Simulation evaluation method and device for vehicle trajectory planning

Abstract

This application relates to a simulation evaluation method and apparatus for vehicle trajectory planning. The method includes: acquiring planning data required for simulation; matching the vehicle's current position with the optimal trajectory of the previous cycle to determine the planning starting point; using the road centerline as a reference line according to the lateral and longitudinal lane change boundary requirements; scattering points according to the lane change process length based on speed to obtain multiple sets of local planned trajectories; replanning at preset intervals; calculating and obtaining the total trajectory cost of each trajectory; selecting the trajectory with the minimum total trajectory cost as the optimal local path; and comparing the optimal curve obtained by fitting the position points based on the optimal situation path throughout the process with the vehicle position during actual tracking to obtain the evaluation result. This solves the technical problem in related technologies where, during dynamic planning, evaluation using static safety boundaries only yields a rough planned trajectory, resulting in low accuracy of the evaluation results.

Description

Technical Field

[0001] This application relates to the field of motion planning technology, and in particular to a simulation evaluation method and device for vehicle trajectory planning. Background Technology

[0002] Motion planning strategies initially developed with the application of mobile robots. Motion planning is considered crucial for robot navigation, providing global and local trajectory planning to describe robot behavior while considering the robot's dynamics and kinematics from its initial position to its final position. The difference between vehicles and robots lies in the fact that vehicles must consider road conditions and traffic rules. Lane changing and overtaking are common driving operations for drivers, and autonomous vehicles frequently encounter these situations during operation. During driving, vehicles must adjust accordingly based on the relative speeds and distances between vehicles and changes in the surrounding environment to fulfill driving requirements. In this process, vehicles must accurately assess the passability of safe lane changes and overtaking to ensure safe operation. Therefore, trajectory planning for autonomous vehicles is a vital component of ensuring safe driving.

[0003] In the current stage of trajectory planning, there are relatively few methods for quantitative evaluation of trajectory planning. Among related technologies, control points and vehicle safety and convenience points can be used to determine the curve shape, and control points can be selected as variables to obtain the optimal trajectory. Evaluation can be carried out by comparing the trajectory points in the entire planning and tracking process with the optimal trajectory.

[0004] However, the relevant technology is a dynamic programming process, and the state variables will change continuously with reprogramming. The dynamic reprogramming process, evaluated by a static safety boundary, can often only obtain a rough planned trajectory, resulting in low accuracy in trajectory planning evaluation, which needs to be improved. Summary of the Invention

[0005] This application provides a simulation evaluation method and apparatus for vehicle trajectory planning, in order to solve the technical problem in related technologies that, in the process of dynamic planning, evaluation through static safety boundaries can only obtain a rough planned trajectory, and the accuracy of the evaluation results is low.

[0006] The first aspect of this application provides a simulation evaluation method for vehicle trajectory planning, comprising the following steps: acquiring planning data required for simulation; based on the planning data, matching the vehicle's current position with the optimal trajectory of the previous cycle to determine the planning starting point, and according to the requirements of lateral and longitudinal lane change boundaries, using the road centerline as a reference line, selecting the lane change process length according to speed to scatter points, obtaining multiple sets of local planning trajectories, and replanning at preset intervals; and calculating the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each trajectory to obtain the total trajectory cost of each trajectory, taking the trajectory with the minimum total trajectory cost as the optimal local path, and comparing the optimal curve obtained by fitting the position points based on the optimal situation path throughout the entire process with the vehicle position during the actual tracking process to obtain the evaluation result.

[0007] Optionally, in one embodiment of this application, the planning data includes at least one of the following: the vehicle's position during lane changing, the lane centerline trajectory point, the position of obstacle vehicles, vehicle size, and safe distance.

[0008] Optionally, in one embodiment of this application, after obtaining the planning data required for the simulation, the method further includes: performing difference processing on the trajectory points of the lane centerline so that the processed uniform difference ensures that the interval between the two points meets the preset distance.

[0009] Optionally, in one embodiment of this application, the formula for calculating the collision cost is:

[0010]

[0011] The formula for calculating the transition cost is as follows:

[0012] r3=f((x t ,y t ),(x t-1 ,y t-1 ))=(y t -y t-1 )d,

[0013] The formula for calculating the maximum lateral acceleration cost is as follows:

[0014] r4=f(κ=v 2 / r,

[0015] Where r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost, and x t y t Let x be the coordinates of the point on the local planning trajectory at time t. c y c Let d be the location of the obstacle. cTo plan the lateral distance between the trajectory and the obstacle, l c To plan the longitudinal distance between the trajectory and the obstacle, x t-1 y t-1 Let t-1 be the coordinates of the position point on the planned trajectory, r be the radius of curvature, v be the velocity, and d be the trajectory density.

[0016] Optionally, in one embodiment of this application, the comparison of the optimal curve obtained by fitting the position points based on the optimal situation path throughout the entire process with the vehicle position during the actual tracking process to obtain the evaluation result includes: obtaining the index range of longitudinal deviation and / or curvature based on multiple reference values ​​obtained from collision cost and maximum lateral acceleration cost; and obtaining the result of evaluating whether the lane change meets the requirements by comparing whether the error between the intermediate position reference value of the multiple reference values ​​and the actual value of the real vehicle meets the index range.

[0017] A second aspect of this application provides a simulation evaluation device for vehicle trajectory planning, comprising: an acquisition module for acquiring planning data required for simulation; a replanning module for matching the vehicle's current position with the optimal trajectory of the previous cycle based on the planning data, determining the planning starting point, and, according to the lateral and longitudinal lane change boundary requirements, using the road centerline as a reference line, selecting the lane change process length according to speed to scatter points, obtaining multiple sets of local planning trajectories, and replanning at preset intervals; and an evaluation module for calculating the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each trajectory to obtain the total trajectory cost of each trajectory, selecting the trajectory with the minimum total trajectory cost as the optimal local path, and comparing the optimal curve obtained by fitting the position points based on the optimal situation path throughout the entire process with the vehicle position during the actual tracking process to obtain the evaluation result.

[0018] Optionally, in one embodiment of this application, the planning data includes at least one of the following: the vehicle's position during lane changing, the lane centerline trajectory point, the position of obstacle vehicles, vehicle size, and safe distance.

[0019] Optionally, in one embodiment of this application, it further includes: a processing module, used to perform difference processing on the trajectory points of the lane centerline, so that the processed uniform difference ensures that the interval between the two points meets the preset distance.

[0020] Optionally, in one embodiment of this application, the formula for calculating the collision cost is:

[0021]

[0022] The formula for calculating the transition cost is as follows:

[0023] r3=f((x t ,yt ),(x t-1 ,y t-1 ))=(y t -y t-1 )d,

[0024] The formula for calculating the maximum lateral acceleration cost is as follows:

[0025] r4=f(κ=v 2 / r,

[0026] Where r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost, and x t y t Let x be the coordinates of the point on the local planning trajectory at time t. c y c Let d be the location of the obstacle. c To plan the lateral distance between the trajectory and the obstacle, l c To plan the longitudinal distance between the trajectory and the obstacle, x t-1 y t-1 Let t-1 be the coordinates of the position point on the planned trajectory, r be the radius of curvature, v be the velocity, and d be the trajectory density.

[0027] Optionally, in one embodiment of this application, the evaluation module includes: a calculation unit, used to obtain the index range of longitudinal deviation and / or curvature based on multiple reference values ​​obtained from the collision cost and the maximum lateral acceleration cost; and an evaluation unit, used to obtain a result evaluating whether the lane change meets the requirements by comparing whether the error between the intermediate reference value of the multiple reference values ​​and the actual value of the real vehicle meets the index range.

[0028] A third aspect of this application provides a vehicle, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the vehicle trajectory planning simulation evaluation method as described in the above embodiments.

[0029] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described simulation and evaluation method for vehicle trajectory planning.

[0030] This application's embodiments can, based on planning data, employ a dynamic point-spreading planning method, replanning at certain periods, and selecting the optimal local path by adding costs. By comparing the optimal curve obtained from fitting the position points of the optimal path throughout the entire process with the actual vehicle position during tracking, the evaluation results are obtained. This effectively improves the theoretical accuracy of the evaluation and the speed of functional implementation. Therefore, it solves the technical problem in related technologies where, during dynamic planning, evaluation using static safety boundaries only yields a rough planned trajectory, resulting in low accuracy of the evaluation results.

[0031] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0032] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0033] Figure 1 This is a flowchart of a simulation evaluation method for vehicle trajectory planning provided according to an embodiment of this application;

[0034] Figure 2 This is a schematic diagram of the lane coordinate system for a simulation evaluation method of vehicle trajectory planning according to an embodiment of this application;

[0035] Figure 3 This is a schematic diagram of a local path scattering for a simulation evaluation method for vehicle trajectory planning according to an embodiment of this application;

[0036] Figure 4 A schematic diagram showing the lane change model and curvature calculation and display of a simulation evaluation method for vehicle trajectory planning according to an embodiment of this application;

[0037] Figure 5 This is a schematic diagram comparing the optimal trajectories of a simulation evaluation method for vehicle trajectory planning according to an embodiment of this application.

[0038] Figure 6 This is a flowchart of a simulation evaluation method for vehicle trajectory planning according to an embodiment of this application;

[0039] Figure 7 This is a schematic diagram of the structure of a vehicle trajectory planning simulation and evaluation device provided according to an embodiment of this application;

[0040] Figure 8 This is a structural schematic diagram of a vehicle provided according to an embodiment of this application. Detailed Implementation

[0041] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0042] The simulation evaluation method and apparatus for vehicle trajectory planning according to embodiments of this application are described below with reference to the accompanying drawings. Addressing the technical problem mentioned in the background section of the related technologies, where evaluation using static safety boundaries during dynamic planning only yields a rough planned trajectory and the evaluation results have low accuracy, this application provides a simulation evaluation method for vehicle trajectory planning. In this method, based on planning data, a dynamic point-spreading planning method is used to replan at certain periods. The optimal local path is selected by adding costs, and the optimal curve obtained by fitting the position points based on the optimal path throughout the process is compared with the vehicle position during actual tracking to obtain the evaluation results. This effectively improves the theoretical accuracy of the evaluation and the speed of functional implementation. Therefore, it solves the technical problem in the related technologies where evaluation using static safety boundaries during dynamic planning only yields a rough planned trajectory and the evaluation results have low accuracy.

[0043] Specifically, Figure 1 This is a flowchart illustrating a simulation evaluation method for vehicle trajectory planning provided in an embodiment of this application.

[0044] like Figure 1 As shown, the simulation evaluation method for vehicle trajectory planning includes the following steps:

[0045] In step S101, the planning data required for simulation is obtained.

[0046] In actual implementation, the embodiments of this application can obtain the planning data required for simulation, including perception messages and vehicle information.

[0047] Optionally, in one embodiment of this application, the planning data includes at least one of the following during lane changing: the vehicle's position, the lane centerline trajectory point, the position of the obstacle vehicle, the vehicle size, and the safety distance.

[0048] Specifically, such as Figure 2 As shown in the embodiment of this application, the planning data required for simulation can be obtained, and a corresponding lane coordinate system can be established. The planning data required for simulation may include the vehicle's x and y positions during lane changing, the lane centerline trajectory point, and the obstacle vehicle's x position. c y c Vehicle dimensions l c w, safe distance s, etc.

[0049] Optionally, in one embodiment of this application, after obtaining the planning data required for simulation, the method further includes: performing difference processing on the trajectory points of the lane centerline so that the uniform difference after processing ensures that the interval between the two points meets the preset distance.

[0050] As one possible implementation method, after obtaining the planning data required for simulation, the obtained lane center trajectory points can be processed by difference. The uniform difference ensures that the interval between the two points meets the preset distance, such as the interval between the two points < 0.5m, which facilitates the subsequent dynamic point placement.

[0051] It should be noted that the preset distance can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0052] In step S102, based on the planning data, the current position of the vehicle is matched with the optimal trajectory of the previous cycle to determine the planning starting point. According to the requirements of the lateral and longitudinal lane change boundaries, the road centerline is used as the reference line. The lane change process length is selected according to the speed to scatter points, resulting in multiple sets of local planning trajectories. Replanning is performed every preset time interval.

[0053] In some embodiments, the present application can determine the planning starting point by matching the vehicle's current location with the optimal trajectory of the previous cycle based on planning data.

[0054] In related technologies, the point closest to the optimal trajectory of the previous cycle can be selected as the starting point for the planning of this cycle to ensure the smoothness of the overall lane change planning. However, in actual testing, due to the delay in planning, control and the response of the underlying vehicles, selecting the closest point often leads to a lag in the lane change process, an overly smooth lane change trajectory, and a long distance required for the lane change process. Therefore, the embodiments of this application can select the target point by pre-aiming based on the speed on the basis of the closest point, which can ensure both smoothness and safe and fast lane change.

[0055] The formula for selecting the aiming distance can be:

[0056] l = kv + d,

[0057] Where d is the aiming distance when stationary, which can be selected from the vehicle length, v is the current vehicle speed, and k is the speed factor.

[0058] Furthermore, when performing dynamic point distribution, such as Figure 3 As shown, in this embodiment of the application, the road centerline can be used as a reference line according to the requirements of the horizontal and vertical lane change boundaries. The lane change process length is selected according to the speed and points are scattered to obtain multiple sets of local planning trajectories. The replanning is performed every preset time interval.

[0059] The specific implementation can be as follows: (e.g.) Figure 4 As shown, calculate the longitudinal interval dis for each local path, where m is the number of local paths and d is the sampling longitudinal interval.

[0060] for(int i = 0; i <m+1;i++)

[0061] {

[0062] dis = d * (im / 2);

[0063] }

[0064] The position of the corresponding point for each local path is calculated based on the position of the center line point of the lane. Here, p is the position of the corresponding point. Different local paths correspond to a series of different trajectory points p as the loop progresses. These trajectory points are stored to obtain the x and y coordinates of the trajectory points corresponding to the local trajectory. n is the number of center line trajectory points. Center is the position of the center line, including the coordinates x, y and the heading angle α.

[0065] The calculation formula can be as follows:

[0066] for(int j = 0; i <n+1;j++)

[0067] {

[0068] px=Center.at(j).x-dis*cos(Center.at(j).a+M_PI_2);

[0069] py=Center.at(j).y-dis*sin(Center.at(j).a+M_PI_2);

[0070] }

[0071] The embodiments of this application can obtain multiple sets of local planning trajectories through the above steps, plan according to a preset time, update the planning starting point, and iterate the planning to obtain the entire dynamic planning process.

[0072] It should be noted that the preset duration can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0073] In step S103, the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each trajectory are calculated to obtain the total trajectory cost of each trajectory. The trajectory with the minimum total trajectory cost is taken as the optimal local path. The optimal curve obtained by fitting the position points based on the optimal situation path throughout the entire process is compared with the vehicle position during the actual tracking process to obtain the evaluation result.

[0074] In actual implementation, the embodiments of this application can calculate the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampled trajectory to obtain the total trajectory cost of each sampled trajectory. The sampled trajectory with the minimum trajectory cost is then selected as the optimal local path, and so on. Figure 5 As shown, by comparing the optimal trajectory throughout the process with the actual vehicle position during tracking, the evaluation results are obtained, and it is determined whether the deviation range meets the requirements. Since the starting point of the planning is selected on the optimal trajectory of the previous frame, the impact of tracking control on planning can be reduced when evaluating the overall lane change, and the planning module can be evaluated more accurately.

[0075] Optionally, in one embodiment of this application, the formula for calculating the collision cost is:

[0076]

[0077] The formula for calculating transition costs is:

[0078] r3=f((x t ,y t ),(x t-1 ,y t-1 ))=(y t -y t-1 )d,

[0079] The formula for calculating the maximum lateral acceleration cost is:

[0080] r4=f(k=v 2 / r,

[0081] Where r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost, and x t y t Let x be the coordinates of the point on the local planning trajectory at time t. c y c Let d be the location of the obstacle. c To plan the lateral distance between the trajectory and the obstacle, l c To plan the longitudinal distance between the trajectory and the obstacle, x t-1 y t-1 Let t-1 be the coordinates of the position point on the planned trajectory, r be the radius of curvature, v be the velocity, and d be the trajectory density.

[0082] The formula for calculating the collision cost is as follows:

[0083]

[0084] The formula for calculating transition costs is:

[0085] r3=f((x t ,yt ),(x t-1 ,y t-1 ))=(y t -y t-1 )d,

[0086] The formula for calculating the maximum lateral acceleration cost is:

[0087] r4=f(κ=v 2 / r,

[0088] Where r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost, and x t y t Let x be the coordinates of the point on the local planning trajectory at time t. c y c Let d be the location of the obstacle. c To plan the lateral distance between the trajectory and the obstacle, l c To plan the longitudinal distance between the trajectory and the obstacle, x t-1 y t-1 Let t-1 be the coordinates of the position point on the planned trajectory, r be the radius of curvature, v be the velocity, and d be the trajectory density.

[0089] The formula for calculating the total cost is:

[0090] Total trajectory cost = t1*r1 + t2*r2 + t3*r3 + t4*r4

[0091] Wherein, t1 is the weight coefficient of priority cost, t2 is the weight coefficient of collision cost, t3 is the weight coefficient of transition cost, and t4 is the weight coefficient of maximum lateral acceleration cost. In this embodiment, the sampling trajectory with the minimum total trajectory cost among each sampling trajectory can be selected as the optimal local path. Since the choice of cost is not fixed, this embodiment can add different costs for evaluation according to different evaluation scenarios.

[0092] Optionally, in one embodiment of this application, the evaluation result is obtained by comparing the optimal curve obtained by fitting the position point based on the optimal situation path throughout the process with the vehicle position during the actual tracking process. This includes: obtaining the index range of longitudinal deviation and / or curvature based on multiple reference values ​​obtained from collision cost and maximum lateral acceleration cost; and obtaining the result of evaluating whether the lane change meets the requirements by comparing whether the error between the intermediate position reference value of multiple reference values ​​and the actual value of the real vehicle meets the index range.

[0093] For example, in this embodiment of the application, a fixed period dt = 20ms can be set for dynamic planning, and the information of the current position point during the lane change process can be accumulated and saved, so as to obtain the reference value of the entire lane change trajectory, and compare the reference value with the actual value for evaluation.

[0094] The evaluation criteria can be divided into two indicators: longitudinal deviation and curvature. According to the method in the above steps, by adjusting the values ​​of collision cost t2 and maximum lateral acceleration t4, a series of reference values ​​are obtained, and the range of indicators is obtained based on these reference values. By comparing the error between the reference value at the middle position and the actual value of the real vehicle, it is determined whether the lane change meets the requirements.

[0095] Combination Figures 2 to 6 As shown, the working principle of the vehicle trajectory planning simulation evaluation method of this application embodiment is explained in detail with an example.

[0096] like Figure 6 As shown, embodiments of this application may include the following steps:

[0097] S601: Obtain the planning data required for simulation. In actual execution, this embodiment of the application can obtain the planning data required for simulation, including perception messages and vehicle information.

[0098] Specifically, such as Figure 2 As shown in the embodiment of this application, the planning data required for simulation can be obtained, and a corresponding lane coordinate system can be established. The planning data required for simulation may include the vehicle's x and y positions during lane changing, the lane centerline trajectory point, and the obstacle vehicle's x position. c y c Vehicle dimensions l c w, safe distance s, etc.

[0099] As one possible implementation method, after obtaining the planning data required for simulation, the obtained lane center trajectory points can be processed by difference. The uniform difference ensures that the interval between the two points meets the preset distance, such as the interval between the two points < 0.5m, which facilitates the subsequent dynamic point placement.

[0100] It should be noted that the preset distance can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0101] S602: Select the planning starting point. In some embodiments, the planning starting point can be determined based on planning data by matching the vehicle's current position with the optimal trajectory of the previous cycle.

[0102] The embodiments of this application can select target points based on speed pre-aiming on the basis of the nearest point, which can ensure both smoothness and safe and fast lane changes.

[0103] The formula for selecting the aiming distance can be:

[0104] l = kv + d,

[0105] Where d is the aiming distance when stationary, which can be selected from the vehicle length, v is the current vehicle speed, and k is the speed factor.

[0106] S603: Dynamic point allocation. When performing dynamic point allocation, such as... Figure 3 As shown, in this embodiment of the application, the road centerline can be used as a reference line according to the requirements of the horizontal and vertical lane change boundaries. The lane change process length is selected according to the speed and points are scattered to obtain multiple sets of local planning trajectories. The replanning is performed every preset time interval.

[0107] The specific implementation can be as follows: (e.g.) Figure 4 As shown, calculate the longitudinal interval dis for each local path, where m is the number of local paths and d is the sampling longitudinal interval.

[0108] for(int i = 0; i <m+1;i++)

[0109] {

[0110] dis = d * (im / 2);

[0111] }

[0112] The position of the corresponding point for each local path is calculated based on the position of the center line point of the lane. Here, p is the position of the corresponding point. Different local paths correspond to a series of different trajectory points p as the loop progresses. These trajectory points are stored to obtain the x and y coordinates of the trajectory points corresponding to the local trajectory. n is the number of center line trajectory points. Center is the position of the center line, including the coordinates x, y and the heading angle α.

[0113] The calculation formula can be as follows:

[0114] for(int j = 0; i <n+1;j++)

[0115] {

[0116] px=Center.at(j).x-dis*cos(Center.at(j).a+M_PI_2);

[0117] py=Center.at(j).y-dis*sin(Center.at(j).a+M_PI_2);

[0118] }

[0119] The embodiments of this application can obtain multiple sets of local planning trajectories through the above steps, plan according to a preset time, update the planning starting point, and iterate the planning to obtain the entire dynamic planning process.

[0120] It should be noted that the preset duration can be set by those skilled in the art according to the actual situation, and no specific restrictions are imposed here.

[0121] S604: Select the optimal trajectory. In actual execution, the embodiments of this application can calculate the priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each sampled trajectory to obtain the total trajectory cost of each sampled trajectory, and select the sampled trajectory with the minimum trajectory cost as the optimal local path.

[0122] The formula for calculating the collision cost is as follows:

[0123]

[0124] The formula for calculating transition costs is:

[0125] r3=f((x t ,y t ),(x t-1 ,y t-1 ))=(y t -y t-1 )d,

[0126] The formula for calculating the maximum lateral acceleration cost is:

[0127] r4=f(κ=v 2 / r,

[0128] Where r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost, and x t y t Let x be the coordinates of the point on the local planning trajectory at time t. c y c Let d be the location of the obstacle. c To plan the lateral distance between the trajectory and the obstacle, l c To plan the longitudinal distance between the trajectory and the obstacle, x t-1 y t-1 Let t-1 be the coordinates of the position point on the planned trajectory, r be the radius of curvature, v be the velocity, and d be the trajectory density.

[0129] The formula for calculating the total cost is:

[0130] Total trajectory cost = t1*r1 + t2*r2 + t3*r3 + t4*r4

[0131] Wherein, t1 is the weight coefficient of priority cost, t2 is the weight coefficient of collision cost, t3 is the weight coefficient of transition cost, and t4 is the weight coefficient of maximum lateral acceleration cost. In this embodiment, the sampling trajectory with the minimum total trajectory cost among each sampling trajectory can be selected as the optimal local path. Since the choice of cost is not fixed, this embodiment can add different costs for evaluation according to different evaluation scenarios.

[0132] S605: Evaluation. For example... Figure 5 As shown, the embodiments of this application can compare the optimal trajectory of the entire process with the vehicle position during the actual tracking process to obtain the evaluation results and determine whether the deviation range meets the requirements. Since the starting point of the planning is selected on the optimal trajectory of the previous frame, the impact of tracking control on planning can be reduced when evaluating the overall lane change, and the planning module can be evaluated more accurately.

[0133] For example, in this embodiment of the application, a fixed period dt = 20ms can be set for dynamic planning, and the information of the current position point during the lane change process can be accumulated and saved, so as to obtain the reference value of the entire lane change trajectory, and compare the reference value with the actual value for evaluation.

[0134] The evaluation criteria can be divided into two indicators: longitudinal deviation and curvature. According to the method in the above steps, by adjusting the values ​​of collision cost t2 and maximum lateral acceleration t4, a series of reference values ​​are obtained, and the range of indicators is obtained based on these reference values. By comparing the error between the reference value at the middle position and the actual value of the real vehicle, it is determined whether the lane change meets the requirements.

[0135] The simulation evaluation method for vehicle trajectory planning proposed in this application can replan based on planning data using a dynamic point-spreading planning method at certain periods. It selects the optimal local path by adding costs and compares the optimal curve obtained by fitting the position points based on the optimal path with the actual vehicle position during tracking to obtain the evaluation result. This effectively improves the theoretical accuracy of the evaluation and the speed of functional implementation. Therefore, it solves the technical problem in related technologies where, during dynamic planning, evaluation using static safety boundaries only yields a rough planned trajectory, resulting in low accuracy of the evaluation results.

[0136] Next, referring to the accompanying drawings, a simulation and evaluation device for vehicle trajectory planning proposed according to an embodiment of this application is described.

[0137] Figure 7 This is a block diagram of a vehicle trajectory planning simulation and evaluation device according to an embodiment of this application.

[0138] like Figure 7As shown, the vehicle trajectory planning simulation evaluation device 10 includes: an acquisition module 100, a replanning module 200, and an evaluation module 300.

[0139] Specifically, module 100 is used to acquire the planning data required for simulation.

[0140] The replanning module 200 is used to match the vehicle's current position with the optimal trajectory of the previous cycle based on the planning data, determine the planning starting point, and, according to the requirements of the lateral and longitudinal lane change boundaries, use the road centerline as a reference line, select the lane change process length according to speed to scatter points, obtain multiple sets of local planning trajectories, and replan at preset intervals.

[0141] The evaluation module 300 is used to calculate the priority cost, collision cost, transition cost and maximum lateral acceleration cost of each trajectory to obtain the total trajectory cost of each trajectory. The trajectory with the minimum total trajectory cost is taken as the optimal local path. The evaluation result is obtained by comparing the optimal curve obtained by fitting the position points based on the optimal situation path throughout the process with the vehicle position during the actual tracking process.

[0142] Optionally, in one embodiment of this application, the planning data includes at least one of the following during lane changing: the vehicle's position, the lane centerline trajectory point, the position of the obstacle vehicle, the vehicle size, and the safety distance.

[0143] Optionally, in one embodiment of this application, the vehicle trajectory planning simulation evaluation device 10 further includes a processing module.

[0144] The processing module is used to perform difference processing on the trajectory points of the lane centerline so that the uniform difference after processing ensures that the interval between the two points meets the preset distance.

[0145] Optionally, in one embodiment of this application, the formula for calculating the collision cost is:

[0146]

[0147] The formula for calculating transition costs is:

[0148] r3=f((x t ,y t ),(x t-1 ,y t-1 ))=(y t -y t-1 )d,

[0149] The formula for calculating the maximum lateral acceleration cost is:

[0150] r4=f(κ=v 2 / r,

[0151] Where r2 is the collision cost, r3 is the transition cost, r4 is the maximum lateral acceleration cost, and x t y t Let x be the coordinates of the point on the local planning trajectory at time t. c y c Let d be the location of the obstacle. c To plan the lateral distance between the trajectory and the obstacle, l c To plan the longitudinal distance between the trajectory and the obstacle, x t-1 y t-1 Let t-1 be the coordinates of the position point on the planned trajectory, r be the radius of curvature, v be the velocity, and d be the trajectory density.

[0152] Optionally, in one embodiment of this application, the evaluation module 300 includes a calculation unit and an evaluation unit.

[0153] The calculation unit is used to obtain the range of indicators for longitudinal deviation and / or curvature based on multiple reference values ​​obtained from the collision cost and the maximum lateral acceleration cost.

[0154] The evaluation unit is used to determine whether the lane change meets the requirements by comparing the error between the intermediate reference value of multiple reference values ​​and the actual value of the actual vehicle.

[0155] It should be noted that the explanation of the above-mentioned simulation evaluation method for vehicle trajectory planning also applies to the simulation evaluation device for vehicle trajectory planning in this embodiment, and will not be repeated here.

[0156] The vehicle trajectory planning simulation and evaluation device proposed in this application can, based on planning data, replan at certain periods using a dynamic point-scattering planning method, select the optimal local path by adding costs, and compare the optimal curve obtained by fitting the position points based on the optimal path throughout the process with the vehicle position during actual tracking to obtain the evaluation result. This can effectively improve the theoretical accuracy of the evaluation and the speed of functional implementation. Therefore, it solves the technical problem in related technologies where, during dynamic planning, evaluation using static safety boundaries can only obtain a rough planned trajectory, resulting in low accuracy of the evaluation results.

[0157] Figure 8 A schematic diagram of the structure of a vehicle provided in an embodiment of this application. The vehicle may include:

[0158] The memory 801, the processor 802, and the computer program stored on the memory 801 and capable of running on the processor 802.

[0159] When the processor 802 executes the program, it implements the simulation evaluation method for vehicle trajectory planning provided in the above embodiments.

[0160] Furthermore, the vehicle also includes:

[0161] Communication interface 803 is used for communication between memory 801 and processor 802.

[0162] The memory 801 is used to store computer programs that can run on the processor 802.

[0163] The memory 801 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0164] If the memory 801, processor 802, and communication interface 803 are implemented independently, then the communication interface 803, memory 801, and processor 802 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be divided into address buses, data buses, control buses, etc. For ease of representation, Figure 8 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0165] Optionally, in a specific implementation, if the memory 801, processor 802, and communication interface 803 are integrated on a single chip, then the memory 801, processor 802, and communication interface 803 can communicate with each other through an internal interface.

[0166] The processor 802 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0167] This embodiment also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described simulation and evaluation method for vehicle trajectory planning.

[0168] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0169] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0170] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0171] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0172] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0173] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0174] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0175] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A simulation evaluation method for vehicle trajectory planning, characterized in that, Includes the following steps: Obtain the planning data required for simulation; Based on the planning data, the vehicle's current position is matched with the optimal trajectory of the previous cycle to determine the planning starting point. According to the requirements of the lateral and longitudinal lane change boundaries, the road centerline is used as the reference line. The length of the lane change process is selected according to the speed to generate multiple sets of local planning trajectories. The planning is then re-planned every preset time interval. as well as The priority cost, collision cost, transition cost, and maximum lateral acceleration cost of each trajectory are calculated to obtain the total trajectory cost of each trajectory. The trajectory with the minimum total trajectory cost is taken as the optimal local path. The optimal curve obtained by fitting the position points based on the optimal local path throughout the entire process is compared with the vehicle position during the actual tracking process to obtain the evaluation result. The planning data includes at least one of the following during lane changing: the vehicle's position, the lane centerline trajectory point, the position of the obstacle vehicle, the vehicle size, and the safe distance. The formula for calculating the collision cost is as follows: ， The formula for calculating the transition cost is as follows: ， The formula for calculating the maximum lateral acceleration cost is as follows: ， in, As a result of the collision, As a transitional cost, For the cost of maximum lateral acceleration, , for t The coordinates of the location point on the local planning trajectory at each moment. , Location of the obstacle. To plan the lateral distance between the trajectory and the obstacle, To plan the longitudinal distance between the trajectory and the obstacle, , for t- The coordinates of the position point on the planned trajectory at time 1. r Let be the radius of curvature. v For speed, d Trajectory density; The evaluation results are obtained by comparing the optimal curve obtained by fitting the location points based on the optimal local path throughout the entire process with the vehicle position during the actual tracking process, including: Based on multiple reference values ​​obtained from the collision cost and the maximum lateral acceleration cost, the range of indices for longitudinal deviation and / or curvature is obtained; By comparing the error between the intermediate reference value and the actual value of the vehicle with the multiple reference values, we can determine whether the lane change meets the requirements.

2. The method according to claim 1, characterized in that, After obtaining the planning data required for the simulation, the process also includes: The trajectory points of the lane centerline are processed by difference to ensure that the uniform difference after processing ensures that the distance between the two points meets the preset distance.

3. A simulation and evaluation device for vehicle trajectory planning, characterized in that, include: The acquisition module is used to acquire the planning data required for simulation. The replanning module is used to match the vehicle's current position with the optimal trajectory of the previous cycle based on the planning data, determine the planning starting point, and, according to the requirements of the lateral and longitudinal lane change boundaries, use the road centerline as a reference line, select the lane change process length according to speed to scatter points, obtain multiple sets of local planning trajectories, and replan every preset time interval. as well as The evaluation module is used to calculate the priority cost, collision cost, transition cost and maximum lateral acceleration cost of each trajectory to obtain the total trajectory cost of each trajectory. The trajectory with the minimum total trajectory cost is taken as the optimal local path. The evaluation result is obtained by comparing the optimal curve obtained by fitting the position points based on the optimal local path with the vehicle position during the actual tracking process. The planning data includes at least one of the following during lane changing: the vehicle's position, the lane centerline trajectory point, the position of the obstacle vehicle, the vehicle size, and the safe distance. The formula for calculating the collision cost is as follows: ， The formula for calculating the transition cost is as follows: ， The formula for calculating the maximum lateral acceleration cost is as follows: ， in, As a result of the collision, As a transitional cost, For the cost of maximum lateral acceleration, , for t The coordinates of the location point on the local planning trajectory at each moment. , Location of the obstacle. To plan the lateral distance between the trajectory and the obstacle, To plan the longitudinal distance between the trajectory and the obstacle, , for t- The coordinates of the position point on the planned trajectory at time 1. r Let be the radius of curvature. v For speed, d Trajectory density; The evaluation module: The calculation unit is used to obtain the range of indicators for longitudinal deviation and / or curvature based on multiple reference values ​​obtained from the collision cost and the maximum lateral acceleration cost; The evaluation unit is used to determine whether the lane change meets the requirements by comparing the error between the intermediate reference value of the multiple reference values ​​and the actual value of the vehicle.

4. A vehicle, characterized in that, include: A memory, a processor, and a computer program stored in the memory and executable on the processor, the processor executing the program to implement the simulation evaluation method for vehicle trajectory planning as described in any one of claims 1-2.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the simulation evaluation method for vehicle trajectory planning as described in any one of claims 1-2.

Images