CN110262508A - Applied to the automated induction systems and method on the closing unmanned goods stock in place - Google Patents
Applied to the automated induction systems and method on the closing unmanned goods stock in place Download PDFInfo
- Publication number
- CN110262508A CN110262508A CN201910607148.4A CN201910607148A CN110262508A CN 110262508 A CN110262508 A CN 110262508A CN 201910607148 A CN201910607148 A CN 201910607148A CN 110262508 A CN110262508 A CN 110262508A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- decision
- positioning system
- point
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000006698 induction Effects 0.000 title abstract description 4
- 230000009466 transformation Effects 0.000 claims abstract description 7
- 230000006870 function Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 10
- 238000011478 gradient descent method Methods 0.000 claims description 8
- 230000007246 mechanism Effects 0.000 claims description 8
- 238000012544 monitoring process Methods 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 5
- 206010048669 Terminal state Diseases 0.000 claims description 4
- 230000008859 change Effects 0.000 claims description 4
- 230000004927 fusion Effects 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000036314 physical performance Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000009795 derivation Methods 0.000 claims description 2
- 238000012804 iterative process Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 230000001131 transforming effect Effects 0.000 claims description 2
- 230000004888 barrier function Effects 0.000 abstract description 6
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000001953 sensory effect Effects 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
Classifications
-
- 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
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
Applied to the automated induction systems and method on the closing unmanned goods stock in place, belong to unmanned field.The existing transformation to the closing such as harbour place has that improvement cost is high, automatic Pilot navigation precision is low to carry out unmanned technology.The posture information for the vehicle center point that the present invention is obtained master positioning system and aided positioning system by positioning system in real time；Lane is monitored by sensory perceptual system, barrier is detected, identifies classification and the judgement of the speed of service；Decision is carried out to vehicle by the data information that decision system receives positioning system and sensory perceptual system upload, carries out local paths planning；The local path reference point information planned by control system according to decision system calculates control command, control command is handed down to executing agency, control command includes the target angle and target velocity of wheel.The present invention is suitable for closing the unmanned transformation guided automatically in place, and navigation accuracy is high.
Description
Technical Field
The invention relates to an automatic guiding system and method applied to an unmanned freight vehicle in a closed place.
Background
The automatic guiding system of the unmanned vehicle is mainly realized by a sensing system, a positioning system, a decision-making system and a control system. At present, an automatic guide system of an unmanned vehicle is mostly realized by various vehicle-mounted sensors, such as a GPS (global positioning system) positioning sensor, a laser radar, a millimeter wave radar and a camera. Because every kind of sensor all has respective use scene and function, GPS location is more accurate under the open and unshielded condition, and laser radar can realize the range finding to the barrier, also can realize assistance-localization real-time, and millimeter wave radar can realize range finding and speed measuring, and the vision camera can realize lane line discernment, lane keep, functions such as barrier discernment and classification. In order to improve the reliability of the automatic guiding system of the unmanned vehicle, the existing technology mostly adopts a scheme of multi-sensor fusion, namely, the functions of the sensors are fused together.
The automatic guidance system in the dock closed scene is different from the system composition in principle according to the selected sensor, and taking the current automatic dock as an example, the method mainly selects a magnetic nail positioning mode and a navigation system consisting of an inertial gyroscope, and the method has the remarkable defects that: (1) the laid magnetic nails and the induction antennas on the vehicle are expensive, and the quantity is large, and the cost is high; (2) the requirements on the field are strict, the pavement needs to be reformed and designed again, and no interfering substances such as metal and the like exist on the pavement and in a certain depth range, otherwise, the accuracy of the magnetic nail detection by the induction antenna is influenced; (3) for the traditional old wharf, the positioning method is not suitable, and the reconstruction or reconstruction cost is high; (4) although the magnetic nail is positioned accurately, the navigation path has limitation and limited flexibility, and vehicles cannot pass effectively in the area where the magnetic nail is not laid. In order to effectively solve the defects, the invention provides an automatic guiding system applied to an unmanned vehicle in a closed scene, wherein the application method is to select a GPS (global positioning system) as a main positioning method and use multi-sensor fusion as an automatic guiding system for auxiliary positioning, so that the investment of high cost and high consumption such as site reconstruction design, magnetic nail laying and the like is avoided.
Disclosure of Invention
The invention aims to solve the problems of high transformation cost and low automatic driving navigation accuracy of the existing unmanned technology for transforming closed places such as wharfs and the like, and provides an automatic guiding system and method applied to an unmanned freight vehicle in the closed places.
An automatic guiding system applied to an unmanned freight vehicle in a closed field comprises a positioning system, a sensing system, a decision-making system and a control system,
the positioning system adopts a GPS and inertial navigation as a main positioning system, adopts the combination of a vehicle-mounted sensor group and a roadside sensor group as an auxiliary positioning system, and is used for uploading accurate and stable pose information of a vehicle central point, which is obtained by the main positioning system and the auxiliary positioning system in real time, to the decision-making system;
the sensing system is used for monitoring a lane, detecting, identifying and classifying obstacles and judging the running speed by adopting a multi-sensor combination of a laser radar, a millimeter wave radar and a visual camera, and uploading the judged information to the decision-making system;
the decision system is used for making a decision on the vehicle by combining the data information uploaded by the positioning system and the sensing system and is used for locally making a decision
And planning a path, wherein an algorithm of local path planning is a method for generating a track by adopting a spiral curve.
An automated guidance method for use with an unmanned freight vehicle in an enclosed area, said method comprising the steps of:
firstly, accurately and stably obtaining pose information of a vehicle central point in real time by a main positioning system and an auxiliary positioning system through a positioning system, and uploading the pose information to a decision-making system; the positioning system comprises a main positioning system and auxiliary positioning systems, wherein the main positioning system is a GPS and inertial navigation system, and the auxiliary positioning system is a combination of a vehicle-mounted sensor group and a roadside sensor group;
monitoring the lane through a sensing system, detecting, identifying and classifying obstacles and judging the running speed, and uploading the judged information to a decision-making system; the sensing system adopts a combination form of a laser radar, a millimeter wave radar and a visual camera multi-sensor;
thirdly, the decision system receives the data information uploaded by the positioning system and the sensing system to make a decision on the vehicle, and local path planning is performed;
step four, calculating a control command through the control system according to the local path reference point information planned by the decision system, and calculating the control command according to the local path reference point information planned by the decision system
And a control command is issued to the executing mechanism, and the control command comprises a target angle and a target speed of the wheel.
The invention has the beneficial effects that:
the invention provides an automatic guiding system and method applied to an unmanned freight vehicle in a closed place. Has the following advantages:
(1) the positioning mode has more advantages, compared with the magnetic nail positioning, the GPS positioning range is wider, and the magnetic nails are not spaced;
(2) the path planning is a track generated on line in real time, the driving route can be changed at any time, and the control is more flexible;
(3) the anti-collision protection can be realized, the barrier-avoiding function of the barrier can be realized, and the barrier-avoiding strategy is complete;
(4) for the port environment, the automatic guide system can be suitable for the environment of a new wharf and can also be suitable for the environment of a traditional old wharf;
(5) compared with a combined navigation system of a magnetic nail positioning unit and an inertia measurement unit, the automatic guiding system has more advantages in the overall cost and the complexity of wharf reconstruction or reconstruction, and the reconstruction time period is shorter;
(6) the magnetic nail maintenance consumes time and labor, the maintenance period is long, the process is complicated, and the scheme is very convenient in later maintenance and saves time and labor.
Drawings
FIG. 1 is a block diagram of the overall system to which the present invention relates;
FIG. 2 is an unmanned cargo vehicle incorporating an automated guidance system in accordance with the present invention;
FIG. 3 is a schematic view of a specific installation configuration of an automated guidance system for an unmanned cargo vehicle according to the present invention;
FIG. 4 is a flow chart of an auto-boot method according to the present invention;
FIG. 5 is a schematic view of an unmanned vehicle according to the present invention operating at a dock site;
FIG. 6 is a flow chart of an algorithm of a decision making system according to the present invention;
fig. 7 is a schematic diagram of a coordinate system relationship between two coordinate systems of an XY ground coordinate system (cartesian coordinate system) and a road coordinate system (SL coordinate system) according to the present invention;
Detailed Description
The first embodiment is as follows:
the automatic guidance system of the present embodiment, which is applied to unmanned freight vehicles in closed fields, is shown in fig. 1, 2 and 3, wherein the automatic guidance system 2 comprises a positioning system 4, a sensing system 5, a decision-making system 6 and a control system 7,
the positioning system 4 adopts a GPS (reference number is 2d in the figure) and inertial navigation as a main positioning system 4, adopts the combination of a vehicle-mounted sensor group and a roadside sensor group as an auxiliary positioning system 4, and is used for uploading accurate and stable pose information of a vehicle central point, which is obtained by the main positioning system 4 and the auxiliary positioning system 4 in real time, to the decision-making system 6;
the perception system 5 is used for monitoring lanes, detecting, identifying and classifying obstacles and judging the running speed by adopting a multi-sensor combination of a laser radar 2b, a millimeter wave radar 2a and a visual camera 2c, and uploading the judged information to the decision-making system 6;
and the decision system 6 decides the vehicle by combining the data information uploaded by the positioning system 4 and the sensing system 5, and is used for planning a local path, wherein the algorithm of the local path planning is a method for generating a track by adopting a spiral curve.
The second embodiment is as follows:
as shown in fig. 1, 2 and 3, in the positioning system 4, the main positioning system 4 includes a GPS (reference numeral 2d in the figure) respectively arranged at the top of a box body 2e at the head and the tail of the freight vehicle, and an antenna of the GPS (reference numeral 2d in the figure) extends out of the surface of the box body 2e, and the main positioning system 4 is selected from a gyroscope inertial navigation system installed in the middle of the body 1; the vehicle body 1 carries goods 3;
and the on-vehicle sensor group of auxiliary positioning system 4 includes 6 laser radar 2b, 8 cameras 2c, 6 millimeter wave radar 2a, and concrete setting mode is: the combination of 3 laser radars 2b, 4 cameras 2c and 3 millimeter wave radars 2a arranged at the head and the tail of the vehicle respectively serves as an auxiliary positioning system 4, the head or the tail of the vehicle is provided with a box body 2e respectively, the top surface of the box body 2e is provided with 4 cameras 2c, the 4 cameras 2c are uniformly distributed into a straight line, the middle part of the outer side surface of the box body 2e is provided with 3 laser radars 2b, the 3 laser radars 2b are uniformly distributed into a horizontal straight line, the lower part of the outer side surface of the box body 2e is provided with 3 millimeter wave radars 2a, and the 3 millimeter wave radars 2a are uniformly distributed into a horizontal straight line; the drive test sensor group of the auxiliary positioning system 4 is a laser radar arranged in a field;
stable and accurate pose information and speed information are provided by the active positioning system 4 and the auxiliary positioning system 4 together; the actual sensor mounting arrangement is schematically shown in fig. 1, 2 and 3. The method can realize that under the condition of an open wharf environment, a relatively ideal positioning result is output by utilizing the positioning result of a GPS (the number is 2d in the figure) and combining the combined positioning result of the sensor group; when a GPS (marked with 2d in the figure) signal has a sheltered position, such as a special area below a shore bridge, a track crane, a storage yard and the like, the auxiliary positioning of the vehicle is carried out through a roadside sensor group, so that the unmanned vehicle can have stable and accurate pose information in the whole wharf scene, and the determined positioning information is uploaded to the decision-making system 6.
The third concrete implementation mode:
the automatic guidance system applied to the unmanned freight vehicle in the closed field of the embodiment is characterized in that the sensing system 5 measures the distance of the obstacle by using the laser radar 2b group at the head and the tail of the vehicle and estimates the running speed of the obstacle; the vehicle-mounted camera 2c is used for detecting, identifying and classifying the obstacles and detecting lanes, and the millimeter wave radar 2a is used for accurately measuring the running speed information of the obstacles; the detection and classification of the obstacles are completed through the multi-sensor fusion technology, then the detected obstacle distance, the speed information and the size information of the obstacles are output, and the obtained obstacle information is uploaded to the decision system 6.
The fourth concrete implementation mode:
the automatic guidance system applied to the unmanned freight vehicle in the closed field of the embodiment adopts the industrial controller with the GPU to make a decision by the decision making system 6, and the decision making system 6 makes a decision by combining the current pose information of the vehicle obtained by the positioning system 4, the obstacle information obtained by the sensing system 5 and the globally planned path information to complete local path planning.
The fifth concrete implementation mode:
the automatic guiding system applied to the unmanned freight vehicle in the closed field of the embodiment adopts the industrial controller with the GPU for control by the control system 7,
firstly, receiving path points issued by a decision system 6 as reference points, and converting the reference point information into actual control commands, namely the rotation angles and the speeds of wheels;
and then, a control command is issued to a controller of an actual execution mechanism 8, and in the process, the control system 7 continuously corrects the path deviation, the speed deviation and the turning angle of the vehicle, so that the control of the vehicle is completed, the tracking of the track is realized, and the vehicle can correctly run according to the target track given by the decision system 6 and normally reach the target point.
In summary, the automatic guidance system 2 of the unmanned vehicle proposed in the present invention can be fully applied to a closed dock environment, and as shown in fig. 5, a schematic diagram of the unmanned vehicle running on a dock site is shown.
The sixth specific implementation mode:
an automatic guiding method applied to an unmanned freight vehicle in a closed place in the embodiment is shown in fig. 4, and the method comprises the following steps:
firstly, accurate and stable pose information of a vehicle central point, which is obtained by a main positioning system 4 and an auxiliary positioning system 4 in real time, is uploaded to a decision-making system 6 through the positioning system 4; the positioning system 4 comprises a main positioning system 4 and auxiliary positioning systems 4, wherein a GPS (reference number is 2d in the figure) and inertial navigation are adopted as the main positioning system 4 of the positioning system 4, and the combination of a vehicle-mounted sensor group and a roadside sensor group is adopted as the auxiliary positioning system 4;
secondly, monitoring the lane through a sensing system 5, detecting, identifying and classifying obstacles and judging the running speed, and uploading the judged information to a decision-making system 6; the perception system 5 adopts a multi-sensor combination mode of a laser radar 2b, a millimeter wave radar 2a and a vision camera 2 c;
thirdly, the decision system 6 receives the data information uploaded by the positioning system 4 and the sensing system 5 to make a decision on the vehicle, and local path planning is performed;
and step four, calculating a control command through the control system 7 according to the local path reference point information planned by the decision system 6, and issuing the control command to an execution mechanism, wherein the control command comprises a target angle and a target speed of the wheel.
The seventh embodiment:
in the third step, the decision system 6 receives the data information uploaded by the positioning system 4 and the sensing system 5 to make a decision on the vehicle, and the process of performing local path planning is that the decision system 6 makes a decision by using an industrial controller with a GPU, and the decision system 6 makes a decision by combining the current pose information of the vehicle obtained by the positioning system 4, the obstacle information obtained by the sensing system 5 and the path information of global planning, so as to complete local path planning.
The specific implementation mode is eight:
in the automatic guidance method applied to the unmanned freight vehicle in the closed field, the algorithm for local path planning adopts a method of generating a track by a spiral curve, that is, the method comprises the following steps:
step 1, defining two coordinate systems of an XY ground coordinate system (a Cartesian coordinate system) and a road coordinate system (an SL coordinate system), determining an initial state value (the current XY coordinate, the course angle and the curvature of the vehicle) from an initial value obtained by a positioning system 4 through the transformation from the XY ground coordinate system to the road coordinate system, and determining a termination state value (the XY coordinate, the course angle and the curvature of a target point) from a termination value obtained by a dispatching system through the transformation from the XY ground coordinate system to the road coordinate system; the dispatching system is a remote fleet management system and is used for automatically driving the upstream;
step 2, solving coefficients of the spiral curve according to the initial state value and the termination state value, and determining unknown parameters in the coefficients of the spiral curve; estimating and calculating unknown parameters in coefficients of the spiral curve by using a gradient descent method to obtain a plurality of groups of estimated values;
step 3, obtaining an expression of a curve according to the estimation value of the unknown parameter, and generating all tracks;
step 4, evaluating each track by utilizing an evaluation function to meet the evaluation requirement of the physical performance of the vehicle to obtain an optimal track; then a series of track point information under the XY coordinate system is obtained through the transformation from the road coordinate system to the XY ground coordinate system, and the points are sent to the control system 7;
wherein,
the single track point information comprises the coordinate position, the course angle and the speed information of the track point;
the evaluation requirements of the vehicle physical performance refer to speed information and position information of the obstacle, the selection of the track is completed, and the function of bypassing the obstacle is realized;
the specific implementation method nine:
the algorithm of the local path planning adopts the following algorithm flows of the decision making system 6 from the step 1 to the step 4 of the method for generating the track by the spiral curve, the algorithm flow chart is shown in figure 6,
first, according to the kinematic model of the vehicle center point: the position is expressed as (x, y), the angular velocity Heading is expressed as θ, the longitudinal velocity of the vehicle is expressed as v, and the curvature is expressed as k, so that the kinematic equation of velocity, angular velocity, and curvature change rate with respect to time is expressed as:
starting from the planned path, the motion of the vehicle is represented as a function of the curvature with respect to the travel distance S, so that the kinematic equation described above is transformed into the following form:
dx/ds＝cos[θ(s)]
dy/ds＝sin[θ(s)]
dθ/ds＝k(s)
then, designing a specific algorithm flow:
acquiring information uploaded by a positioning system 4 and a sensing system 5, namely the current pose of a vehicle and surrounding obstacle information; then, describing a lane coordinate system by S and L, and representing the coordinates of the defined point in the SL coordinate system as p (S, L), where S represents an arc length and L represents a lateral deviation from the center line of the lane, which is substantially the relationship between the two coordinate systems, and the schematic diagrams of the two coordinate systems are shown in fig. 7;
then, a path which enables the vehicle to run stably and meets the constraint is searched between the starting point and the end point to realize path planning;
then, expressing the path by a polynomial spiral curve, and generating a track by the spiral curve; the polynomial spiral line is a plane curve, the curvature of the polynomial spiral line is a polynomial function k(s) related to the arc length, a cubic polynomial is used at low speed, and a quintic polynomial is used at high speed to ensure the continuity of the curvature change rate and the derivative thereof;
the cubic polynomial spiral is represented as:
k(s)＝k0+k1s+k2s2+k3s3
starting the configuration from the vehicle: q. q.sinit＝[xIyIθIkI]To the end point configuration qgoal＝[xGyGθGkG]When the starting position s is 0, k0＝kIThen there are four unknowns k2,k3,k4,sGAt high speed, the high-order derivative of k can be ensured to be continuous, the initial state of the vehicle is expanded, and when s is equal to 0, the first derivative and the second derivative of k to s are obtained, namely(simplification to) Can obtainSo the initial values are defined as:it is possible to obtain:
k0＝kI
so far, only k remains3,sGTwo parameters are unknown; by adding two inputs, the cubic polynomial can be expanded to a quintic polynomial;
to improve numerical accuracy, a new parameter definition p ═ p is used0...3,sG]The coefficients are solved directly using the following polynomial: k(s) ═ a (p) + b (p) s + c (p) s2+d(p)s3These parameters are constrained to be equal to the curvature of the path at equidistant points on the path:
k(0)＝p0
k(sG)＝p3
the expression for the polynomial coefficients can be found:
a(p)＝p0
known as p0＝kI，p3＝kGSo that only three unknowns remain, i.e.
Three unknowns:
the state is given as follows: starting position qinit＝[xI,yI,θI,kI]Desired end point qgoal＝[xG,yG,θG,kG]. Taking the starting point position as the origin, a new starting point q can be obtainedinit＝[0,0,0,kI]And end point qgoal. Given a candidate point P, the position state of the end point is calculated according to the point P, and the calculation is carried out by using a gradient descent method:
θp(s)＝a(p)s+b(p)s2/2+c(p)s3/3+d(p)s4/4
kp(s)＝a(p)+b(p)s+c(p)s2+d(p)s3
gradient descent method using xp(sG) As a reference path end point, s is impliedG＝sG(p), then the state of the path end point is configured to:
the terminal state vector can be used as a function of the parameter P to calculate a Jacobian matrix of the terminal state vector about unknown parameters, wherein the unknown parameters are
Due to kp(sG)＝p3Is not a function of unknown variables, so there is no need for kpDerivation is carried out; the goal is to find P such that
First, toAssuming a reasonable initial value, using a Jacobian matrix to passIterative optimization of gradient descent methodTo obtain a better estimate
Then, the iterative process is repeated to letInstead of the formerUntil Δ q is small enough to meet the expected value; in the formula, ← represents the replacement of a latter term by a former term of the symbol;
one of the very critical problems is thatBased on the above calculation process, a set of initial guessesThe values, ultimately correspond to a set of target point coordinates. This translates the problem of generating multiple paths into an estimation problem of the initial values of the parameters.
In the process of initial value estimation, the problem of solving the equation set is equivalent to knowing the state values of the initial point and the target point and aiming at unknown polynomial coefficientsCarrying out inverse solution; in the actual process, the current point and the target point are known, the information of the current point is obtained by the positioning system 4, and the information of the target point is from a command issued by the dispatching system; therefore, the left side of the equation set is actually a known value, and the right side is an expression containing unknown parameters, i.e. the unknown parameters are calculated by these equationsFor sGThe value of (b) is, in the case of the target point determination, ascertainable by a certain conversion, which represents the curve length, i.e. the projected point coordinates of the target point on the center line of the lane line in the SL coordinate system, so that sGEquivalent to a known value; now is leftIs unknown;
θp(s)＝a(p)s+b(p)s2/2+c(p)s3/3+d(p)s4/4
kp(s)＝a(p)+b(p)s+c(p)s2+d(p)s3
then, given the knowledge of the target point, the unknown parameters can be calculated, i.e. the target point information is knownAn initial estimation value; then, one track can be obtained according to each group of estimation values, and finally, the generation of all tracks is completed;
then, evaluating all tracks through an evaluation function, wherein the evaluation function can evaluate the tracks by combining obstacle information, lane restriction information, vehicle body mechanical performance, comfort level and the like, and selecting the track with the highest evaluation as the most optimal track;
and then, the optimal track point information is sent to the control system 7.
The detailed implementation mode is ten:
in the automatic guidance method applied to the unmanned freight vehicle in the closed place, the control system 7 receives the path points issued by the decision system 6 as reference points, and converts the reference point information into actual control commands, namely, the turning angles and the speeds of the wheels. And issuing the control command to a controller of an actual execution mechanism, wherein the control system 7 can continuously correct the path deviation, the speed deviation and the turning angle of the vehicle in the process, and finally the control of the vehicle is completed to realize the track tracking, so that the vehicle can correctly run according to the target track given by the decision system 6 and normally reach a target point.
In summary, the automatic guidance system 2 of the unmanned vehicle proposed in the present invention can be fully applied to a closed dock environment, and as shown in fig. 5, a schematic diagram of the unmanned vehicle running on a dock site is shown.
Example (b):
the automatic guiding system 2 of the unmanned vehicle provided by the invention can be applied to the unmanned vehicle in a dock closed scene. The structural block diagram of the whole system is shown in the following fig. 1, which gives a specific composition structure, including a positioning system 4, a sensing system 5, a decision system 6 and a control system 7.
Each subsystem is an indispensable part, the positioning system 4 provides the current stable and accurate pose of the vehicle in real time, the sensing system 5 provides barrier information in real time, and the decision-making system 6 decides the next action of the vehicle in real time according to the current pose of the vehicle and the information of the barrier, and plans a local path in real time. The decision system 6 issues the planned optimal path to the control system 7 in the form of a series of points, and the path points are used as reference points of the control system 7. After receiving the command issued by the decision, the control system 7 calculates a control command, namely a target angle and a target speed of the front wheel and the rear wheel according to the coordinate position and the speed of the current point and the reference point, and then issues the control command to the executing mechanism to complete the tracking of the track, and finally normally reaches the target point.
Claims (10)
1. The utility model provides an automatic bootstrap system for on closed place unmanned freight vehicles which characterized in that: the automatic guiding system comprises a positioning system, a sensing system, a decision-making system and a control system,
the positioning system adopts a GPS and inertial navigation as a main positioning system, adopts the combination of a vehicle-mounted sensor group and a roadside sensor group as an auxiliary positioning system, and is used for uploading pose information of a vehicle center point obtained by the main positioning system and the auxiliary positioning system in real time to the decision-making system;
the sensing system is used for monitoring the lane, detecting, identifying and classifying obstacles and judging the running speed by combining a laser radar, a millimeter wave radar and a visual camera, and uploading the judged information to the decision-making system;
and the decision system is used for deciding the vehicle by combining the data information uploaded by the positioning system and the sensing system and planning a local path, wherein the local path planning is a method for generating a track by adopting a spiral curve.
2. The automated guidance system for use with an enclosed area unmanned cargo vehicle of claim 1, wherein: in the positioning system, a main positioning system comprises a GPS antenna respectively arranged at the tops of box bodies of a head and a tail of a freight vehicle, and a gyroscope inertial navigation device is selected and mounted in the middle of a vehicle body to serve as the main positioning system; the vehicle-mounted sensor group of the auxiliary positioning system comprises 3 laser radars, 4 cameras and a combination of 3 millimeter wave radars which are respectively arranged at the head and the tail of the vehicle as the auxiliary positioning system, the head or the tail of the vehicle is respectively provided with a box body, the top surface of the box body is provided with 4 cameras, the 4 cameras are uniformly distributed into a straight line, the middle part of the outer side surface of the box body is provided with 3 laser radars, the 3 laser radars are uniformly distributed into a horizontal straight line, the lower part of the outer side surface of the box body is provided with 3 millimeter wave radars, and the 3 millimeter wave radars are uniformly distributed into a horizontal straight line; the drive test sensor group of the auxiliary positioning system is a laser radar arranged in a field;
stable and accurate pose information and speed information are provided by the active positioning system and the auxiliary positioning system together; under the condition of an open wharf environment, outputting a positioning result by utilizing a positioning result of a GPS and combining a combined positioning result of the sensor group; when the GPS signal has a sheltered position, such as a special area below a shore bridge, a track crane, a storage yard and the like, the auxiliary positioning of the vehicle is carried out through the roadside sensor group, so that the unmanned vehicle can have stable and accurate pose information in the whole wharf scene, and the determined positioning information is uploaded to a decision-making system.
3. The automated guidance system for use with an enclosed area unmanned cargo vehicle of claim 2, wherein: the sensing system measures the distance of the obstacle by using the laser radar group at the head and the tail of the vehicle and estimates the running speed of the obstacle; the vehicle-mounted camera group is used for detecting, identifying and classifying the obstacles and detecting lanes, and the millimeter wave radar group is used for accurately measuring the running speed information of the obstacles; the method comprises the steps of detecting and classifying obstacles through fusion of multiple sensors, outputting the detected distance of the obstacles, speed information and size information of the obstacles, and uploading the obtained information of the obstacles to a decision-making system.
4. The automated guidance system for use with an enclosed area unmanned cargo vehicle of claim 3, wherein: the decision system adopts an industrial controller with a GPU to make decisions.
5. The automated guidance system for use with an enclosed area unmanned cargo vehicle of claim 4, wherein: the control system adopts an industrial controller with a GPU to make decisions,
firstly, receiving path points issued by a decision system as reference points, and converting the reference point information into actual control commands, namely the rotation angles and the speeds of wheels;
and then, a control command is issued to a controller of an actual execution mechanism, and a control system continuously corrects the path deviation, the speed deviation and the turning angle of the vehicle, so that the control of the vehicle is completed, the tracking of the track is realized, and the vehicle can correctly run according to the target track given by the decision system and normally reach a target point.
6. A method for automated guidance for use with an unmanned freight vehicle in an enclosed area using the system of the preceding claims, characterized by: the method comprises the following steps:
firstly, acquiring pose information of a vehicle center point in real time by a main positioning system and an auxiliary positioning system through a positioning system, and uploading the pose information to a decision-making system; the positioning system comprises a main positioning system and auxiliary positioning systems, wherein the main positioning system is a GPS and inertial navigation system, and the auxiliary positioning system is a combination of a vehicle-mounted sensor group and a roadside sensor group;
monitoring the lane through a sensing system, detecting, identifying and classifying obstacles and judging the running speed, and uploading the judged information to a decision-making system; the sensing system adopts a combination form of a laser radar, a millimeter wave radar and a visual camera;
thirdly, the decision system receives the data information uploaded by the positioning system and the sensing system to make a decision on the vehicle, and local path planning is performed;
and step four, calculating a control command through the control system according to the local path reference point information planned by the decision system, and issuing the control command to the executing mechanism, wherein the control command comprises a target angle and a target speed of the wheel.
7. The automated guided vehicle system of claim 6, further comprising: and in the third step, the decision system receives the data information uploaded by the positioning system and the sensing system to make a decision on the vehicle, and the process of local path planning is that the decision system makes a decision by adopting an industrial controller with a GPU, and the decision system makes a decision by combining the current pose information of the vehicle obtained by the positioning system, the obstacle information obtained by the sensing system and the path information of global planning, so that local path planning is completed.
8. The automated guided method of claim 7, applied to an unmanned freight vehicle for closed space, wherein: the algorithm for planning the local path adopts a method for generating a track by a spiral curve, namely:
step 1, defining two coordinate systems of an XY ground coordinate system and a road coordinate system, determining an initial state value by converting an initial value obtained by a positioning system from the XY ground coordinate system to the road coordinate system, and determining a termination state value (a target point XY coordinate, a course angle and a curvature) by converting a termination value obtained by a dispatching system from the XY ground coordinate system to the road coordinate system;
step 2, solving coefficients of the spiral curve according to the initial state value and the termination state value, and determining unknown parameters in the coefficients of the spiral curve; estimating and calculating unknown parameters in coefficients of the spiral curve by using a gradient descent method to obtain a plurality of groups of estimated values;
step 3, obtaining an expression of a curve according to the estimation value of the unknown parameter, and generating all tracks;
step 4, evaluating each track by utilizing an evaluation function to meet the evaluation requirement of the physical performance of the vehicle to obtain an optimal track; then a series of track point information under the XY coordinate system is obtained through the transformation from the road coordinate system to the XY ground coordinate system, and the points are sent to a control system;
wherein,
the single track point information comprises the coordinate position, the course angle and the speed information of the track point;
the evaluation requirements of the vehicle physical performance refer to speed information and position information of the obstacle, the selection of the track is completed, and the function of bypassing the obstacle is realized.
9. The automated guided method of claim 8, applied to an unmanned freight vehicle for closed space, wherein: the algorithm for the local path planning adopts the following algorithm flow of the decision system from step 1 to step 4 of the method for generating the track by the spiral curve,
first, according to the kinematic model of the vehicle center point: the position is expressed as (x, y), the angular velocity Heading is expressed as θ, the longitudinal velocity of the vehicle is expressed as v, and the curvature is expressed as k, so that the kinematic equation of velocity, angular velocity, and curvature change rate with respect to time is expressed as:
starting from the planned path, the motion of the vehicle is represented as a function of the curvature with respect to the travel distance S, transforming the kinematic equation into the form:
dx/ds＝cos[θ(s)]
dy/ds＝sin[θ(s)]
dθ/ds＝k(s)
then, designing a specific algorithm flow:
acquiring information uploaded by a positioning system and a sensing system, namely the current pose of a vehicle and the information of surrounding obstacles; then, describing a lane coordinate system by S and L, and expressing the coordinate of a defined point in the SL coordinate system as p (S, L), wherein S represents an arc length and L represents a transverse deviation from the center line of the lane;
then, a path which enables the vehicle to run stably and meets the constraint is searched between the starting point and the end point to realize path planning;
then, expressing the path by a polynomial spiral curve, and generating a track by the spiral curve; the polynomial spiral line is a plane curve, the curvature of the polynomial spiral line is a polynomial function k(s) related to the arc length, a cubic polynomial is used at low speed, and a quintic polynomial is used at high speed to ensure the continuity of the curvature change rate and the derivative thereof;
the cubic polynomial spiral is represented as:
k(s)＝k0+k1s+k2s2+k3s3
starting the configuration from the vehicle: q. q.sinit＝[xIyIθIkI]To the end point configuration qgoal＝[xGyGθGkG]When the starting position s is 0, k0＝kIThen there are four unknowns k2,k3,k4,sGAt high speed, the high-order derivative of k is ensured to be continuous, the initial state of the vehicle is expanded, and when s is equal to 0, the first derivative and the second derivative of k to s are obtained, namelyReduced to dsk(s),To obtain dskI＝dsk(0),Defining an initial value as:obtaining:
k0＝kI
calculate so far, k3,sGTwo parameters are unknown; expanding the cubic polynomial into a quintic polynomial by adding two inputs;
using a new parameter definition p ═ p0...3,sG]The coefficients are solved using the following polynomial: k(s) ═ a (p) + b (p) s + c (p) s2+d(p)s3These parameters are constrained to be equal to the curvature of the path at equidistant points on the path:
k(0)＝p0
k(sG)＝p3
solving an expression of polynomial coefficients:
a(p)＝p0
known as p0＝kI，p3＝kGSo that only three unknowns remain, i.e.
Three unknowns:
the state is given as follows: starting position qinit＝[xI,yI,θI,kI]Desired end point qgoal＝[xG,yG,θG,kG](ii) a Taking the starting point position as the origin, a new starting point q can be obtainedinit＝[0,0,0,kI]And end point qgoal(ii) a Given a candidate point P, the position state of the end point is calculated according to the point P, and the calculation is carried out by using a gradient descent method:
θp(s)＝a(p)s+b(p)s2/2+c(p)s3/3+d(p)s4/4
kp(s)＝a(p)+b(p)s+c(p)s2+d(p)s3
gradient descent method using xp(sG) As a reference path end point, s is impliedG＝sG(p), then the state of the path end point is configured to:
using the terminal state vector as a function of the parameter P to calculate a Jacobian matrix of the terminal state vector about unknown parameters, wherein the unknown parameters are
Due to kp(sG)＝p3Not a function of unknown variables, not necessarily for kpDerivation is carried out; the goal is to find P such that
First, toAssuming a reasonable initial value, using a Jacobian matrix to passIterative optimization of gradient descent methodObtaining an estimated value
Then, the iterative process is repeated to letInstead of the formerUntil Δ q satisfies the expected value; in the formula, ← represents the replacement of a latter term by a former term of the symbol;
in the process of initial value estimation, the state values of an initial point and a target point are known, and unknown polynomial coefficients are subjected toCarrying out inverse solution; the current point and the target point are known, the information of the current point is obtained by a positioning system, and the information of the target point is from a command issued by a dispatching system; therefore, the left side of the equation set of the following formula is a known value, and the right side is an expression including an unknown parameter, and the unknown parameter is calculated by these equationssGRepresenting the curve length, i.e. the coordinates of the projected point of the target point on the centre line of the lane line, so sGIn the known manner, it is known that,is unknown;
θp(s)＝a(p)s+b(p)s2/2+c(p)s3/3+d(p)s4/4
kp(s)＝a(p)+b(p)s+c(p)s2+d(p)s3
then, with the knowledge of the target point, the unknown parameters are calculated, i.e. the target point information is knownAn initial estimation value; then, one track can be obtained according to each group of estimation values, and finally, the generation of all tracks is completed;
then, evaluating all tracks through an evaluation function, wherein the evaluation function can evaluate the tracks by combining obstacle information, lane restriction information, vehicle body mechanical performance, comfort level and the like, and selecting the track with the highest evaluation as the most optimal track;
and then, transmitting the optimal track point information to a control system.
10. The automated guided method of claim 9, applied to an unmanned freight vehicle for closed space, wherein: the control system receives the path points issued by the decision system as reference points, and converts the reference point information into actual control commands, namely the rotation angles and the speeds of the wheels; and the control command is issued to a controller of an actual execution mechanism, the control system can continuously correct the path deviation, the speed deviation and the turning angle of the vehicle in the process, and finally the control of the vehicle is completed to realize the track tracking, so that the vehicle can correctly run according to the target track given by the decision-making system and normally reach a target point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910607148.4A CN110262508B (en) | 2019-07-06 | 2019-07-06 | Automatic guiding system and method applied to unmanned freight vehicle in closed field |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910607148.4A CN110262508B (en) | 2019-07-06 | 2019-07-06 | Automatic guiding system and method applied to unmanned freight vehicle in closed field |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110262508A true CN110262508A (en) | 2019-09-20 |
| CN110262508B CN110262508B (en) | 2024-05-31 |
Family
ID=67924790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910607148.4A Active CN110262508B (en) | 2019-07-06 | 2019-07-06 | Automatic guiding system and method applied to unmanned freight vehicle in closed field |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110262508B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989618A (en) * | 2019-12-23 | 2020-04-10 | 福建工程学院 | Cooperative carrying control system and method for swarm type carrying vehicle |
| CN111026122A (en) * | 2019-12-24 | 2020-04-17 | 江苏徐工工程机械研究院有限公司 | Speed planning method, device and system for unmanned vehicle |
| CN111338342A (en) * | 2020-02-28 | 2020-06-26 | 江苏徐工工程机械研究院有限公司 | Automatic tracking driving control system and method for wheel type engineering machinery |
| CN111427331A (en) * | 2020-03-24 | 2020-07-17 | 新石器慧通（北京）科技有限公司 | Perception information display method and device of unmanned vehicle and electronic equipment |
| CN111561944A (en) * | 2020-04-07 | 2020-08-21 | 中铁工程机械研究设计院有限公司 | Beam transporting vehicle operation path planning method and automatic driving operation control method |
| CN112068548A (en) * | 2020-08-07 | 2020-12-11 | 北京航空航天大学 | Special scene-oriented unmanned vehicle path planning method in 5G environment |
| CN112099025A (en) * | 2020-08-20 | 2020-12-18 | 杭州飞步科技有限公司 | Method, device and equipment for positioning vehicle under bridge crane and storage medium |
| CN112415548A (en) * | 2020-11-09 | 2021-02-26 | 北京斯年智驾科技有限公司 | Unmanned card-collecting positioning method, device and system, electronic device and storage medium |
| CN112683291A (en) * | 2020-12-30 | 2021-04-20 | 广州小鹏自动驾驶科技有限公司 | Vehicle turning path planning method and device, vehicle and storage medium |
| CN112700668A (en) * | 2020-12-22 | 2021-04-23 | 北京百度网讯科技有限公司 | Remote control method for automatic driving, automatic driving vehicle and cloud equipment |
| CN113022408A (en) * | 2021-04-15 | 2021-06-25 | 中国矿业大学 | 360-degree self-adaptive loading and unloading unmanned mining dump truck and control method thereof |
| CN113064415A (en) * | 2019-12-31 | 2021-07-02 | 华为技术有限公司 | Method and device for planning track, controller and intelligent vehicle |
| CN113183943A (en) * | 2021-06-03 | 2021-07-30 | 南昌智能新能源汽车研究院 | Intelligent driving system of agricultural equipment and operation method thereof |
| CN113204236A (en) * | 2021-04-14 | 2021-08-03 | 华中科技大学 | Intelligent agent path tracking control method |
| CN113257026A (en) * | 2021-06-24 | 2021-08-13 | 浙江海康智联科技有限公司 | Seaport cargo vehicle guiding method based on vehicle-road cooperative environment |
| CN113268055A (en) * | 2021-04-07 | 2021-08-17 | 北京拓疆者智能科技有限公司 | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment |
| CN113467474A (en) * | 2021-07-29 | 2021-10-01 | 安徽江淮汽车集团股份有限公司 | Automatic driving hierarchical control system |
| CN113483770A (en) * | 2021-06-30 | 2021-10-08 | 上海西井信息科技有限公司 | Path planning method and device in closed scene, electronic equipment and storage medium |
| WO2021238723A1 (en) * | 2020-05-29 | 2021-12-02 | 杭州海康威视数字技术股份有限公司 | Method, apparatus and system for controlling automatic driving device, and storage medium |
| CN113791619A (en) * | 2021-09-14 | 2021-12-14 | 北京航空航天大学 | Dispatching navigation system and method for airport automatic driving tractor |
| CN115123217A (en) * | 2022-09-02 | 2022-09-30 | 青岛慧拓智能机器有限公司 | Mining area obstacle vehicle driving track generation method and device and computer equipment |
| LU500260B1 (en) * | 2021-06-09 | 2022-12-13 | Phoenix Contact Gmbh & Co | Self-propelled device for use in an industrial environment |
| CN116412818A (en) * | 2022-01-05 | 2023-07-11 | 腾讯科技（深圳）有限公司 | Positioning method, positioning device, positioning apparatus, positioning device, computer-readable storage medium, and computer program product |
| CN117953065A (en) * | 2024-03-26 | 2024-04-30 | 新乡职业技术学院 | Site vehicle control system based on image processing |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07129243A (en) * | 1993-11-08 | 1995-05-19 | Shinko Electric Co Ltd | Controller for steering unmanned vehicle |
| DE102009039111A1 (en) * | 2009-08-27 | 2011-03-03 | Spiegelmacher, Kurt, Prof. Dr. Ing. | Method for automatic or driver supported reversing method of vehicle units, involves providing global positioning system based navigation system |
| CN107671853A (en) * | 2017-07-31 | 2018-02-09 | 深圳市海思科自动化技术有限公司 | Open robot's trajectory planning control method and system |
| CN107702716A (en) * | 2017-08-31 | 2018-02-16 | 广州小鹏汽车科技有限公司 | A kind of unmanned paths planning method, system and device |
| CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
| CN108845579A (en) * | 2018-08-14 | 2018-11-20 | 苏州畅风加行智能科技有限公司 | A kind of automated driving system and its method of port vehicle |
| CN109866762A (en) * | 2019-03-11 | 2019-06-11 | 武汉环宇智行科技有限公司 | Autonomous Parallel parking method based on high-precision map |
| CN109885891A (en) * | 2019-01-24 | 2019-06-14 | 中国科学院合肥物质科学研究院 | A kind of intelligent vehicle GPU accelerates method for planning track parallel |
| CN109901574A (en) * | 2019-01-28 | 2019-06-18 | 华为技术有限公司 | Automatic Pilot method and device |
-
2019
- 2019-07-06 CN CN201910607148.4A patent/CN110262508B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07129243A (en) * | 1993-11-08 | 1995-05-19 | Shinko Electric Co Ltd | Controller for steering unmanned vehicle |
| DE102009039111A1 (en) * | 2009-08-27 | 2011-03-03 | Spiegelmacher, Kurt, Prof. Dr. Ing. | Method for automatic or driver supported reversing method of vehicle units, involves providing global positioning system based navigation system |
| CN107671853A (en) * | 2017-07-31 | 2018-02-09 | 深圳市海思科自动化技术有限公司 | Open robot's trajectory planning control method and system |
| CN107702716A (en) * | 2017-08-31 | 2018-02-16 | 广州小鹏汽车科技有限公司 | A kind of unmanned paths planning method, system and device |
| CN108387242A (en) * | 2018-02-07 | 2018-08-10 | 西南交通大学 | Automatic Pilot lane-change prepares and executes integrated method for planning track |
| CN108845579A (en) * | 2018-08-14 | 2018-11-20 | 苏州畅风加行智能科技有限公司 | A kind of automated driving system and its method of port vehicle |
| CN109885891A (en) * | 2019-01-24 | 2019-06-14 | 中国科学院合肥物质科学研究院 | A kind of intelligent vehicle GPU accelerates method for planning track parallel |
| CN109901574A (en) * | 2019-01-28 | 2019-06-18 | 华为技术有限公司 | Automatic Pilot method and device |
| CN109866762A (en) * | 2019-03-11 | 2019-06-11 | 武汉环宇智行科技有限公司 | Autonomous Parallel parking method based on high-precision map |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110989618A (en) * | 2019-12-23 | 2020-04-10 | 福建工程学院 | Cooperative carrying control system and method for swarm type carrying vehicle |
| CN111026122A (en) * | 2019-12-24 | 2020-04-17 | 江苏徐工工程机械研究院有限公司 | Speed planning method, device and system for unmanned vehicle |
| CN113064415A (en) * | 2019-12-31 | 2021-07-02 | 华为技术有限公司 | Method and device for planning track, controller and intelligent vehicle |
| CN111338342A (en) * | 2020-02-28 | 2020-06-26 | 江苏徐工工程机械研究院有限公司 | Automatic tracking driving control system and method for wheel type engineering machinery |
| CN111427331A (en) * | 2020-03-24 | 2020-07-17 | 新石器慧通（北京）科技有限公司 | Perception information display method and device of unmanned vehicle and electronic equipment |
| CN111561944A (en) * | 2020-04-07 | 2020-08-21 | 中铁工程机械研究设计院有限公司 | Beam transporting vehicle operation path planning method and automatic driving operation control method |
| WO2021238723A1 (en) * | 2020-05-29 | 2021-12-02 | 杭州海康威视数字技术股份有限公司 | Method, apparatus and system for controlling automatic driving device, and storage medium |
| CN112068548A (en) * | 2020-08-07 | 2020-12-11 | 北京航空航天大学 | Special scene-oriented unmanned vehicle path planning method in 5G environment |
| CN112068548B (en) * | 2020-08-07 | 2022-06-07 | 北京航空航天大学 | Special scene-oriented unmanned vehicle path planning method in 5G environment |
| CN112099025A (en) * | 2020-08-20 | 2020-12-18 | 杭州飞步科技有限公司 | Method, device and equipment for positioning vehicle under bridge crane and storage medium |
| CN112099025B (en) * | 2020-08-20 | 2024-04-02 | 杭州飞步科技有限公司 | Method, device, equipment and storage medium for positioning vehicle under bridge crane |
| CN112415548A (en) * | 2020-11-09 | 2021-02-26 | 北京斯年智驾科技有限公司 | Unmanned card-collecting positioning method, device and system, electronic device and storage medium |
| CN112415548B (en) * | 2020-11-09 | 2023-09-29 | 北京斯年智驾科技有限公司 | Positioning method, device and system of unmanned integrated card, electronic device and storage medium |
| CN112700668A (en) * | 2020-12-22 | 2021-04-23 | 北京百度网讯科技有限公司 | Remote control method for automatic driving, automatic driving vehicle and cloud equipment |
| CN112700668B (en) * | 2020-12-22 | 2022-08-02 | 北京百度网讯科技有限公司 | Remote control method for automatic driving, automatic driving vehicle and cloud equipment |
| WO2022143560A1 (en) * | 2020-12-30 | 2022-07-07 | 广州小鹏自动驾驶科技有限公司 | Vehicle turning path planning method and apparatus, vehicle, and storage medium |
| CN112683291B (en) * | 2020-12-30 | 2023-03-31 | 广州小鹏自动驾驶科技有限公司 | Vehicle turning path planning method and device, vehicle and storage medium |
| CN112683291A (en) * | 2020-12-30 | 2021-04-20 | 广州小鹏自动驾驶科技有限公司 | Vehicle turning path planning method and device, vehicle and storage medium |
| CN113268055A (en) * | 2021-04-07 | 2021-08-17 | 北京拓疆者智能科技有限公司 | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment |
| CN113268055B (en) * | 2021-04-07 | 2023-01-13 | 北京拓疆者智能科技有限公司 | Obstacle avoidance control method and device for engineering vehicle and mechanical equipment |
| CN113204236A (en) * | 2021-04-14 | 2021-08-03 | 华中科技大学 | Intelligent agent path tracking control method |
| CN113204236B (en) * | 2021-04-14 | 2022-05-20 | 华中科技大学 | Intelligent agent path tracking control method |
| CN113022408A (en) * | 2021-04-15 | 2021-06-25 | 中国矿业大学 | 360-degree self-adaptive loading and unloading unmanned mining dump truck and control method thereof |
| CN113183943A (en) * | 2021-06-03 | 2021-07-30 | 南昌智能新能源汽车研究院 | Intelligent driving system of agricultural equipment and operation method thereof |
| LU500260B1 (en) * | 2021-06-09 | 2022-12-13 | Phoenix Contact Gmbh & Co | Self-propelled device for use in an industrial environment |
| CN113257026A (en) * | 2021-06-24 | 2021-08-13 | 浙江海康智联科技有限公司 | Seaport cargo vehicle guiding method based on vehicle-road cooperative environment |
| CN113483770A (en) * | 2021-06-30 | 2021-10-08 | 上海西井信息科技有限公司 | Path planning method and device in closed scene, electronic equipment and storage medium |
| CN113467474A (en) * | 2021-07-29 | 2021-10-01 | 安徽江淮汽车集团股份有限公司 | Automatic driving hierarchical control system |
| CN113467474B (en) * | 2021-07-29 | 2023-09-22 | 安徽江淮汽车集团股份有限公司 | Automatic driving layering control system |
| CN113791619A (en) * | 2021-09-14 | 2021-12-14 | 北京航空航天大学 | Dispatching navigation system and method for airport automatic driving tractor |
| CN113791619B (en) * | 2021-09-14 | 2024-04-12 | 北京航空航天大学 | Airport automatic driving tractor dispatching navigation system and method |
| CN116412818A (en) * | 2022-01-05 | 2023-07-11 | 腾讯科技（深圳）有限公司 | Positioning method, positioning device, positioning apparatus, positioning device, computer-readable storage medium, and computer program product |
| CN115123217B (en) * | 2022-09-02 | 2022-11-25 | 青岛慧拓智能机器有限公司 | Mine obstacle vehicle driving track generation method and device and computer equipment |
| CN115123217A (en) * | 2022-09-02 | 2022-09-30 | 青岛慧拓智能机器有限公司 | Mining area obstacle vehicle driving track generation method and device and computer equipment |
| CN117953065A (en) * | 2024-03-26 | 2024-04-30 | 新乡职业技术学院 | Site vehicle control system based on image processing |
| CN117953065B (en) * | 2024-03-26 | 2024-06-11 | 新乡职业技术学院 | Site vehicle control system based on image processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110262508B (en) | 2024-05-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110262508B (en) | Automatic guiding system and method applied to unmanned freight vehicle in closed field | |
| CN108983781B (en) | Environment detection method in unmanned vehicle target search system | |
| CN109164809B (en) | Autonomous following control system and method for vehicle formation | |
| EP3764060B1 (en) | Fusion framework of navigation information for autonomous navigation | |
| CN106598055B (en) | A kind of intelligent vehicle local paths planning method and its device, vehicle | |
| US10310087B2 (en) | Range-view LIDAR-based object detection | |
| CN106080744B (en) | Automatic driving vehicle system | |
| CN104950313B (en) | Extract and identification of road grade method on a kind of road surface | |
| US11648939B2 (en) | Collision monitoring using system data | |
| WO2018181974A1 (en) | Determination device, determination method, and program | |
| CN110155031A (en) | Use the track following for vehicle lateral control of neural network | |
| US11697412B2 (en) | Collision monitoring using statistic models | |
| CN108628324A (en) | Unmanned vehicle navigation method, device, equipment based on map vector and storage medium | |
| WO2020178639A1 (en) | Aligning road information for navigation | |
| EP3578919A1 (en) | Travel history storage method, method for producing travel path model, method for estimating local position, and travel history storage device | |
| JP2022532920A (en) | Yaw rate from radar data | |
| CN110264721A (en) | A kind of urban intersection nearby vehicle trajectory predictions method | |
| CN109084798A (en) | Network issues the paths planning method at the control point with road attribute | |
| CN112577506B (en) | Automatic driving local path planning method and system | |
| US11754415B2 (en) | Sensor localization from external source data | |
| CN211427151U (en) | Automatic guide system applied to unmanned freight vehicle in closed field | |
| CN111208820B (en) | Particle unmanned vehicle set under artificial intelligence big data, control method and medium | |
| CN113227831B (en) | Guardrail estimation method based on multi-sensor data fusion and vehicle-mounted equipment | |
| CN115079699A (en) | Model prediction control-based motion planning method for man-machine co-driving automobile | |
| WO2018180247A1 (en) | Output device, control method, program, and storage medium |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20240328 Address after: Building 3, 7th Floor, Gaosheng Plaza, No. 163 Yingbin Avenue, Xinhua Street, Huadu District, Guangzhou City, Guangdong Province, 510802 Applicant after: Guangzhou Carl Power Technology Co.,Ltd. Country or region after: China Address before: 518118 No.1, Jinlong Avenue, pinghuan community, Malian street, Pingshan District, Shenzhen City, Guangdong Province Applicant before: Shenzhen Shuxiang Technology Co.,Ltd. Country or region before: China |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No. 1 Wulanmulun East Street, Kangbashi District, Ordos City, Inner Mongolia Autonomous Region, 017010 Patentee after: Ordos Kal Power Technology Co.,Ltd. Country or region after: China Address before: Building 3, 7th Floor, Gaosheng Plaza, No. 163 Yingbin Avenue, Xinhua Street, Huadu District, Guangzhou City, Guangdong Province, 510802 Patentee before: Guangzhou Carl Power Technology Co.,Ltd. Country or region before: China |