WO2023236476A1 - 一种无车道线下确定跟踪轨迹的方法及装置 - Google Patents

一种无车道线下确定跟踪轨迹的方法及装置 Download PDF

Info

Publication number
WO2023236476A1
WO2023236476A1 PCT/CN2022/137888 CN2022137888W WO2023236476A1 WO 2023236476 A1 WO2023236476 A1 WO 2023236476A1 CN 2022137888 W CN2022137888 W CN 2022137888W WO 2023236476 A1 WO2023236476 A1 WO 2023236476A1
Authority
WO
WIPO (PCT)
Prior art keywords
trajectory
vehicle
evaluation
motion
point
Prior art date
Application number
PCT/CN2022/137888
Other languages
English (en)
French (fr)
Inventor
凌鹏
刘备
Original Assignee
合众新能源汽车股份有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 合众新能源汽车股份有限公司 filed Critical 合众新能源汽车股份有限公司
Publication of WO2023236476A1 publication Critical patent/WO2023236476A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
    • B60W30/14—Adaptive cruise control
    • B60W30/16—Control of distance between vehicles, e.g. keeping a distance to preceding vehicle
    • B60W30/165—Automatically following the path of a preceding lead vehicle, e.g. "electronic tow-bar"
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
    • B60W40/10—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to vehicle motion
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W60/00—Drive control systems specially adapted for autonomous road vehicles
    • B60W60/001—Planning or execution of driving tasks
    • B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B60—VEHICLES IN GENERAL
    • B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
    • B60W2554/00—Input parameters relating to objects
    • B60W2554/40—Dynamic objects, e.g. animals, windblown objects
    • B60W2554/404—Characteristics

Definitions

  • the present invention relates to the field of automatic driving technology, and in particular to a method and device for a vehicle to follow the vehicle in front of a vehicle without a lane.
  • the path closest to the self-driving vehicle will be When the movement trajectory of the vehicle is used as the movement trajectory of the own vehicle, the movement trajectory is not the optimal movement trajectory, resulting in the problem of inaccurate tracking trajectory.
  • the present invention provides a method and device for determining a tracking trajectory offline without lane lines, which can select the optimal tracking trajectory based on the motion data of the own vehicle, thereby improving the accuracy of selecting the tracking trajectory.
  • the present invention mainly provides the following technical solutions:
  • the present invention provides a method for determining a tracking trajectory without lane lines.
  • the method includes:
  • the motion parameters of the target vehicle Based on the position coordinates of the own vehicle, determine the motion parameters of the target vehicle corresponding to the trajectory point of each motion trajectory, wherein the motion parameters include position coordinates and motion data;
  • the evaluation results of each of the trajectory points are obtained according to the motion parameters of the target vehicle and the motion parameters of the own vehicle corresponding to each of the trajectory points, wherein the evaluation results are used to represent the motion parameters of the own vehicle. How difficult it is for the car to reach the track point;
  • One of the evaluation results is selected from each of the evaluation results, and the motion trajectory where the selected evaluation result is located is determined as the tracking trajectory of the own vehicle.
  • the present invention provides a device for determining a tracking trajectory without lane lines.
  • the device includes:
  • a motion trajectory acquisition module used to acquire the motion trajectory of at least one target vehicle
  • a motion parameter determination module configured to determine the motion parameters of the target vehicle corresponding to the trajectory point of each motion trajectory based on the position coordinates of the own vehicle;
  • An evaluation result calculation module is used to use the first preset equation to obtain the evaluation results of each of the trajectory points according to the motion parameters of the target vehicle and the motion parameters of the own vehicle corresponding to each of the trajectory points;
  • a tracking trajectory selection module is configured to select one of the evaluation results among each of the evaluation results, and determine the motion trajectory where the selected evaluation result is located as the tracking trajectory of the own vehicle.
  • the present invention provides a method and device for determining the tracking trajectory offline without lanes.
  • the invention can accurately calculate The vehicle reaches the evaluation results of each trajectory point, and selects an optimal evaluation result among multiple evaluation results, and determines the motion trajectory where the optimal evaluation result is located as the tracking trajectory.
  • Motion parameters can accurately select the optimal tracking trajectory based on the evaluation results, effectively improving the accuracy of selecting tracking trajectories.
  • each trajectory point of the target vehicle's motion trajectory corresponds to the motion parameters of the target vehicle and the motion parameters of the own vehicle
  • the first preset equation is used to accurately calculate the evaluation results of each trajectory point on the target vehicle's motion trajectory
  • the optimal evaluation result is determined from the rating results, and the tracking trajectory is accurately selected, effectively avoiding the existing technology in which the movement trajectory of the vehicle closest to the vehicle is regarded as the vehicle due to different motion parameters of the vehicle and surrounding vehicles.
  • the motion trajectory is not the optimal motion trajectory, resulting in the problem of inaccurate tracking trajectory.
  • Figure 1 is a schematic flow chart of a method for determining tracking trajectories offline without lanes disclosed in the present invention
  • Figure 2 is a schematic flow chart of a method for determining a target vehicle disclosed in the present invention
  • Figure 3 is a schematic flow chart of a method for updating the movement trajectory of a target vehicle disclosed in the present invention
  • Figure 4 is a schematic flow chart of a method for calculating evaluation results disclosed in the present invention.
  • Figure 5 is a schematic flowchart of another method for determining a tracking trajectory disclosed in the present invention.
  • Figure 6 is a schematic flow chart of a method for determining a driving trajectory disclosed in the present invention.
  • Figure 7 is a schematic flow chart of a method for changing a driving trajectory disclosed in the present invention.
  • Figure 8 is a schematic diagram of a device for determining a tracking trajectory without lane lines disclosed in the present invention.
  • Figure 9 is a schematic diagram of another device for determining a tracking trajectory without lane lines disclosed in the present invention.
  • the autonomous vehicle When an autonomous vehicle is driving on a road without lane lines, the autonomous vehicle will generally follow the trajectory of the vehicle in front.
  • the trajectory of the autonomous vehicle deviates from the trajectory of the vehicle in front and the tracking trajectory needs to be re-determined, currently it is only based on the autonomous driving
  • the position of the vehicle calculates the distance between the motion trajectories of the self-driving vehicle and the moving vehicle, and selects the closest moving vehicle trajectory as the tracking trajectory of the self-driving vehicle. Since the motion parameters of the self-driving vehicle and surrounding vehicles are different, the path closest to the self-driving vehicle will be When the movement trajectory of the vehicle is used as the movement trajectory of the own vehicle, the movement trajectory is not the optimal movement trajectory, resulting in the problem of inaccurate tracking trajectory.
  • embodiments of the present invention provide a method for determining a tracking trajectory offline without lanes.
  • the specific steps are shown in Figure 1.
  • the method includes:
  • Step 101 Obtain the motion trajectory of at least one target vehicle.
  • the target vehicle in front of the vehicle is determined through a camera or a displacement sensor, where the target vehicle is a moving vehicle that meets the preset conditions.
  • draw the movement trajectory of the target vehicle to obtain the movement trajectory of the target vehicle, where each movement trajectory is composed of several trajectory points.
  • Step 102 Based on the position coordinates of the own vehicle, determine the motion parameters of the target vehicle corresponding to the trajectory points of each motion trajectory.
  • the motion parameters include position coordinates and motion data.
  • the vehicle's longitudinal direction front and rear direction
  • the vehicle's transverse direction left and right direction
  • the motion data in the example of the present invention preferably includes the target vehicle's heading angle and traveling speed, and may also include the target vehicle's acceleration, and the target vehicle's movement data is obtained based on the target vehicle's heading angle, traveling speed, and acceleration.
  • Step 103 Use the first preset equation to obtain the evaluation results of each trajectory point according to the motion parameters of the target vehicle and the motion parameters of the own vehicle corresponding to each of the trajectory points.
  • the evaluation result is used to represent the difficulty of the vehicle reaching the trajectory point.
  • the vehicle's motion data is brought into the first preset equation to obtain the evaluation results of all trajectory points.
  • the rating result is used to represent the degree of difficulty for the vehicle to reach the trajectory point. When the value of the evaluation result is larger, it means the difficulty for the vehicle to reach the trajectory point is greater. When the evaluation result is The smaller the value of the result, the less difficult it is for the vehicle to reach the trajectory point.
  • Step 104 Select one of the evaluation results from each of the evaluation results, and determine the motion trajectory where the selected evaluation result is located as the tracking trajectory of the own vehicle.
  • trajectory Specifically, for example, there are three movement trajectories of the target vehicle, namely the first movement trajectory, the second movement trajectory and the third movement trajectory. After obtaining the evaluation results of all trajectory points on the above three movement trajectories, when the final When the motion trajectory with the best evaluation result is the second motion trajectory, the second motion trajectory is used as the tracking trajectory of the vehicle.
  • the embodiment of the present invention also provides a method for determining a target vehicle.
  • This method is a specific introduction to "obtaining the motion trajectory of at least one target vehicle" in step 101 of the embodiment shown in Figure 1.
  • the specific steps are as shown in Figure 2. indication, including:
  • Step 201 Obtain the position coordinates of the moving vehicle.
  • the vehicle when the vehicle deviates from the tracking trajectory being tracked, all moving vehicles traveling in front of the vehicle are acquired through cameras or displacement sensors, and based on the position of the front of the vehicle at the current moment, the vehicle is The longitudinal direction (front and rear direction) of the vehicle is the Y-axis, and the transverse direction (left-right direction) of the vehicle is the X-axis.
  • a rectangular coordinate system is established to determine the position coordinates of each moving vehicle, where the moving vehicle is the vehicle driving in front of the vehicle.
  • Step 202 According to the movement trajectory of the own vehicle, the position coordinates of the moving vehicle are used to determine the closest point between the moving vehicle and the movement trajectory of the own vehicle.
  • the closest point between each moving vehicle and the own vehicle's movement trajectory is determined based on the drawn movement trajectory of the own vehicle.
  • the number of moving vehicles obtained in step 201 is 5, and the position coordinates of the above 5 moving vehicles are obtained, and the movement trajectories of the own vehicle are used to sequentially obtain the closest points of the trajectories of the above 5 moving vehicles and the own vehicle, and at the same time, the The position coordinates of each nearest point.
  • Step 203 Calculate the distance between the moving vehicle and the closest point according to the position coordinates of the moving vehicle.
  • step 202 after determining the closest point of each moving vehicle and the motion trajectory of the own vehicle, calculate the corresponding closest point of each moving vehicle and the moving vehicle based on the position coordinates of the moving vehicle and the position coordinates of the corresponding closest point of the moving vehicle.
  • distance Specifically, for example, the position coordinates of the moving vehicle are (X1, Y1), and the position coordinates of the closest point corresponding to the moving vehicle are (X2, Y2). Then based on the position coordinates of the moving vehicle and the position coordinates of the closest point corresponding to the moving vehicle, calculate the relationship between the moving vehicle and the moving vehicle. The distance between the vehicle's corresponding closest points.
  • Step 204 When the distance is less than a preset distance, determine the moving vehicle as the target vehicle, and obtain the movement trajectory of the target vehicle.
  • the distance between each moving vehicle and the corresponding closest point of the moving vehicle is compared with the preset distance in turn.
  • the distance between the moving vehicle and the corresponding closest point of the moving vehicle is less than the preset distance
  • the moving vehicle is judged to be the target vehicle, and the movement trajectory of the target vehicle is obtained at the same time.
  • the preferred preset distance in this embodiment of the present invention is the longest distance that the vehicle can travel within 30 seconds while complying with current road traffic rules.
  • Step 205 When the distance is greater than or equal to the preset distance, the moving vehicle is determined to be a non-target vehicle.
  • the distance between each moving vehicle and the corresponding closest point of the moving vehicle is compared with the preset distance in turn.
  • the distance between the moving vehicle and the corresponding closest point of the moving vehicle is greater than or equal to the preset distance.
  • the moving vehicle is judged to be a non-target vehicle, and there is no need to obtain the movement trajectory of the non-target vehicle.
  • the embodiment of the present invention accurately selects the target vehicle by acquiring all moving vehicles driving in front of the vehicle, and at the same time, calculating the distance between the moving vehicle and the closest point of the moving vehicle, thereby accurately acquiring the movement trajectory of the target vehicle, and thus can Accurately use the movement trajectory of the target vehicle to select the optimal tracking trajectory, and at the same time improve the accuracy of selecting the tracking trajectory.
  • the present invention also provides a method for updating the movement trajectory of the target vehicle.
  • step 102 of the embodiment shown in Figure 1 "based on the position coordinates of the vehicle, determine that the trajectory point of each movement trajectory corresponds to the The specific introduction after "Motion Parameters of the Target Vehicle", the specific steps are shown in Figure 3, the method also includes:
  • Step 301 Determine whether the ordinate of the trajectory point of each movement trajectory is less than 0 based on the current position coordinates of the vehicle.
  • the movement trajectory of the target vehicle is divided into two parts, one part is in front of the own vehicle and the other part is behind the own vehicle.
  • the current location of the vehicle is determined at the same time.
  • the ordinate of each track point is judged according to the current position coordinate of the vehicle. When the ordinate of the track point is less than 0, it is judged that the track point is behind the vehicle. When the ordinate of the track point is greater than or equal to 0, Then it is judged that the trajectory point is in front of the vehicle.
  • Step 302 Delete the corresponding track point.
  • step 301 when it is determined in step 301 that the ordinate of the trajectory point is less than 0, it is determined that the trajectory point does not have reference value, and the trajectory point whose ordinate is less than 0 is deleted, so that the trajectory points of each target vehicle are The motion trajectory is updated.
  • Step 303 Keep the corresponding trajectory points.
  • step 301 when it is determined in step 301 that the ordinate of the trajectory point is greater than or equal to 0, it is determined that the trajectory point has a reference value, and the trajectory point whose ordinate is greater than or equal to 0 is retained, so as to calculate each trajectory point.
  • the movement trajectory of the target vehicle is updated.
  • the ordinates of each trajectory point are judged based on the current location coordinates of the vehicle, and the movement trajectories of all target vehicles are determined based on the judgment results. Updating and deleting trajectory points that have no reference value can effectively reduce the amount of calculation, thereby improving the efficiency of trajectory point calculation and improving the efficiency of selecting the optimal tracking estimate.
  • the embodiment of the present invention also provides a method for calculating evaluation results. This method is based on "using the first preset equation in step 103 of the embodiment shown in Figure 1 to calculate the target vehicle according to each of the trajectory points.
  • the specific introduction of "motion parameters and the motion parameters of the vehicle to obtain the evaluation results of each of the trajectory points" is shown in Figure 4, including:
  • Step 401 Determine a first evaluation value based on the first evaluation parameter and the first evaluation coefficient, where the first evaluation parameter is the square of the difference between the abscissa of the trajectory point and the abscissa of the vehicle's position.
  • Step 402 Determine a second evaluation value based on the second evaluation parameter and the second evaluation coefficient, where the second evaluation parameter is the square of the difference between the ordinate of the trajectory point and the ordinate of the vehicle's position.
  • Step 403 Determine a third evaluation value based on the third evaluation parameter and the third evaluation coefficient, where the third evaluation parameter is the square of the difference between the heading angle of the target vehicle corresponding to the track point and the heading angle of the own vehicle.
  • Step 404 Determine a fourth evaluation value based on the fourth evaluation parameter and the fourth evaluation coefficient, where the fourth evaluation parameter is the square of the difference between the speed of the target vehicle corresponding to the trajectory point and the speed of the own vehicle.
  • Step 405 Obtain the evaluation result of each trajectory point based on the sum of the first evaluation value, the second evaluation value, the third evaluation value and the fourth evaluation value.
  • Cost K x (x p -x ego ) 2 +K y (y p -y ego ) 2 +K t ( ⁇ p - ⁇ ego ) 2 +K v (v p -v ego ) 2 ;
  • x p , y p , ⁇ p and v p in the formula respectively represent the abscissa and ordinate coordinates, heading angle and speed of each trajectory point on the target vehicle's movement trajectory
  • x ego , y ego , ⁇ ego and v ego represent respectively The abscissa and ordinate of the vehicle's current position, heading angle and speed
  • the first evaluation coefficient K x is 1
  • the second evaluation coefficient K y is 1
  • the third evaluation coefficient K t is 10.3
  • the fourth evaluation coefficient K v is 3.5.
  • Cost K x (x p -x ego ) 2 +K y (y p -y ego ) 2 +K t ( ⁇ p - ⁇ ego ) 2 +K v (v p -v ego ) 2 +K a (a ego -a obs ) 2 ;
  • K a is the fifth evaluation parameter
  • a ego is the acceleration of the target vehicle
  • a obs is the acceleration of the own vehicle.
  • the fifth evaluation parameter K a is 3.5.
  • the present invention provides another method for determining the tracking trajectory.
  • This method is to "select one of the evaluation results among the evaluation results in step 104 of the embodiment shown in Figure 1, and add the evaluation result to
  • the specific introduction of "determine the tracking trajectory of the vehicle based on the movement trajectory where it is located" the specific steps are shown in Figure 5, including:
  • Step 501 Obtain the minimum value among the evaluation results.
  • step 104 when performing step 104, when selecting one of the evaluation results among the evaluation results, compare the values of each evaluation result, and select the minimum value of the evaluation result among the comparison results, where the value of the evaluation result is The smaller the value, the easier it is for the vehicle to reach the trajectory point.
  • Step 502 Determine the motion trajectory where the minimum value of the evaluation result corresponds to the trajectory point, and determine the motion trajectory as the tracking trajectory of the own vehicle.
  • step 501 after selecting the minimum value of the evaluation result, determine the trajectory point corresponding to the minimum value of the evaluation result, determine the motion trajectory where the trajectory point is located, and use the determined motion trajectory as the tracking trajectory of the vehicle.
  • the embodiment of the present invention can accurately select the optimal following trajectory based on the motion parameters of the own vehicle and the target vehicle, thereby improving the accuracy of selecting the tracking trajectory.
  • the embodiment of the present invention also provides a method for determining a driving trajectory.
  • the method is to "select one of the evaluation results among the evaluation results and add the The detailed introduction is given after "determining the tracking trajectory of the vehicle based on the motion trajectory where the evaluation result is located.”
  • the specific steps are shown in Figure 6.
  • the method also includes:
  • Step 601 Obtain the motion data of the target vehicle corresponding to the trajectory point with the minimum evaluation result.
  • step 104 after executing step 104, after determining the trajectory point with the minimum evaluation result, the motion data of the target vehicle corresponding to the trajectory point is obtained, specifically, the heading angle of the target vehicle at the trajectory point is obtained.
  • Step 602 Use the second preset equation to determine the driving trajectory of the vehicle based on the trajectory point coordinates, the heading angle of the trajectory point corresponding to the target vehicle, the location coordinates of the vehicle, and the heading angle of the vehicle.
  • the driving trajectory is the driving route of the vehicle to the trajectory point corresponding to the minimum value of the evaluation result.
  • y ego ax ego 3 +bx ego 2 +cx ego +d;
  • ⁇ ego 3ax ego 2 +2abx ego +c.
  • the present invention fully considers the influence of the target vehicle's motion data and the own vehicle's motion data by using the second preset equation. After determining the tracking trajectory, it fits the optimal driving trajectory according to the second preset equation, so that The vehicle can drive to the determined trajectory point in the shortest time, effectively reducing the time it takes the vehicle to reach the target trajectory point and ensuring the safety of the vehicle's driving.
  • the embodiment of the present invention also provides a method for changing the driving trajectory.
  • This method is specifically introduced after "determining the driving trajectory of the vehicle" in step 602 of the embodiment shown in Figure 6.
  • the specific steps are as shown in Figure 7 As shown, the method also includes:
  • Step 701 During the preset driving cycle, determine whether the vehicle reaches the trajectory point corresponding to the minimum value of the evaluation result.
  • step 602 when a preset driving cycle is reached, it is determined according to the position coordinates of the vehicle whether the vehicle reaches the trajectory point corresponding to the minimum value of the evaluation result.
  • the position coordinates of the vehicle are consistent with the When the minimum value of the evaluation result corresponds to the position coordinate of the trajectory point, it is judged that the vehicle has reached the minimum value of the evaluation result corresponding to the trajectory point.
  • the position coordinate of the vehicle corresponds to the minimum value of the evaluation result corresponding to the trajectory point, When the position coordinates are different, it is determined that the vehicle has not reached the trajectory point corresponding to the minimum value of the evaluation result.
  • Step 702 The vehicle follows the tracking trajectory.
  • step 701 when it is determined in step 701 that the vehicle reaches the trajectory point corresponding to the minimum value of the evaluation result, the fitted driving trajectory is deleted and the vehicle follows the determined tracking trajectory.
  • Step 703 The vehicle continues to drive according to the driving trajectory, and in the next preset driving cycle, it is determined again whether the vehicle reaches the trajectory point corresponding to the minimum value of the evaluation result.
  • the vehicle after executing step 701, if the vehicle does not reach the trajectory point corresponding to the minimum value of the evaluation result within the preset driving period, it will continue to fit the driving trajectory of the preset period, and will continue to fit the driving trajectory of the preset period, and when it reaches the next driving cycle When, it is judged again whether the vehicle reaches the trajectory point corresponding to the minimum value of the evaluation result.
  • the preset driving cycle in this embodiment of the present invention is 30 seconds.
  • embodiments of the present invention provide a device for determining a tracking trajectory offline without lane lines, which can select the optimal tracking trajectory based on the motion data of the own vehicle. , improving the accuracy of selecting tracking trajectories.
  • the embodiment of the device corresponds to the foregoing method embodiment. For the convenience of reading, this embodiment will not elaborate on the details of the foregoing method embodiment one by one. However, it should be clear that the device in this embodiment can correspondingly implement the foregoing method implementation. All the contents in the example are shown in Figure 8.
  • the device includes:
  • the motion trajectory acquisition module 10 is used to acquire the motion trajectory of at least one target vehicle.
  • the motion parameter determination module 20 is configured to determine, based on the position coordinates of the own vehicle, the motion parameters of the target vehicle corresponding to the trajectory points of each of the motion trajectories obtained by the motion trajectory module 10 .
  • the evaluation result calculation module 30 is configured to use the first preset equation to obtain the motion parameters of each of the trajectory points according to the motion parameters of the target vehicle and the motion parameters of the own vehicle corresponding to each of the trajectory points determined by the motion parameter determination module 20. Evaluation results.
  • the tracking trajectory selection module 40 is configured to select one of the evaluation results according to the evaluation results calculated by the evaluation result calculation module 30, and determine the tracking of the own vehicle based on the motion trajectory where the evaluation result is located. trajectory.
  • the motion trajectory acquisition module 10 includes:
  • the position coordinate acquisition unit 110 is used to obtain the position coordinates of the moving vehicle
  • the closest point determination unit 120 determines the closest point between the moving vehicle and the own vehicle's movement trajectory based on the movement trajectory of the vehicle and the position coordinates of the moving vehicle obtained by the position coordinate acquisition unit 110 .
  • the distance calculation unit 130 is configured to calculate the distance between the moving vehicle and the closest point determined by the closest point determination unit 120 based on the position coordinates of the moving vehicle acquired by the position coordinate acquisition unit 110 .
  • the target vehicle determination unit 140 determines the moving vehicle as the target vehicle and obtains the movement trajectory of the target vehicle when the distance obtained by the distance calculation unit 130 is less than the preset distance.
  • the device for determining the tracking trajectory without lane lines also includes an update motion trajectory module 50:
  • the position determination unit 510 is configured to determine whether the ordinate of the trajectory point of each movement trajectory is less than 0 based on the position coordinates of the vehicle at the current moment.
  • the deletion unit 520 is configured to delete the corresponding trajectory point when the position determination unit 510 determines that the ordinate of the trajectory point is less than 0.
  • the update unit 530 is configured to retain the corresponding trajectory point when the position determination unit 510 determines that the ordinate of the trajectory point is greater than or equal to 0.
  • the evaluation result calculation module 30 also includes:
  • the first calculation unit 310 is used to determine the first evaluation value according to the first evaluation parameter and the first evaluation coefficient.
  • the second calculation unit 320 is used to determine the second evaluation value according to the second evaluation parameter and the second evaluation coefficient.
  • the third calculation unit 330 is used to determine the third evaluation value according to the third evaluation parameter and the third evaluation coefficient.
  • the fourth calculation unit 340 is used to determine the fourth evaluation value according to the fourth evaluation parameter and the fourth evaluation coefficient.
  • the fifth calculation unit 350 is used to calculate the first evaluation value calculated by the first calculation unit 310 , the second evaluation value calculated by the second calculation unit 320 , the third evaluation value calculated by the third calculation unit 330 and the fourth calculation unit 340 The sum of the calculated fourth evaluation values is used to obtain the evaluation results of each of the trajectory points.
  • the tracking trajectory selection module 40 also includes:
  • the evaluation result comparison unit 410 is used to obtain the minimum value among the evaluation results.
  • the tracking trajectory determination unit 420 is configured to determine the movement trajectory where the minimum value of the evaluation result corresponds to the trajectory point according to the evaluation result comparison unit 410, and determine the movement trajectory as the tracking trajectory of the own vehicle.
  • the device for determining the tracking trajectory offline without lane lines also includes a driving trajectory fitting module 60.
  • the driving trajectory fitting module 60 includes:
  • the motion data acquisition unit 610 is configured to acquire the motion data of the target vehicle corresponding to the trajectory point with the minimum evaluation result.
  • the driving trajectory fitting unit 620 is configured to use the second preset equation to determine the trajectory point coordinates obtained by the motion data acquisition unit 610, the heading angle of the trajectory point corresponding to the target vehicle, the position coordinates of the own vehicle, and the heading angle of the own vehicle. The driving trajectory of the vehicle.
  • the device for determining the tracking trajectory without lane lines also includes a trajectory switching module 70.
  • the trajectory switching module 70 includes:
  • the switching judgment unit 710 is used to judge whether the vehicle reaches the trajectory point corresponding to the minimum value of the evaluation result within the preset driving cycle;
  • the trajectory switching unit 720 is used to determine in the switching judgment unit 710 that the vehicle reaches the minimum value of the evaluation result corresponding to the trajectory point, and control the vehicle to follow the tracking trajectory;
  • the secondary judgment unit 730 is used to judge in the switching judgment unit 710 that the vehicle has not reached the trajectory point corresponding to the minimum value of the evaluation result, control the vehicle to continue driving according to the driving trajectory, and make the judgment again in the next preset driving cycle. Whether the vehicle reaches the minimum value of the evaluation result corresponds to the trajectory point.
  • memory may include non-volatile memory in computer-readable media, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flash RAM).
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash RAM
  • Memory includes At least one memory chip.
  • embodiments of the present invention may be provided as methods, systems, or computer program products.
  • the invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.
  • the invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • These computer program instructions may also be stored in a computer-readable memory that causes a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including the instruction means, the instructions
  • the device implements the functions specified in a process or processes of the flowchart and/or a block or blocks of the block diagram.
  • These computer program instructions may also be loaded onto a computer or other programmable data processing device, causing a series of operating steps to be performed on the computer or other programmable device to produce computer-implemented processing, thereby executing on the computer or other programmable device.
  • Instructions provide steps for implementing the functions specified in a process or processes of a flowchart diagram and/or a block or blocks of a block diagram.
  • a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • Memory may include non-volatile memory in computer-readable media, random access memory (RAM) and/or non-volatile memory in the form of read-only memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
  • RAM random access memory
  • ROM read-only memory
  • flash RAM flash memory
  • Computer-readable media includes both persistent and non-volatile, removable and non-removable media that can be implemented by any method or technology for storage of information.
  • Information may be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory
  • PRAM phase change memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • RAM random access memory
  • ROM read-only memory
  • EEPROM electrically erasable programmable read-only memory
  • flash memory or other memory technology
  • CD-ROM CD-ROM
  • DVD Digital Versatile Disc
  • magnetic tape cassettes tape magnetic disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
  • computer-readable media does not include transitory media, such as modulated data signals and carrier waves.
  • embodiments of the present invention may be provided as methods, systems or computer program products.
  • the invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects.
  • the invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

Landscapes

  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Transportation (AREA)
  • Mechanical Engineering (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Traffic Control Systems (AREA)
  • Image Analysis (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种无车道线下确定跟踪轨迹的方法及装置，该方法包括：获取至少一个目标车辆的运动轨迹；基于本车位置坐标，确定每个运动轨迹的轨迹点对应目标车辆的运动参数；利用第一预设方程，根据各轨迹点对应目标车辆的运动参数和本车的运动参数，得到各轨迹点的评价结果；在各评价结果中选择一个评价结果，并将该评价结果所在的运动轨迹，确定本车的跟踪轨迹。该方法可以准确的根据评价结果选择最优的跟踪轨迹，有效的提高了选择跟踪轨迹的准确率。

Description

一种无车道线下确定跟踪轨迹的方法及装置 技术领域
本发明涉及自动驾驶技术领域，特别是涉及一种无车道线下车辆跟随前车行驶的方法及装置。
背景技术
近年来，汽车智能驾驶蓬勃发展，智能驾驶提供了出行便利，在生产和应用过程中对于周围环境尤其是运动车辆轨迹的追踪，评估有着巨大的需求，在进行自动驾驶时，需要对周围车辆信息进行综合评判。在自动驾驶车辆在无车道线的道路上进行行驶时，自动驾驶车辆一般都会跟随前车轨迹，当自动驾驶车辆行驶轨迹脱离前车轨迹，并且需要重新确定跟踪轨迹时，目前仅仅是根据自动驾驶车辆的位置计算自动驾驶车辆与运动车辆的运动轨迹之间的距离，并选择距离最近的运动车辆轨迹作为自动驾驶车辆的跟踪轨迹，由于本车和周围车辆的运动参数不同，将与本车最近的车辆的运动轨迹作为本车的运动轨迹时，该运动轨迹并非是最优运动轨迹，导致出现选择的跟踪轨迹不准确的问题。
发明内容
有鉴于此，本发明提供一种无车道线下确定跟踪轨迹的方法及装置，可以根据自车的运动数据选择最优的跟踪轨迹，提高了选择跟踪轨迹的准确率。
为达到上述目的，本发明主要提供如下技术方案：
第一方面，本发明提供了一种无车道线下确定跟踪轨迹的方法，所述方法包括：
获取至少一个目标车辆的运动轨迹；
基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数，其中，所述运动参数包括位置坐标和运动数据；
利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果，其中，所述评价结果 用于表示所述本车到达所述轨迹点的困难程度；
在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹。
第二方面，本发明提供了一种无车道线下确定跟踪轨迹的装置，所述装置包括：
运动轨迹获取模块，用于获取至少一个目标车辆的运动轨迹；
运动参数确定模块，用于基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数；
评价结果计算模块，用于利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果；
跟踪轨迹选择模块，用于在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹。
借由上述技术方案，本发明提供了一种无车道线下确定跟踪轨迹的方法及装置，通过根据目标车辆各个轨迹点的运动参数和本车运动参数，利用第一预设方程，准确的计算本车到达各个轨迹点的评价结果，并在多个评价结果中，选择一个最优的评价结果，将最优评价结果所在的运动轨迹确定为跟踪轨迹，通过结合本车运动参数和目标车辆的运动参数，可以准确的根据评价结果选择最优的跟踪轨迹，有效的提高了选择跟踪轨迹的准确率。同时本发明实施例中，通过目标车辆运动轨迹各个轨迹点对应目标车辆的运动参数和本车运动参数，利用第一预设方程，准确的计算目标车辆运动轨迹上各个轨迹点的评价结果，并在评级结果中确定最优的评价结果，进而准确的选择跟踪轨迹，有效的避免了现有技术中由于本车和周围车辆的运动参数不同，将与本车最近的车辆的运动轨迹作为本车的运动轨迹时，该运动轨迹并非是最优运动轨迹，导致出现选择的跟踪轨迹不准确的问题。
上述说明仅是本发明技术方案的概述，为了能够更清楚了解本发明的技术手段，而可依照说明书的内容予以实施，并且为了让本发明的上述和 其它目的、特征和优点能够更明显易懂，以下特举本发明的具体实施方式。
附图说明
为了更清楚地说明本发明实施例或现有技术中的技术方案，下面将对实施例或现有技术描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1为本发明公开的一种无车道线下确定跟踪轨迹的方法流程示意图；
图2为本发明公开的一种确定目标车辆的方法流程示意图；
图3为本发明公开的一种更新目标车辆运动轨迹的方法流程示意图；
图4为本发明公开的一种计算评价结果的方法流程示意图；
图5为本发明公开的又一种确定跟踪轨迹的方法流程示意图；
图6为本发明公开的一种确定行驶轨迹的方法流程示意图；
图7为本发明公开的一种更换行驶轨迹的方法流程示意图；
图8为本发明公开的一种无车道线下确定跟踪轨迹的装置示意图；
图9为本发明公开的又一种无车道线下确定跟踪轨迹的装置示意图。
具体实施方式
下面将参照附图更详细地描述本发明的示例性实施例。虽然附图中显示了本发明的示例性实施例，然而应当理解，可以以各种形式实现本发明而不应被这里阐述的实施例所限制。相反，提供这些实施例是为了能够更透彻地理解本发明，并且能够将本发明的范围完整的传达给本领域的技术人员。
在自动驾驶车辆在无车道线的道路上进行行驶时，自动驾驶车辆一般都会跟随前车轨迹，当自动驾驶车辆行驶轨迹脱离前车轨迹，并且需要重新确定跟踪轨迹时，目前仅仅是根据自动驾驶车辆的位置计算自动驾驶车辆与运动车辆的运动轨迹之间的距离，并选择距离最近的运动车辆轨迹作为自动驾驶车辆的跟踪轨迹，由于本车和周围车辆的运动参数不同，将与 本车最近的车辆的运动轨迹作为本车的运动轨迹时，该运动轨迹并非是最优运动轨迹，导致出现选择的跟踪轨迹不准确的问题。
为了解决上述问题，本发明实施例提供了一种无车道线下确定跟踪轨迹的方法，具体步骤如图1所示，所述方法包括：
步骤101，获取至少一个目标车辆的运动轨迹。
具体的，在本发明实施例的步骤中，在本车脱离正在跟踪车辆的运动轨迹时，通过摄像头或位移传感器确定在本车前方的目标车辆，其中，目标车辆为符合预设条件的运动车辆，同时，在确定目标车辆之后，绘制目标车辆的运动轨迹，从而得到目标车辆的运动轨迹，其中，每个运动轨迹由若干轨迹点构成。具体的，本发明实施例中目标车辆可以为一个或多个，每个目标车辆对应一个运动轨迹。
步骤102，基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数。
其中，所述运动参数包括位置坐标和运动数据。
具体的，在执行步骤101之后，在获取所有目标车辆的运动轨迹后，根据本车当前时刻车头所在的位置，以车辆的纵向(前后方向)为Y轴，以车辆的横向(左右方向)为X轴，建立直角坐标系，并根据建立的直角坐标系确定所有目标车辆运动轨迹上各个轨迹点的坐标，同时获取每个目标车辆在各个轨迹点的航向角和行驶速度，并根据航向角和行驶速度形成目标车辆运动数据，并根据轨迹点的坐标和目标车辆运动数据，得到每个轨迹点对应目标车辆的运动参数。具体的，本发明实例运动数据优先的包括目标车辆航向角和行驶速度，还可以包括目标车辆的加速度，并根据目标车辆航向角、行驶速度和加速度得到目标车辆运动数据。
步骤103，利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果。
其中，所述评价结果用于表示所述本车到达所述轨迹点的困难程度。
具体的，在执行步骤102之后，在得到各个轨迹点对应目标车辆的运动参数后，根据本车的运动参数，将目标车辆每个轨迹点坐标、轨迹点坐标对应的运动数据、本车坐标和本车运动数据带入至第一预设方程，得到 所有轨迹点的评价结果。具体的，本发明实施例中，评级结果用于表示所述本车到达所述轨迹点的困难程度，当评价结果的值越大时，表示本车到轨迹点的困难程度越大，当评价结果的值越小时，表示本车到轨迹点的困难程度越小。
步骤104，在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹。
具体的，在执行步骤103之后，在得到所述轨迹点的评价结果后，在所有轨迹点中选择一个最优的评价结果，并将最优评价结果所在的运动轨迹，确定为本车的跟踪轨迹。具体的，例如存在三个目标车辆的运动轨迹，分别为第一运动轨迹、第二运动轨迹和第三运动轨迹，在得到上述三个运动轨迹上所有轨迹点的评价结果后，其中，当最优评价结果所在的运动轨迹为第二运动轨迹时，则将第二运动轨迹作为本车的跟踪轨迹。
进一步的，本发明实施例还提供一种确定目标车辆的方法，该方法是对图1所示实施例步骤101中“获取至少一个目标车辆的运动轨迹”的具体介绍，具体步骤如图2所示，包括：
步骤201，获取运动车辆的位置坐标。
具体的，在本发明实施例的步骤中，当本车脱离正在跟踪的跟踪轨迹时，通过摄像头或者位移传感器获取在本车前方行驶的所有运动车辆，并根据当前时刻车头所在的位置，以本车的纵向(前后方向)为Y轴，以车辆的横向(左右方向)为X轴，建立直角坐标系，从而确定各个运动车辆的位置坐标，其中，运动车辆为在本车前方行驶的车辆。
步骤202，根据本车运动轨迹，利用所述运动车辆的位置坐标，确定所述运动车辆与所述本车运动轨迹的最近点。
具体的，在执行步骤201之后，在确定各个运动车辆的位置坐标之后，根据绘制的本车的运动轨迹，确定各个运动车辆与本车运动轨迹的最近点。具体的，例如步骤201中得到的运动车辆为5辆，并获取上述5辆运动车辆的位置坐标，利用本车的运动轨迹，依次获取上述5辆运动车辆与本车轨迹的最近点，同时得到各个最近点的位置坐标。
步骤203，根据所述运动车辆的位置坐标，计算所述运动车辆与所述最 近点的距离。
具体的，在执行步骤202之后，在确定各个运动车辆与本车运动轨迹的最近点之后，根据运动车辆的位置坐标和运动车辆对应最近点的位置坐标，计算各个运动车辆与运动车辆对应最近点的距离。具体的，例如运动车辆的位置坐标为(X1，Y1)，运动车辆对应最近点位置坐标为(X2，Y2)，则根据运动车辆位置坐标和运动车辆对应最近点位置坐标，计算运动车辆与运动车辆对应最近点之间的距离。
步骤204，在所述距离小于预设距离时，将所述运动车辆确定为所述目标车辆，并获取所述目标车辆的运动轨迹。
具体的，在执行步骤203之后，将各个运动车辆与运动车辆对应最近点之间的距离，依次与预设距离进行比对，当运动车辆与运动车辆对应最近点之间的距离小于预设距离时，则判断该运动车辆为目标车辆，同时获取目标车辆的运动轨迹。具体的，本发明实施例优选的预设距离为在遵守当前道路交通规则的情况下，本车在30s内可以行驶的最远距离。
步骤205，在所述距离大于或等于预设距离时，则将运动车辆判断为非目标车辆。
具体的，在执行步骤203之后，将各个运动车辆与运动车辆对应最近点之间的距离，依次与预设距离进行比对，当运动车辆与运动车辆对应最近点之间的距离大于或等于预设距离时，则判断该运动车辆为非目标车辆，并无需获取非目标车辆的运动轨迹。
具体的，本发明实施例通过获取在本车前方行驶的所有运动车辆，同时通过计算运动车辆与运动车辆最近点的距离，准确的选择目标车辆，从而准确的获取目标车辆的运动轨迹，进而可以准确的利用目标车辆的运动轨迹选择最优的跟踪轨迹，同时提高了选择跟踪轨迹的准确率。
进一步的，本发明还提供一种更新目标车辆运动轨迹的方法，该方法是在图1所示实施例步骤102中“基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数”之后的具体介绍，具体步骤如图3所示，所述方法还包括：
步骤301，根据所述本车当前时刻的位置坐标，判断各所述运动轨迹的 轨迹点纵坐标是否小于0。
具体的，在本发明实施例的步骤中，目标车辆的运动轨迹分为两个部分，一部分在本车前方，一部分在本车后方，在确定目标车辆的运动轨迹，同时确定本车当前时刻所在位置坐标后，根据本车当前位置坐标对各个轨迹点的纵坐标进行判断，当轨迹点的纵坐标小于0时，则判断轨迹点在本车后方，当轨迹点纵坐标大于或等于0时，则判断轨迹点在本车前方。
步骤302，删除对应的所述轨迹点。
具体的，在执行步骤301之后，当步骤301中判断轨迹点的纵坐标小于0时，则判断轨迹点不具有参考价值，并删除轨迹点纵坐标小于0的轨迹点，从而对各个目标车辆的运动轨迹进行更新。
步骤303，则保留对应的所述轨迹点。
具体的，在执行步骤301之后，当步骤301中判断轨迹点的纵坐标大于或等于0时，则判断轨迹点具有参考价值，并保留轨迹点纵坐标大于或等于0的轨迹点，从而对各个目标车辆的运动轨迹进行更新。
具体的，本发明实施例中在获取所述目标车辆的运动轨迹后，通过本车当前时刻所在位置坐标，对各个轨迹点的纵坐标进行判断，并根据判断结果对所有目标车辆的运动轨迹进行更新，删除不具有参考价值的轨迹点，可以有效的减少计算量，从而提高了轨迹点计算效率，同时提高了选择最优跟踪估计的效率。
进一步的，本发明实施例还提供一种计算评价结果的方法，该方法是对图1所示实施例步骤103中“利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果”的具体介绍，具体步骤如图4所示，包括：
步骤401，根据第一评价参数和第一评价系数，确定第一评价值，其中，所述第一评价参数为轨迹点横坐标与本车位置横坐标差值的平方。
步骤402，根据第二评价参数和第二评价系数，确定第二评价值，其中，所述第二评价参数为轨迹点纵坐标与本车位置纵坐标差值的平方。
步骤403，根据第三评价参数和第三评价系数，确定第三评价值，其中，所述第三评价参数为轨迹点对应目标车辆航向角与本车航向角差值的平 方。
步骤404，根据第四评价参数和第四评价系数，确定第四评价值，其中，所述第四评价参数为轨迹点对应目标车辆速度与本车速度差值的平方。
步骤405，根据所述第一评价值、所述第二评价值、所述第三评价值和所述第四评价值的和，得到各所述轨迹点的所述评价结果。
具体的，本发明实施例中在计算各轨迹点的评价结果时，采用下列公式计算：
Cost＝K x(x p-x ego) 2+K y(y p-y ego) 2+K t(θ p-θ ego) 2+K v(v p-v ego) 2；
其中，公式中x p、y p、θ p和v p分别表示目标车辆运动轨迹上各轨迹点的横坐标和纵坐标，航向角和速度，x ego、y ego、θ ego和v ego分别表示本车当前位置点的横坐标和纵坐标，航向角和速度，第一评价系数K x为1，第二评价系数K y为1，第三评价系数K t为10.3，第四评价系数K v为3.5。
具体的，本发明实施例中在计算各轨迹点的评价结果时，还采用下列公式计算：
Cost＝K x(x p-x ego) 2+K y(y p-y ego) 2+K t(θ p-θ ego) 2+K v(v p-v ego) 2+K a(a ego-a obs) 2；
其中，K a为第五评价参数，a ego为目标车辆加速度，a obs为本车加速度，具体的，第五评价参数K a为3.5。
进一步的，本发明提供又一种确定跟踪轨迹的方法，该方法是对图1所示实施例步骤104中“在各所述评价结果中选择一个所述评价结果，并将该所述评价结果所在的所述运动轨迹，确定所述本车的跟踪轨迹”的具体介绍，具体步骤如图5所示，包括：
步骤501，获取各所述评价结果中的最小值。
具体的，在执行步骤104时，在各所述评价结果中选择一个所述评价结果时，将各个评价结果的值进行比对，在比对结果中选择评价结果最小值，其中，评价结果的值越小，表示本车到达轨迹点越容易。
步骤502，确定评价结果最小值对应所述轨迹点所在的所述运动轨迹，并将该所述运动轨迹确定为所述本车的跟踪轨迹。
具体的，在执行步骤501之后，在选择评价结果的最小值之后，确定评价结果最小值对应的轨迹点，并确定该轨迹点所在的运动轨迹，将确定 的运动轨迹作为本车的跟踪轨迹。
具体的，本发明实施例通过选择评价结果最小值，可以根据自车和目标车辆的运动参数，准确的选择最优跟随轨迹，提高了选择跟踪轨迹的准确率。
进一步的，本发明实施例还提供一种确定行驶轨迹的方法，该方法是在图1所示实施例步骤104中“在各所述评价结果中选择一个所述评价结果，并将该所述评价结果所在的所述运动轨迹，确定所述本车的跟踪轨迹”之后的具体介绍，具体步骤如图6所示，所述方法还包括：
步骤601，获取评价结果最小值的所述轨迹点对应所述目标车辆的运动数据。
具体的，在执行步骤104之后，在确定评价结果最小值的轨迹点之后，获取该轨迹点对应目标车辆的运动数据，具体为获取目标车辆在该轨迹点的航向角。
步骤602，利用第二预设方程，根据轨迹点坐标、轨迹点对应所述目标车辆的航向角、本车位置坐标和本车航向角，确定所述本车的行驶轨迹。其中，所述行驶轨迹为所述本车向所述评价结果最小值对应所述轨迹点的行驶路线。
具体的，第二预设方程为y＝ax 3+bx 2+cx+d。
当获取的轨迹点对应的目标车辆运动参数为(x obs，y obs，θ obs)，本车的运动参数为(x ego，y ego，θ ego)时，则求解下列方程，即可得到本车的行驶轨迹；
y obs＝ax obs 3+bx obs 2+cx obs+d；
y ego＝ax ego 3+bx ego 2+cx ego+d；
θ obs＝3ax obs 2+2abx obs+c；
θ ego＝3ax ego 2+2abx ego+c。
具体的，本发明通过使用第二预设方程，充分考虑目标车辆的运动数据和本车运动数据的影响，在确定跟踪轨迹后，根据第二预设方程拟合最优的行驶轨迹，以使本车可以在最短的时间内行驶到确定的轨迹点的位置，有效的降低了本车到达目标轨迹点的时间，保证了本车行驶的安全性。
进一步的，本发明实施例还提供一种更换行驶轨迹的方法，该方法是在图6所示实施例步骤602中“确定所述本车的行驶轨迹”之后的具体介绍，具体步骤如图7所示，所述方法还包括：
步骤701，在预设行驶周期内，判断所述本车是否到达所述评价结果最小值对应所述轨迹点。
具体的，在执行步骤602之后，在到达一个预设行驶周期时，根据本车的位置坐标，判断本车是否到达所述评价结果最小值对应所述轨迹点，当本车位置坐标与所述评价结果最小值对应所述轨迹点的位置坐标相同时，则判断本车到达所述评价结果最小值对应所述轨迹点，当本车位置坐标与所述评价结果最小值对应所述轨迹点的位置坐标不同时，则判断本车未到达所述评价结果最小值对应所述轨迹点。
步骤702，则所述本车跟随所述跟踪轨迹行驶。
具体的，在执行步骤701之后，当步骤701中判断本车到达所述评价结果最小值对应所述轨迹点时，则删除拟合的行驶轨迹，并跟随确定的跟踪轨迹行驶。
步骤703，则所述本车继续按照所述行驶轨迹行驶，并在下一个预设行驶周期内，再次判断所述本车是否到达所述评价结果最小值对应所述轨迹点。
具体的，在执行步骤701之后，在预设行驶周期内本车未到达所述评价结果最小值对应所述轨迹点时，则继续拟合预设周期的行驶轨迹，并在到达下一个行驶周期时，在再次判断本车是否到达所述评价结果最小值对应所述轨迹点。具体的，本发明实施例的预设行驶周期为30s。
进一步的，作为上述图1-7所示方法实施例的实现，本发明实施例提供了一种无车道线下确定跟踪轨迹的装置，该装置可以根据自车的运动数据选择最优的跟踪轨迹，提高了选择跟踪轨迹的准确率。该装置的实施例与前述方法实施例对应，为便于阅读，本实施例不再对前述方法实施例中的细节内容进行逐一赘述，但应当明确，本实施例中的装置能够对应实现前述方法实施例中的全部内容，具体如图8所示，该装置包括：
运动轨迹获取模块10，用于获取至少一个目标车辆的运动轨迹。
运动参数确定模块20，用于基于本车位置坐标，确定运动轨迹模块获10获取的每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数。
评价结果计算模块30，用于利用第一预设方程，根据运动参数确定模块20确定的各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果。
跟踪轨迹选择模块40，用于根据评价结果计算模块30计算的各所述评价结果中选择一个所述评价结果，并将该所述评价结果所在的所述运动轨迹，确定所述本车的跟踪轨迹。
进一步的，如图9所示，运动轨迹获取模块10包括：
位置坐标获取单元110，用于获取运动车辆的位置坐标；
最近点确定单元120，根据本车运动轨迹，根据位置坐标获取单元110获取的运动车辆位置坐标，确定所述运动车辆与所述本车运动轨迹的最近点。
距离计算单元130，用于根据位置坐标获取单元110获取的所述运动车辆的位置坐标，计算所述运动车辆与最近点确定单元120确定的所述最近点的距离。
目标车辆确定单元140，在距离计算单元130得到的所述距离小于预设距离时，将所述运动车辆确定为所述目标车辆，并获取所述目标车辆的运动轨迹。
进一步的，如图9所示，无车道线下确定跟踪轨迹的装置还包括更新运动轨迹模块50：
位置判断单元510，用于根据所述本车当前时刻的位置坐标，判断各所述运动轨迹的轨迹点纵坐标是否小于0。
删除单元520，用于在位置判断单元510判断轨迹点纵坐标小于0时，删除对应的所述轨迹点。
更新单元530，用于在位置判断单元510判断轨迹点纵坐标大于或等于0时，保留对应的所述轨迹点。
进一步的，如图9所示，评价结果计算模块30还包括：
第一计算单元310，用于根据第一评价参数和第一评价系数，确定第一 评价值。
第二计算单元320，用于根据第二评价参数和第二评价系数，确定第二评价值。
第三计算单元330，用于根据第三评价参数和第三评价系数，确定第三评价值。
第四计算单元340，用于根据第四评价参数和第四评价系数，确定第四评价值。
第五计算单元350，用于根据第一计算单元310计算的第一评价值、第二计算单元320计算的第二评价值、第三计算单元330计算的第三评价值和第四计算单元340计算的第四评价值的和，得到各所述轨迹点的所述评价结果。
进一步的，如图9所示，跟踪轨迹选择模块40还包括：
评价结果比对单元410，用于获取各所述评价结果中的最小值。
跟踪轨迹确定单元420，用于根据评价结果比对单元410确定评价结果最小值对应所述轨迹点所在的所述运动轨迹，并将该所述运动轨迹确定为所述本车的跟踪轨迹。
进一步的，如图9所示，无车道线下确定跟踪轨迹的装置还包括行驶轨迹拟合模块60，行驶轨迹拟合模块60包括：
运动数据获取单元610，用于获取评价结果最小值的所述轨迹点对应所述目标车辆的运动数据。
行驶轨迹拟合单元620，用于利用第二预设方程，根据运动数据获取单元610获取的轨迹点坐标、轨迹点对应所述目标车辆的航向角、本车位置坐标和本车航向角，确定所述本车的行驶轨迹。
进一步的，如图9所示，无车道线下确定跟踪轨迹的装置还包括轨迹切换模块70，轨迹切换模块70包括：
切换判断单元710，用于在预设行驶周期内，判断所述本车是否到达所述评价结果最小值对应所述轨迹点；
轨迹切换单元720，用于在切换判断单元710判断本车到达评价结果最小值对应所述轨迹点，控制本车跟随所述跟踪轨迹行驶；
二次判断单元730，用于在切换判断单元710判断本车未到达评价结果最小值对应所述轨迹点，控制本车继续按照所述行驶轨迹行驶，并在下一个预设行驶周期内，再次判断所述本车是否到达所述评价结果最小值对应所述轨迹点。
在上述实施例中，对各个实施例的描述都各有侧重，某个实施例中没有详述的部分，可以参见其他实施例的相关描述。
可以理解的是，上述方法及装置中的相关特征可以相互参考。另外，上述实施例中的“第一”、“第二”等是用于区分各实施例，而并不代表各实施例的优劣。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再一一赘述。
在此提供的算法和显示不与任何特定计算机、虚拟系统或者其它设备固有相关。各种通用系统也可以与基于在此的示教一起使用。根据上面的描述，构造这类系统所要求的结构是显而易见的。此外，本发明也不针对任何特定编程语言。应当明白，可以利用各种编程语言实现在此描述的本发明的内容，并且上面对特定语言所做的描述是为了披露本发明的最佳实施方式。
此外，存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)，存储器包括至少一个存储芯片。
本领域内的技术人员应明白，本发明的实施例可提供为方法、系统、或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本发明是参照根据本发明实施例的方法、设备(系统)、和计算机程序 产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
在一个典型的配置中，计算设备包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
存储器可能包括计算机可读介质中的非永久性存储器，随机存取存储器(RAM)和/或非易失性内存等形式，如只读存储器(ROM)或闪存(flash RAM)。存储器是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括，但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器
(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可 擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带，磁带磁磁盘存储或其他磁性存储设备或任何其他非传输介质，可用于存储可以被计算设备访问的信息。按照本文中的界定，计算机可读介质不包括暂存电脑可读媒体(transitory media)，如调制的数据信号和载波。
还需要说明的是，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、商品或者设备不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、商品或者设备所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括要素的过程、方法、商品或者设备中还存在另外的相同要素。
本领域技术人员应明白，本发明的实施例可提供为方法、系统或计算机程序产品。因此，本发明可采用完全硬件实施例、完全软件实施例或结合软件和硬件方面的实施例的形式。而且，本发明可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
以上仅为本发明的实施例而已，并不用于限制本发明。对于本领域技术人员来说，本发明可以有各种更改和变化。凡在本发明的精神和原理之内所作的任何修改、等同替换、改进等，均应包含在本发明的权利要求范围之内。

Claims (10)

  1. 一种无车道线下确定跟踪轨迹的方法，其特征在于，所述方法包括：
    获取至少一个目标车辆的运动轨迹；
    基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数，其中，所述运动参数包括位置坐标和运动数据；
    利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果，其中，所述评价结果用于表示所述本车到达所述轨迹点的困难程度；
    在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹。
  2. 根据权利要求1所述的方法，其特征在于，所述获取至少一个目标车辆的运动轨迹，包括：
    获取运动车辆的位置坐标；
    根据本车运动轨迹，利用所述运动车辆的位置坐标，确定所述运动车辆与所述本车运动轨迹的最近点；
    根据所述运动车辆的位置坐标，计算所述运动车辆与所述最近点的距离；
    在所述距离小于预设距离时，将所述运动车辆确定为所述目标车辆，并获取所述目标车辆的运动轨迹。
  3. 根据权利要求1所述的方法，其特征在于，在基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数之后，所述方法还包括：
    根据所述本车当前时刻的位置坐标，判断各所述运动轨迹的轨迹点纵坐标是否小于0；
    若是，则删除对应的所述轨迹点；
    若否，则保留对应的所述轨迹点。
  4. 根据权利要求1所述的方法，其特征在于，所述利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果，包括：
    根据第一评价参数和第一评价系数，确定第一评价值，其中，所述第一评价参数为轨迹点横坐标与本车位置横坐标差值的平方；
    根据第二评价参数和第二评价系数，确定第二评价值，其中，所述第二评价参数为轨迹点纵坐标与本车位置纵坐标差值的平方；
    根据第三评价参数和第三评价系数，确定第三评价值，其中，所述第三评价参数为轨迹点对应目标车辆航向角与本车航向角差值的平方；
    根据第四评价参数和第四评价系数，确定第四评价值，其中，所述第四评价参数为轨迹点对应目标车辆速度与本车速度差值的平方；
    根据所述第一评价值、所述第二评价值、所述第三评价值和所述第四评价值的和，得到各所述轨迹点的所述评价结果。
  5. 根据权利要求1所述的方法，其特征在于，所述在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹，包括：
    获取各所述评价结果中的最小值；
    确定评价结果最小值对应所述轨迹点所在的所述运动轨迹，并将该所述运动轨迹确定为所述本车的跟踪轨迹。
  6. 根据权利要求1所述的方法，其特征在于，在所述在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹之后，所述方法还包括：
    获取评价结果最小值的所述轨迹点对应所述目标车辆的运动数据；
    利用第二预设方程，根据轨迹点坐标、轨迹点对应所述目标车辆的航向角、本车位置坐标和本车航向角，确定所述本车的行驶轨迹，其中，所述行驶轨迹为所述本车向所述评价结果最小值对应所述轨迹点的行驶路线。
  7. 根据权利要求6所述的方法，其特征在于，在所述确定所述本车的行驶轨迹之后，所述方法还包括：
    在预设行驶周期内，判断所述本车是否到达所述评价结果最小值对应所述轨迹点；
    若是，则所述本车跟随所述跟踪轨迹行驶；
    若否，则所述本车继续按照所述行驶轨迹行驶，并在下一个预设行驶周期内，再次判断所述本车是否到达所述评价结果最小值对应所述轨迹点。
  8. 一种无车道线下确定跟踪轨迹的装置，其特征在于，所述装置包括：
    运动轨迹获取模块，用于获取至少一个目标车辆的运动轨迹；
    运动参数确定模块，用于基于本车位置坐标，确定每个所述运动轨迹的轨迹点对应所述目标车辆的运动参数；
    评价结果计算模块，用于利用第一预设方程，根据各所述轨迹点对应所述目标车辆的运动参数和本车的运动参数，得到各所述轨迹点的评价结果；
    跟踪轨迹选择模块，用于在各所述评价结果中选择一个所述评价结果，并将选择的所述评价结果所在的所述运动轨迹，确定为所述本车的跟踪轨迹。
  9. 一种终端，其特征在于，所述终端用于运行程序，其中，所述终端运行时执行权利要求1-7中任意一项所述的无车道线下确定跟踪轨迹的方法。
  10. 一种存储介质，其特征在于，所述存储介质用于存储计算机程序，其中，所述计算机程序运行时控制所述存储介质所在设备执行权利要求1-7中任意一项所述的无车道线下确定跟踪轨迹的方法。
PCT/CN2022/137888 2022-06-08 2022-12-09 一种无车道线下确定跟踪轨迹的方法及装置 WO2023236476A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210642328.8 2022-06-08
CN202210642328.8A CN115042787B (zh) 2022-06-08 2022-06-08 一种无车道线下确定跟踪轨迹的方法及装置

Publications (1)

Publication Number Publication Date
WO2023236476A1 true WO2023236476A1 (zh) 2023-12-14

Family

ID=83162140

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/137888 WO2023236476A1 (zh) 2022-06-08 2022-12-09 一种无车道线下确定跟踪轨迹的方法及装置

Country Status (2)

Country Link
CN (1) CN115042787B (zh)
WO (1) WO2023236476A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115042787B (zh) * 2022-06-08 2024-06-04 合众新能源汽车股份有限公司 一种无车道线下确定跟踪轨迹的方法及装置

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108919802A (zh) * 2018-07-04 2018-11-30 百度在线网络技术（北京）有限公司 无人驾驶的车辆行驶和装置
CN110435654A (zh) * 2019-07-11 2019-11-12 浙江吉利汽车研究院有限公司 一种用于智能领航系统的跟车方法、装置和设备
CN111762183A (zh) * 2019-03-27 2020-10-13 本田技研工业株式会社 车辆控制装置、车辆和车辆控制方法
DE102019217212B3 (de) * 2019-11-07 2021-05-12 Zf Friedrichshafen Ag Verfahren und Steuereinrichtung zur Überwachung eines Fahrzeugzwischenbereichs
CN113353078A (zh) * 2021-06-24 2021-09-07 中汽创智科技有限公司 一种无车道线自动跟车轨迹确定方法及装置
CN113771829A (zh) * 2020-12-15 2021-12-10 北京京东乾石科技有限公司 用于自动驾驶车辆的控制方法和装置
CN115042787A (zh) * 2022-06-08 2022-09-13 合众新能源汽车有限公司 一种无车道线下确定跟踪轨迹的方法及装置

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6294924B2 (ja) * 2016-09-05 2018-03-14 株式会社Ｓｕｂａｒｕ 車両の走行制御装置
US10703365B1 (en) * 2018-12-26 2020-07-07 Automotive Research & Testing Center Lane tracking method and lane tracking system for an autonomous vehicle
CN111752254A (zh) * 2019-03-28 2020-10-09 深圳市商汤科技有限公司 轨迹跟踪控制器的测试方法、装置、介质及设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108919802A (zh) * 2018-07-04 2018-11-30 百度在线网络技术（北京）有限公司 无人驾驶的车辆行驶和装置
CN111762183A (zh) * 2019-03-27 2020-10-13 本田技研工业株式会社 车辆控制装置、车辆和车辆控制方法
CN110435654A (zh) * 2019-07-11 2019-11-12 浙江吉利汽车研究院有限公司 一种用于智能领航系统的跟车方法、装置和设备
DE102019217212B3 (de) * 2019-11-07 2021-05-12 Zf Friedrichshafen Ag Verfahren und Steuereinrichtung zur Überwachung eines Fahrzeugzwischenbereichs
CN113771829A (zh) * 2020-12-15 2021-12-10 北京京东乾石科技有限公司 用于自动驾驶车辆的控制方法和装置
CN113353078A (zh) * 2021-06-24 2021-09-07 中汽创智科技有限公司 一种无车道线自动跟车轨迹确定方法及装置
CN115042787A (zh) * 2022-06-08 2022-09-13 合众新能源汽车有限公司 一种无车道线下确定跟踪轨迹的方法及装置

Also Published As

Publication number Publication date
CN115042787A (zh) 2022-09-13
CN115042787B (zh) 2024-06-04

Similar Documents

Publication Publication Date Title
CN112099493B (zh) 一种自主移动机器人轨迹规划方法、系统及设备
CN110260867B (zh) 一种机器人导航中位姿确定、纠正的方法、设备及装置
CN108609014B (zh) 智能车辆的横向控制方法及装置
CN111830979B (zh) 一种轨迹优化方法和装置
US11377119B2 (en) Drifting correction between planning stage and controlling stage of operating autonomous driving vehicles
CN112020014B (zh) 一种换道轨迹规划方法、装置、服务器及存储介质
US20230077347A1 (en) Vehicle behavior prediction method and apparatus, electronic device, and storage medium
JP6910973B2 (ja) 車両制御装置及びその制御方法並びに車両制御システム
WO2022056770A1 (zh) 一种路径规划方法和路径规划装置
CN113204236A (zh) 一种智能体路径跟踪控制方法
US20210362741A1 (en) Method for constructing driving coordinate system, and application thereof
WO2022095023A1 (zh) 一种交通流信息的确定方法、装置、电子设备和存储介质
WO2023236476A1 (zh) 一种无车道线下确定跟踪轨迹的方法及装置
CN110789530B (zh) 一种四轮独立转向-独立驱动车辆轨迹跟踪方法和系统
CN116520847A (zh) 路径规划方法、装置、移动机器人、电子设备及存储介质
CN110094498B (zh) 一种轮速比的获取方法及装置
CN111951552B (zh) 一种自动驾驶中风险管理的方法以及相关装置
CN117250957A (zh) 路径跟踪控制关键参考点选取方法、装置、设备和介质
CN115097826A (zh) 一种车辆掉头轨迹规划方法及装置
CN115366872A (zh) 车辆转向避障方法、设备和存储介质
CN111413982A (zh) 一种规划多辆车的循迹路线的方法及终端
JP6717132B2 (ja) 車両走行制御方法及び車両走行制御装置
CN114407883B (zh) 障碍物方向角的融合方法及系统
CN114506343B (zh) 轨迹规划方法、装置、设备、存储介质及自动驾驶车辆
WO2022217819A1 (zh) 目标速度估计方法、装置以及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22945604

Country of ref document: EP

Kind code of ref document: A1