waypoint;
and the path generation module is used for selecting a target path point from a plurality of path points in each row of the path point array based on the cost and generating a planning path according to the selected target path point in each row.
A third aspect of the embodiments of the present disclosure provides an electronic device, where the electronic device includes a processor and a memory, where the computer program is stored in the memory and executable by the processor, and the method mentioned in the first aspect may be implemented when the processor executes the computer program.
In a fourth aspect of the embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the method mentioned in the first aspect.
The above-mentioned at least one technical scheme that the embodiment of the disclosure adopted can reach following beneficial effect:
the method comprises the steps of aiming at a road area in front of an unmanned vehicle, sampling at intervals along the length direction or the width direction of the road area to obtain a path point array, determining the cost of each path point based on the collision risk with a dynamic barrier in the road area and a static barrier area and the risk of crossing a road boundary when the unmanned vehicle is positioned at each path point, and selecting a target path point from each row of the path point array based on the cost to generate a planned path. By sampling the road area at intervals in the length direction and the width direction respectively, a path point array is obtained, so that the sampled path points can more uniformly cover all positions of the road area, the road area is more representative, and the planned path of the target path point selected based on the sampled path points is more reasonable. And when planning the route, the situations of static obstacles, dynamic obstacles and road boundaries are comprehensively considered, so that collision of the unmanned aerial vehicle can be avoided, and meanwhile, the problem of low communication efficiency caused by that the unmanned aerial vehicle always follows behind the dynamic obstacles can be avoided as the dynamic obstacles are bypassed when the route points are determined.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings that are required for the embodiments or the description of the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and other drawings may be obtained according to these drawings without inventive effort for a person of ordinary skill in the art.
Fig. 1 is a schematic diagram of a planned path affecting unmanned vehicle passing efficiency in one embodiment of the present disclosure.
Fig. 2 (a) is a flow chart of a path planning method in one embodiment of the present disclosure.
Fig. 2 (b) is a schematic diagram of a path planning method in one embodiment of the present disclosure.
Fig. 3 (a) -3 (d) are schematic diagrams of collision situations of an unmanned vehicle and a dynamic obstacle in one embodiment of the present disclosure.
FIG. 4 is a schematic diagram of optimizing an initial path based on vehicle dynamics in one embodiment of the present disclosure.
Fig. 5 is a logic structure diagram of a road planning apparatus in one embodiment of the present disclosure.
Fig. 6 is a logical block diagram of an electronic device in one embodiment of the present disclosure.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples are not representative of all implementations consistent with the present disclosure. Rather, they are merely examples of apparatus and methods consistent with some aspects of the present disclosure as detailed in the accompanying claims.
The terminology used in the present disclosure is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. As used in this disclosure and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used in this disclosure to describe various information, these information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present disclosure. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "responsive to a determination", depending on the context.
With the development of unmanned technology, unmanned vehicles are increasingly used in various fields. The path planning is a key link in the unmanned process, and the path planning refers to analyzing and processing various information such as environmental information acquired by sensors on the unmanned vehicle, running state information of the unmanned vehicle, barrier information and the like, and planning a running path meeting various constraint conditions (such as safety, path smoothness, dynamic constraint of the vehicle and the like) for the unmanned vehicle based on analysis processing results. And carrying out speed planning at the same time of path planning, wherein the speed planning is to determine the running speed of each path point on the running path of the unmanned vehicle.
The path planning and the speed planning are generally simplified into an equation solving problem, namely, the surrounding obstacle information (such as the position and the speed of the obstacle, and the like) is known, the running state information of the unmanned vehicle, the destination of the unmanned vehicle, a high-precision map, and the like, and the position and the speed of the unmanned vehicle at each moment in a future period (generally 8 s) are solved. Because the problem needs to solve the positions and the speeds corresponding to different time points in the three-dimensional space, the calculated amount is very large, and the path planning efficiency is low.
In order to reduce the calculation amount, one method of planning the path and the speed is that: the path planning and the speed planning are decoupled, namely, the path can be planned firstly, a series of path points can be determined based on the distribution condition of the static obstacles in the road when the path is planned, and the path points can bypass the static obstacles to avoid collision. And then, speed planning is carried out, namely, the speed of the unmanned vehicle at each path point is respectively determined according to the information (such as the movement speed, the movement track and the like) of the dynamic obstacle in the road aiming at each determined path point, so as to avoid collision with the dynamic obstacle. The method is equivalent to the step of disassembling the high-dimension problem into a plurality of low-dimension problems, so that the calculated amount can be reduced, and the calculation speed can be improved.
Although the path planning method can reduce the calculated amount, and can obtain ideal planned paths in most driving environments. However, the applicant found that, for some more complex scenarios, for example, in the case of a large traffic flow in the driving environment, only part of the environmental information (for example, only the distribution situation of the static obstacle is considered) is considered in the path planning stage, which results in lower traffic efficiency and longer duration of the unmanned vehicle driving to the destination when the unmanned vehicle is driven based on the planned path.
For example, as shown in fig. 1, with the existing path planning method, the planned path bypasses a static obstacle in the road, for example, a planned path 1 is generated, but if the moving speed of a dynamic obstacle in the road is low, according to the existing path planning method, the unmanned vehicle can only follow the dynamic obstacle and run at a slower speed, so that the passing efficiency is low. In the actual path planning process, the unmanned vehicle can completely bypass the dynamic obstacle, for example, can run according to the planned path 2, so as to improve the passing efficiency.
Based on this, the embodiment of the disclosure provides a path planning method, when planning a path of an unmanned vehicle, for a road area at a front position of the unmanned vehicle, the road area may be subjected to interval sampling along a length direction and a width direction of the road area, so as to obtain a path point array that substantially covers the road area. For each waypoint in the waypoint array, a cost corresponding to each waypoint may be determined based at least on the risk of collision with a dynamic obstacle in the road area, the risk of collision with a static obstacle in the road area, and the risk of crossing the road boundary when the drone is at that waypoint, which cost may be used to evaluate how appropriate each waypoint is as a waypoint on the drone's planned path, e.g., the smaller the risk of collision of the drone with a dynamic or static obstacle, the more appropriate the waypoint the drone will not exceed the road boundary is as a waypoint on the planned path. Then, for each row in the array of path points, a target path point may be selected from a plurality of path points in the row based on the cost, and a planned path may be generated from the target path points selected for each row.
By sampling the road area at intervals in the length direction and the width direction respectively, a path point array is obtained, so that the sampled path points can more uniformly cover all positions of the road area, the road area is more representative, and the planned path of the target path point selected based on the sampled path points is more reasonable. And when planning the route, the situations of static obstacles, dynamic obstacles and road boundaries are comprehensively considered, so that collision of the unmanned aerial vehicle can be avoided, and meanwhile, the problem of low communication efficiency caused by that the unmanned aerial vehicle always follows behind the dynamic obstacles can be avoided as the dynamic obstacles are bypassed when the route points are determined.
The unmanned vehicle in the embodiment of the disclosure can be various movable devices which are provided with sensors and can control the unmanned vehicle to move based on environmental information acquired by the sensors, and the unmanned vehicle can be an unmanned vehicle used in various fields, such as a mining unmanned vehicle, an unmanned meal delivery vehicle, an unmanned disinfection vehicle and the like.
The unmanned vehicle path planning method provided by the embodiment of the disclosure can be executed by vehicle-mounted equipment installed on the unmanned vehicle, for example, the unmanned vehicle can be executed by a controller on the unmanned vehicle, the controller on the unmanned vehicle can acquire environment information acquired by various sensors (such as a laser radar, a camera, a positioning sensor and the like) on the unmanned vehicle, running state information of the unmanned vehicle, road information and a high-precision map, and then a path is planned based on the information. Of course, in some scenes, considering that the requirement of path planning on computing capacity is high, the method can also be executed by the cloud server, for example, the unmanned vehicle can send environmental information acquired by various sensors on the unmanned vehicle, running state information of the unmanned vehicle and the like to the cloud server, and the cloud server generates a planned path and then sends the planned path to the unmanned vehicle.
The method for planning the path of the unmanned vehicle provided by the embodiment of the disclosure can be executed at regular intervals (for example, 100 ms) in the driving process of the unmanned vehicle, for example, the path in a future period (for example, 8 s) is planned when the unmanned vehicle plans each time, so that the method for planning the path can be executed every interval or every preset distance travelled by the unmanned vehicle.
As shown in fig. 2 (a), a flowchart of a method for planning a path of an unmanned vehicle according to an embodiment of the present disclosure may include the following steps:
s202, performing interval sampling processing on a road area in front of an unmanned aerial vehicle to obtain a path point array, wherein each row of path points in the path point array are distributed along the width direction of the road area, and each column of path points in the path point array are distributed along the length direction of the road area;
in step S202, the relevant information of the road area in front of the unmanned vehicle, such as the road width, the position of the road boundary, etc., may be determined based on the high-precision map of the traveling area of the unmanned vehicle, and then the interval sampling process may be performed on the road area in front of the unmanned vehicle, where the length of the road area may be determined based on the traveling speed of the unmanned vehicle, such as the traveling speed of the unmanned vehicle is longer, and the length of the path predicted each time may be longer, i.e., the length of the road area may be set longer, or vice versa. After determining the relevant information of the road area in front of the unmanned aerial vehicle, the road area can be subjected to interval sampling processing based on the information, and a plurality of path points are determined in the road area and used as potential path points on the unmanned aerial vehicle planning path. As shown in fig. 2 (b), in order to obtain the route points by sampling, the road area may be covered more uniformly, and the route points may be sampled at intervals along the width direction and the length direction of the road area, so as to obtain a route point array, where each row of route points in the route point array are distributed along the width direction of the road area, and each column of route points are distributed along the length direction of the road area, so that the route points obtained by sampling may cover the road area uniformly.
In the interval sampling process, the sampling intervals in different directions can be set based on actual requirements, and the distance between two adjacent path points in each row can be the same or different.
S204, determining a cost corresponding to each path point in the path point array, wherein the cost is determined at least based on collision risk with a dynamic obstacle in a road area, collision risk with a static obstacle in the road area and risk crossing a road boundary when an unmanned vehicle is positioned at each path point;
in step S204, after the sampling to obtain the path point array, a cost corresponding to each path point in the path point array may be determined, where the cost may be used to evaluate the suitability of the path point as a path point on the planned path. For example, when an unmanned vehicle is located at a certain route point, the lower the collision probability with various obstacles in the road is, the lower the probability that the unmanned vehicle crosses the road boundary is, the more suitable the unmanned vehicle is as a route point on a planned route. In general, in order to ensure that the unmanned vehicles do not collide, the unmanned vehicles need not to exceed the road boundary and the distance from the static obstacle cannot be too small when located at the waypoints, and thus, the cost of each waypoint can be determined according to the collision risk of the unmanned vehicles with the static obstacle in the road area and the risk of crossing the road boundary. In addition, although the dynamic obstacle can bypass by controlling the speed of the unmanned vehicle, that is, the collision can be avoided without considering the dynamic obstacle when determining the route point, since the scene of bypassing the dynamic obstacle only by controlling the speed of the unmanned vehicle, a problem occurs in that the determined planned route appears as shown in fig. 1, that is, the unmanned vehicle can always travel behind the dynamic obstacle, although the collision does not occur, but when the movement speed of the dynamic obstacle is very low, the passing efficiency of the unmanned vehicle is affected. Therefore, the collision risk of the dynamic obstacle in the unmanned road can also be taken into account when determining the cost, so that the collision situation with the dynamic obstacle is also taken into account when determining the waypoint.
In some scenarios, the smaller the cost, the smaller the probability that the unmanned vehicle collides at the waypoint and out of range occurs, i.e. the more suitable the waypoint is as the waypoint on the planned path. When the unmanned vehicle is located at a certain path point, the information such as the size, the position, the distribution condition and the like of the static barrier in the surrounding environment can be determined through the environmental information perceived by the sensor (such as a camera, a laser radar, a millimeter wave radar and the like) on the unmanned vehicle. Similarly, the information such as the size, the position, the distribution condition, the movement speed and the like of the dynamic obstacle in the road area can also be determined through the environmental information sensed by the sensor on the unmanned vehicle, and the positions of the dynamic obstacle at different moments can be predicted based on the movement speed and the movement track of the dynamic obstacle.
S206, selecting a target path point from a plurality of path points in the line based on the cost aiming at each line in the path point array, and generating a planning path according to the selected target path point in each line.
In step S206, after determining the cost of each of the path point arrays, for each row of the path point arrays, a target path point, such as a black point in fig. 2 (b), may be selected from the plurality of path points in the row based on the cost of each path point in the row. Generally, the smaller the cost is, the smaller the probability that the unmanned vehicle collides with the path point and out of range occurs, namely the path point is more suitable for being used as the path point on the planned path, so that the path point with the minimum cost can be selected as the target path point, or any path point with the cost smaller than the preset threshold value can be selected as the target path point. A planned path may then be generated from the target path points selected for each row.
When sampling is performed at intervals in a road area, if the distance between two adjacent path points is shorter in the width direction or the length direction, namely, the sampling interval is shorter, the sampling precision is higher, the more path points are obtained through sampling, the more paths are ideal finally, but after the number of the path points obtained through sampling is increased, the calculated amount is increased to a certain extent, and the processing efficiency is reduced. In some embodiments, in order to obtain a more suitable sampling interval, a more ideal planned path may be obtained, and the calculation amount is not too high. The distance (i.e., sampling interval) between two adjacent waypoints in each row and/or each column of the waypoint array may be determined based on one or more of the following information: the current running speed of the unmanned vehicle, the distribution condition of the obstacles in the road area and the size of the obstacles in the road area.
When the unmanned vehicle is traveling at a higher speed, the road area to be planned is usually longer, the sampling interval may be appropriately larger, and conversely, the sampling interval may be smaller. When static barriers and dynamic barriers distributed in the road area are more and denser, the sampling interval can be set smaller to ensure the driving safety and avoid the barriers as much as possible so as to improve the sampling precision. In addition, the sampling interval may also be adjusted based on the size of the obstacle in the road area, for example, when the size of the obstacle in the road area is large, the sampling interval may be set larger, and conversely, may be set smaller, so that the most suitable planned path may be obtained.
In some embodiments, the collision risk with a dynamic obstacle in a road area when an unmanned vehicle is located at a certain waypoint may also be characterized by a certain cost, hereinafter collectively referred to as a dynamic obstacle collision cost. The smaller the collision cost of the dynamic obstacle is, the smaller the collision risk of the unmanned vehicle and the dynamic obstacle is. The collision condition of the unmanned vehicle and the dynamic obstacle is influenced by a plurality of factors such as the relative position relation of the unmanned vehicle and the dynamic obstacle, the distance between the unmanned vehicle and the dynamic obstacle, the movement speed and the movement direction of the unmanned vehicle and the dynamic obstacle. Therefore, when the unmanned vehicle is located on a certain path point, the relative position relation and distance between the unmanned vehicle and the dynamic barriers in the surrounding environment, the movement speed of the unmanned vehicle and the movement speed of the dynamic barriers can be determined, for example, when the unmanned vehicle is located on the path point, the current position, the movement speed, the movement track and the like of the dynamic barriers collected by the sensors on the unmanned vehicle can be estimated, the position of the surrounding dynamic barriers is determined, the distance between the unmanned vehicle and each dynamic barrier when the unmanned vehicle is located on the path point, the speed direction and the speed of the unmanned vehicle and each dynamic barrier are determined, and the probability of collision between the unmanned vehicle and each dynamic barrier is determined based on the factors. The movement speed of the unmanned vehicle and the movement speed of the dynamic obstacle can be the current speed of the unmanned vehicle and the dynamic obstacle, or the average speed of the unmanned vehicle and the dynamic obstacle in a period of time.
It is considered that a dynamic obstacle located on an extension line of the speed direction of the unmanned vehicle is an object that the unmanned vehicle needs to pay attention to. As shown in fig. 3 (a), if the dynamic obstacle is located on an extension line of the speed direction of the unmanned vehicle and the speed of the dynamic obstacle is in the same direction as the speed of the unmanned vehicle, in this case, if the movement speed of the unmanned vehicle is smaller than the speed of the dynamic obstacle, no collision occurs even if the two are located closer together. Thus, in some embodiments, if the speed of movement of the drone is less than the speed of movement of the dynamic obstacle, the dynamic obstacle collision cost is 0, i.e., the risk of collision of the two is minimal.
If the speed of movement of the unmanned vehicle is not less than the speed of the dynamic obstacle, the collision risk is related to the distance between the two. When the distance between the unmanned vehicle and the dynamic obstacle is smaller than a certain critical point, for example, the risk of collision is greatly increased, and when the distance is larger than the critical point, the risk of collision is not changed greatly. Therefore, a safe distance for ensuring that the unmanned vehicle and the dynamic obstacle do not collide can be set, and the first distance threshold is hereinafter referred to as a first distance threshold, and the first distance threshold can be a preset fixed threshold, or can be adjusted in real time based on information such as the sizes, the movement speeds, the types and the like of the unmanned vehicle and the dynamic obstacle.
In order to determine the collision costs of the dynamic obstacle at different distances, a mapping relationship between the collision costs of the dynamic obstacle and the distances may be preset. Wherein the mapping relationship may follow the following law: under the condition that the movement speed of the unmanned vehicle is not less than the movement speed of the dynamic obstacle and the distance between the unmanned vehicle and the dynamic obstacle is less than the first distance threshold, the collision cost of the dynamic obstacle can show a sharp increasing trend along with the reduction of the distance between the unmanned vehicle and the dynamic obstacle, and under the condition that the movement speed of the unmanned vehicle is not less than the movement speed of the dynamic obstacle and the distance between the unmanned vehicle and the dynamic obstacle is greater than the first distance threshold, the collision cost of the dynamic obstacle shows a slow increasing trend along with the reduction of the distance between the unmanned vehicle and the dynamic obstacle.
As shown in fig. 3 (b), if the dynamic obstacle is located on an extension line of the speed direction of the unmanned vehicle and the speed of the dynamic obstacle is reversed from the speed of the unmanned vehicle, the collision risk thereof is related to the distance therebetween. For example, when the distance between the unmanned vehicle and the dynamic obstacle is smaller than the first distance threshold, the collision cost of the dynamic obstacle may show a steep increase trend along with the decrease of the distance between the unmanned vehicle and the dynamic obstacle, and when the distance between the unmanned vehicle and the dynamic obstacle is larger than the first distance threshold, the collision cost of the dynamic obstacle shows a slow increase trend along with the decrease of the distance between the unmanned vehicle and the dynamic obstacle.
As shown in fig. 3 (c), if the dynamic obstacle is located on the extension line of the speed direction of the unmanned vehicle, and the included angle between the speed of the dynamic obstacle and the speed of the unmanned vehicle is within a preset included angle, for example, 5 ° to 170 °, the preset included angle range may be set based on the two sizes, then the collision between the unmanned vehicle and the dynamic obstacle will not happen with a high probability, and at this time, the collision cost of the dynamic obstacle may also be set to 0.
As shown in fig. 3 (d), if the dynamic obstacle is not on the extension line of the speed direction of the unmanned vehicle, the probability that the dynamic obstacle is at collision risk can be comprehensively determined based on the relative position of the dynamic obstacle and the extension line of the speed direction of the unmanned vehicle, the included angle of the speed direction and the speed, and then the collision cost of the dynamic obstacle can be determined.
In some embodiments, when the drone is located at each waypoint, the risk of collision with a static obstacle in the road area may also be characterized by a cost, hereinafter referred to as a static obstacle collision cost, the smaller the risk of collision of the drone with the static obstacle. Since the static obstacle position is unchanged, when the distance between the unmanned vehicle and the static obstacle exceeds a certain critical distance, the unmanned vehicle basically does not collide with the static obstacle, and when the distance is smaller than the critical distance, the smaller the distance between the unmanned vehicle and the static obstacle is, the larger the risk of collision is. Therefore, a safety distance, hereinafter referred to as a second distance threshold, may be set to ensure that the unmanned vehicle does not collide with the static obstacle. The second distance threshold may be a fixed threshold set in advance, or may be adjusted in real time based on the movement speed of the unmanned vehicle, the type of the dynamic obstacle, and the like.
In order to determine the collision cost of the static obstacle under different distances, a mapping relation between the distance between the unmanned vehicle and the static obstacle and the collision cost of the static obstacle can be preset, and the mapping relation can follow the following rules: when the distance between the unmanned vehicle and the static obstacle is smaller than the second distance threshold, the static obstacle cost is negatively related to the distance between the unmanned vehicle and the static obstacle, and when the distance between the unmanned vehicle and the static obstacle is larger than the second distance threshold, the static obstacle cost is 0.
In some embodiments, when an unmanned vehicle is located at each waypoint, the risk of the unmanned vehicle crossing the road boundary may be characterized by a crossing cost, wherein a smaller crossing cost indicates a smaller risk of the unmanned vehicle crossing the road boundary. When the distance between the unmanned vehicle and the road boundary exceeds a certain threshold value, the condition of crossing the road boundary basically does not occur, otherwise, the closer the distance between the unmanned vehicle and the road boundary is, the greater the risk of crossing the boundary is. Therefore, a safe distance between the unmanned vehicle and the road boundary, hereinafter referred to as a third distance threshold, may also be set, and in the case that the distance between the waypoint and the road boundary is smaller than the third distance threshold, the cross-boundary cost negatively correlates to the distance between the waypoint and the road boundary. In the case where the distance between the waypoint and the road boundary is greater than the third distance threshold, the cross-boundary cost is 0.
In planning a path of an unmanned vehicle, it is desirable to plan the path as smoothly as possible, for example, without making a sharp turn or the like, in addition to taking into consideration that no collision occurs and that the path does not cross a road boundary. In addition, when planning a route of an unmanned vehicle, a global route is usually planned based on a high-precision map and a destination of the unmanned vehicle, and the reference route is usually located in a middle position of a road. In path planning, it is often desirable that the planned path be close to the reference path.
Therefore, in some embodiments, the cost of each waypoint may also be determined based on a steering cost that characterizes the steering condition of the drone, where a smaller steering cost indicates a flatter planned path. In order to make the planned path of the unmanned vehicle as gentle as possible, the steering cost may be positively related to the offset of each path point in the road width direction from the target path point selected in the previous row, and negatively related to the offset of each path point in the road length direction from the target path point selected in the previous row.
In some embodiments, the cost of each of the waypoints is also determined based on a deviated reference path cost that characterizes the unmanned vehicle's deviation from the reference path, which may be positively correlated to the distance of each of the waypoints from the reference path.
In some embodiments, the total cost corresponding to each path point may be obtained by integrating the dynamic obstacle cost, the static obstacle cost, the cross-boundary cost, the steering cost and the deviation reference path cost, for example, the total cost may be a weighted average of the above costs. The importance degree of different types of costs is also different, so that the influence of each cost on path planning can be controlled by adjusting the weight of each cost. Considering that dynamic barrier costs, static barrier costs, cross-boundary costs and the like directly affect driving safety, the weights corresponding to the costs can be set larger. The steering cost and the deviation cost from the reference path have little influence on the driving safety, but influence the comfort level in the driving process, so the weights of the costs can be set smaller. Of course, for the dynamic obstacle collision cost, the static obstacle collision cost, and the like, the respective corresponding weights may also be adjusted based on the magnitude of the collision risk, for example, the higher the collision risk, the greater the weight thereof. Taking the collision cost of the dynamic obstacle as an example, the weight can be adjusted based on the relative position, the speed included angle or the speed of the dynamic obstacle and the unmanned vehicle, so that the higher the collision risk, the larger the weight.
In addition, when the path planning is performed, the planned path also needs to conform to the dynamic characteristics of the vehicle, for example, the curvature of the path, the curvature change rate needs to conform to the attribute range of the unmanned vehicle, and the like. Thus, in some embodiments, as shown in fig. 4, after the target waypoints are selected from each row in the waypoint array, the selected target waypoints of each row may be connected along the length of the road area to obtain an initial path, which may then be optimized based on vehicle dynamics to obtain a planned path that satisfies the unmanned vehicle dynamics constraints.
To further explain the path planning method provided by the embodiments of the present disclosure, the following is explained in connection with a specific embodiment.
At present, when a path planning is carried out on an unmanned vehicle, a planning path capable of bypassing the static obstacle is generally determined based on the distribution condition of the static obstacle in a road area, and then the speed of the unmanned vehicle at each path point of the planning path is determined by combining the distribution condition of the dynamic obstacle so as to avoid the dynamic obstacle. The way of planning the path may have the problem that the unmanned vehicle always follows a dynamic obstacle with slow running speed to run, so that the passing efficiency of the unmanned vehicle is low.
In order to solve the above problems, the present embodiment provides a method for planning a path of an unmanned vehicle, which specifically includes the following steps:
1. and performing interval sampling processing on a road area in front of the unmanned aerial vehicle to obtain a path point array.
The method of path planning may be performed once at intervals (e.g., 100 ms) for the unmanned vehicle to plan a travel path within a road area of a preset length in the forward direction. The road area can be sampled at intervals along the width direction and the length direction of the road respectively, so that a path point array is obtained. The sampling interval can be flexibly set based on factors such as the running speed of the unmanned vehicle, the size of road obstacles, the distribution situation and the like. For example, in a scene with a high travel speed, the sampling interval may be larger, and vice versa. The intervals in the width direction and the length direction may be uniform or non-uniform.
2. Determining a total cost for each path point on the path lattice column, wherein the total cost can be determined based on the following formula (1):
cost all =cost dynamic +cost static +cost bound +cost ref +cost smoot h formula
(1)
Wherein, cost all Representing the total cost corresponding to each path point;
cost dynamic representing the collision cost of the dynamic obstacle, and evaluating the risk of collision with the dynamic obstacle;
cost static Representing the collision cost of the static obstacle, and evaluating the risk of collision with the static obstacle;
cost bound representing the crossing cost, and evaluating the risk of the unmanned vehicle crossing the road boundary;
cost ref representing the cost of deviating from the reference line and evaluating the condition of the unmanned vehicle deviating from the reference line;
cost smoot h represents the steering cost and is used for evaluating the steering condition of the unmanned vehicle;
(1)cost dynamic can be determined based on the following formula (2):
wherein k is dynamic The value may be preset as a weight coefficient.
d dynamic Distance from dynamic obstacle when unmanned vehicle is located at the path point, speed of obstacle is higher than that of unmanned vehicleAt the speed of the vehicle, this term is infinite, i.e. cost dynamic Is 0.
(2)cost static Can be determined based on equation (3):
wherein k is static The value may be preset as a weight coefficient.
d static Is the distance from the dynamic obstacle when the unmanned vehicle is positioned at the path point. When d static When the threshold value is larger than a certain critical threshold value, the unmanned vehicle of the instruction book and the static obstacle cannot collide, and at the moment, the cost static Is 0.
(3)cost bound Can be determined based on equation (4):
k bound the value may be preset as a weight coefficient.
d bound Is the distance of the waypoint from the road boundary. When d bound When the threshold value is larger than a certain critical threshold value, the unmanned vehicle cannot exceed the road boundary, and at the moment, the cost bound Is 0.
(4)cost ref Can be determined based on equation (5):
cost ref =k ref ×d ref
k ref the value may be preset as a weight coefficient.
d ref Is the distance of the waypoint from the reference route.
(5)cost smoot h may be determined based on equation (6);
k smooth is a weight systemThe number may be preset.
dl represents the offset of the waypoint from the last selected target waypoint in the road width direction;
ds represents the offset of the waypoint from the last selected target waypoint in the road length direction.
(3) For each row in the path point array, the path point with the minimum total cost can be selected from the path points in the row to be used as the target path point. The steering cost is related to the position of the target path point determined in the previous line, so that when each line determines the target path point, the steering cost of each path point in the current line is determined by combining the position of the target path point determined in the previous line, and then the target path point is selected.
(4) And connecting the target path points selected by each row along the length direction of the road to obtain an initial path, and optimizing the initial path based on the dynamic characteristics of the vehicle to obtain a planned path of the unmanned vehicle.
It will be appreciated that the schemes described in the above embodiments may be freely combined to obtain new schemes without any conflict, and for reasons of brevity, will not be described in detail herein.
The following are device embodiments of the present disclosure that may be used to perform method embodiments of the present disclosure. For details not disclosed in the embodiments of the apparatus of the present disclosure, please refer to the embodiments of the method of the present disclosure.
Fig. 5 is a schematic structural diagram of a path planning apparatus of an unmanned vehicle according to an embodiment of the present disclosure. As shown in fig. 5, the path planning apparatus of the unmanned vehicle includes:
the sampling module 51 is configured to sample a road area in front of the unmanned aerial vehicle at intervals to obtain a path point array, where each row of path points in the path point array is distributed along a width direction of the road area, and each column of path points in the path point array is distributed along a length direction of the road area;
a cost determination module 52 for determining a cost corresponding to each waypoint in the waypoint array, the cost being determined based at least on a collision risk with a dynamic obstacle in the road area, a collision risk with a static obstacle in the road area, and a risk of crossing a road boundary when the drone is located at each waypoint;
the path generating module 53 is configured to, for each row in the path point array, select a target path point from a plurality of path points in the row based on the cost, and generate a planned path according to the selected target path point in each row.
The implementation process of the functions and roles of each module in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure. The electronic device 60 may be an in-vehicle device on an unmanned vehicle, for example, a controller on the unmanned vehicle, or a cloud server.
As shown in fig. 6, the electronic device 60 of this embodiment includes: a processor 601, a memory 602 and a computer program 603 stored in the memory 602 and executable on the processor 601. The steps of the various method embodiments described above are implemented by the processor 601 when executing the computer program 603. Alternatively, the processor 601, when executing the computer program 603, performs the functions of the modules/units of the apparatus embodiments described above.
Illustratively, the computer program 603 may be partitioned into one or more modules/units that are stored in the memory 602 and executed by the processor 601 to complete the present disclosure. One or more of the modules/units may be a series of computer program instruction segments capable of performing particular functions for describing the execution of the computer program 603 in the electronic device 60.
The electronic device 60 may include, but is not limited to, a processor 601 and a memory 602. It will be appreciated by those skilled in the art that fig. 6 is merely an example of an electronic device 60 and is not intended to limit the electronic device 60, and may include more or fewer components than shown, or may combine certain components, or different components, e.g., an electronic device may also include an input-output device, a network access device, a bus, etc.
The processor 601 may be a central processing unit (Central Processing Unit, CPU) or other general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory 602 may be an internal storage unit of the electronic device 60, for example, a hard disk or a memory of the electronic device 60. The memory 602 may also be an external storage device of the electronic device 60, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card) or the like, which are provided on the electronic device 60. Further, the memory 602 may also include both internal storage units and external storage devices of the electronic device 60. The memory 602 is used to store computer programs and other programs and data required by the electronic device. The memory 602 may also be used to temporarily store data that has been output or is to be output.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, specific names of the functional units and modules are also only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present disclosure. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and in part, not described or illustrated in any particular embodiment, reference is made to the related descriptions of other embodiments.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present disclosure.
In the embodiments provided in the present disclosure, it should be understood that the disclosed apparatus/electronic device and method may be implemented in other manners. For example, the apparatus/electronic device embodiments described above are merely illustrative, e.g., the division of modules or elements is merely a logical functional division, and there may be additional divisions of actual implementations, multiple elements or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection via interfaces, devices or units, which may be in electrical, mechanical or other forms.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated modules/units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the present disclosure may implement all or part of the flow of the method of the above-described embodiments, or may be implemented by a computer program to instruct related hardware, and the computer program may be stored in a computer readable storage medium, where the computer program, when executed by a processor, may implement the steps of the method embodiments described above. The computer program may comprise computer program code, which may be in source code form, object code form, executable file or in some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, a recording medium, a U disk, a removable hard disk, a magnetic disk, an optical disk, a computer Memory, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), an electrical carrier signal, a telecommunications signal, a software distribution medium, and so forth. It should be noted that the content of the computer readable medium can be appropriately increased or decreased according to the requirements of the jurisdiction's jurisdiction and the patent practice, for example, in some jurisdictions, the computer readable medium does not include electrical carrier signals and telecommunication signals according to the jurisdiction and the patent practice.
The above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included in the scope of the present disclosure.
The above embodiments are merely for illustrating the technical solution of the present disclosure, and are not limiting thereof; although the present disclosure has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the disclosure, and are intended to be included in the scope of the present disclosure.
Claims (10)
1. A method for path planning for an unmanned vehicle, the method comprising:
The method comprises the steps that a road area in front of an unmanned aerial vehicle is sampled at intervals to obtain a path point array, wherein each row of path points in the path point array are distributed along the width direction of the road area, and each column of path points in the path point array are distributed along the length direction of the road area;
determining a cost corresponding to each waypoint in the waypoint array, the cost determined based at least on a collision risk with a dynamic obstacle in a road area, a collision risk with a static obstacle in the road area, and a risk of crossing a road boundary when an unmanned vehicle is located at each waypoint;
and selecting a target path point from a plurality of path points in each row of the path point array based on the cost, and generating a planning path according to the selected target path point in each row.
2. The method according to claim 1, wherein the distance between two adjacent waypoints in each row and/or each column of the waypoint array is determined based on one or more of the following information: the current running speed of the unmanned vehicle, the distribution condition of the obstacles in the road area and the sizes of the obstacles in the road area.
3. The method according to claim 1 or 2, characterized in that the collision risk with a dynamic obstacle in a road area is characterized by a dynamic obstacle collision cost when the drone is located at each waypoint;
under the condition that the dynamic obstacle is positioned on an extension line of the speed direction of the unmanned vehicle and the speed of the dynamic obstacle is in the same direction as the speed of the unmanned vehicle:
if the movement speed of the unmanned vehicle is smaller than the movement speed of the dynamic obstacle, the collision cost of the dynamic obstacle is 0;
if the movement speed of the unmanned vehicle is not less than the movement speed of the dynamic obstacle, and the distance between the unmanned vehicle and the dynamic obstacle is less than a first distance threshold, the collision cost of the dynamic obstacle shows a trend of sharply increasing along with the decrease of the distance;
if the movement speed of the unmanned vehicle is not less than the movement speed of the dynamic obstacle, and the distance between the unmanned vehicle and the dynamic obstacle is greater than the first distance threshold, the collision cost of the dynamic obstacle is in a trend of slowly increasing along with the decrease of the distance;
in the case that the dynamic obstacle is located on an extension line of the speed direction of the unmanned vehicle and the speed of the dynamic obstacle is opposite to the speed of the unmanned vehicle:
If the distance between the unmanned vehicle and the dynamic obstacle is smaller than a first distance threshold, the collision cost of the dynamic obstacle shows a trend of sharply increasing along with the decrease of the distance;
if the distance between the unmanned vehicle and the dynamic obstacle is greater than the first distance threshold, the collision cost of the dynamic obstacle tends to increase slowly as the distance decreases;
and under the condition that the dynamic obstacle is positioned on the extension line of the speed direction of the unmanned vehicle and the included angle between the speed direction of the unmanned vehicle and the speed direction of the dynamic obstacle is positioned in a preset angle, the collision cost of the dynamic obstacle is 0.
4. The method according to claim 1 or 2, characterized in that the collision risk with a static obstacle in a road area is characterized by a static obstacle collision cost when the drone is located at each waypoint;
in the case that the distance between the unmanned vehicle and the static obstacle is smaller than a second distance threshold, the static obstacle cost is negatively related to the distance;
and in the case that the distance between the unmanned vehicle and the static obstacle is greater than a second distance threshold, the static obstacle cost is 0.
5. The method according to claim 1 or 2, wherein the risk of the drone crossing a road boundary is characterized by a crossing cost when the drone is at each waypoint,
under the condition that the distance between the path point and the road boundary is smaller than a third distance threshold value, the cross-boundary cost negatively correlates with the distance between the path point and the road boundary;
and in the case that the distance between the path point and the road boundary is greater than the third distance threshold, the cross-boundary cost is 0.
6. The method according to claim 1 or 2, wherein the cost is further determined based on a steering cost characterizing a steering situation of the unmanned vehicle, the steering cost being positively related to an offset in a road width direction of each of the waypoints from a target waypoint selected in a preceding row, and negatively related to an offset in a road length direction of each of the waypoints from a target waypoint selected in a preceding row; and/or
The cost is also determined based on a deviated reference path cost characterizing a deviated reference path condition of the drone, the deviated reference path cost being directly related to a distance of each path point from a reference path.
7. A method according to claim 1 or 2, wherein said determining a planned path from the target path points selected for each row comprises:
Connecting the selected target path points of each row along the length direction of the road area to obtain an initial path;
and optimizing the initial path based on the vehicle dynamics characteristics to obtain a planned path.
8. A path planning apparatus for an unmanned vehicle, the apparatus comprising:
the sampling module is used for performing interval sampling on a road area in front of the unmanned aerial vehicle to obtain a path point array, wherein each row of path points in the path point array are distributed along the width direction of the road area, and each column of path points in the path point array are distributed along the length direction of the road area;
a cost determination module configured to determine a cost corresponding to each waypoint in the waypoint array, the cost being determined based at least on a collision risk with a dynamic obstacle in a road area, a collision risk with a static obstacle in the road area, and a risk of crossing a road boundary when an unmanned vehicle is located at each waypoint;
and the path generation module is used for selecting a target path point from a plurality of path points in each row of the path point array based on the cost and generating a planning path according to the selected target path point in each row.
9. An electronic device comprising a processor, a memory, a computer program stored in the memory for execution by the processor, the processor implementing the method of any of claims 1-7 when executing the computer program.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program which, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211529575.3A CN116295473A (en) | 2022-11-30 | 2022-11-30 | Unmanned vehicle path planning method, unmanned vehicle path planning device, unmanned vehicle path planning equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211529575.3A CN116295473A (en) | 2022-11-30 | 2022-11-30 | Unmanned vehicle path planning method, unmanned vehicle path planning device, unmanned vehicle path planning equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116295473A true CN116295473A (en) | 2023-06-23 |
Family
ID=86817373
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211529575.3A Pending CN116295473A (en) | 2022-11-30 | 2022-11-30 | Unmanned vehicle path planning method, unmanned vehicle path planning device, unmanned vehicle path planning equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116295473A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116700315A (en) * | 2023-07-03 | 2023-09-05 | 苏州优世达智能科技有限公司 | Unmanned ship track tracking control method and system |
CN117091618A (en) * | 2023-10-18 | 2023-11-21 | 理工雷科智途(北京)科技有限公司 | Unmanned vehicle path planning method and device and electronic equipment |
-
2022
- 2022-11-30 CN CN202211529575.3A patent/CN116295473A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116700315A (en) * | 2023-07-03 | 2023-09-05 | 苏州优世达智能科技有限公司 | Unmanned ship track tracking control method and system |
CN116700315B (en) * | 2023-07-03 | 2024-02-06 | 苏州优世达智能科技有限公司 | Unmanned ship track tracking control method and system |
CN117091618A (en) * | 2023-10-18 | 2023-11-21 | 理工雷科智途(北京)科技有限公司 | Unmanned vehicle path planning method and device and electronic equipment |
CN117091618B (en) * | 2023-10-18 | 2024-01-26 | 理工雷科智途(北京)科技有限公司 | Unmanned vehicle path planning method and device and electronic equipment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109739219B (en) | Method, device and equipment for planning passing path and readable storage medium | |
US10642268B2 (en) | Method and apparatus for generating automatic driving strategy | |
US10296004B2 (en) | Autonomous operation for an autonomous vehicle objective in a multi-vehicle environment | |
CN113905940B (en) | Autonomous vehicle maneuvering based on risks associated with obscured areas | |
CN110843789B (en) | Vehicle lane change intention prediction method based on time sequence convolution network | |
US10235881B2 (en) | Autonomous operation capability configuration for a vehicle | |
CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
JP2020132151A (en) | Prediction method for travel locus of vehicle, device, terminal, storage medium and program | |
CN116295473A (en) | Unmanned vehicle path planning method, unmanned vehicle path planning device, unmanned vehicle path planning equipment and storage medium | |
CN113844451B (en) | Driving device control method and device, electronic device and storage medium | |
CN113353103A (en) | Method, device, equipment and medium for controlling speed of curve vehicle | |
CN114964284B (en) | Vehicle path planning method and device | |
CN112394725A (en) | Predictive and reactive view-based planning for autonomous driving | |
CN114604268A (en) | Vehicle driving intention prediction method and device, electronic equipment and vehicle | |
CN114715154A (en) | Lane-changing driving track planning method, device, equipment and medium | |
CN115123216A (en) | Vehicle obstacle avoidance method and device, vehicle, equipment and storage medium | |
Althoff et al. | Stochastic reachable sets of interacting traffic participants | |
CN115892076B (en) | Lane obstacle screening method and device and domain controller | |
CN114475656B (en) | Travel track prediction method, apparatus, electronic device and storage medium | |
US20230168368A1 (en) | Guardrail estimation method based on multi-sensor data fusion, and vehicle-mounted device | |
CN110614995B (en) | Lane selection method and system during automatic driving of vehicle and vehicle | |
CN115447607A (en) | Method and device for planning a vehicle driving trajectory | |
CN113734191A (en) | Artificially spoofing sensor data to initiate safety actions for autonomous vehicles | |
CN112462776A (en) | Unmanned driving decision-making method based on unstructured road | |
CN118034287A (en) | Control system of automatic driving motorcade |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |