Track generation method and device for testing control performance of automatic parking system

Abstract

The application discloses a trajectory generation method and device for testing the control performance of an automatic parking system, and the method comprises the following steps: acquiring a planning problem description file generated by a first vehicle in an actual parking scene; performing parking trajectory planning according to vehicle parameter information of a second vehicle and the planning problem description file to generate an initial parking planning trajectory; rendering the initial parking planning trajectory in a top-down view in an interactive trajectory adjustment interface, and superimposing environment information currently perceived by the second vehicle on the initial parking planning trajectory in a case where the current pose information of the second vehicle coincides with the pose information of a starting point in the initial parking planning trajectory; and in a case where there are non-drivable trajectory points in the initial parking planning trajectory after the environment information is superimposed, obtaining a target parking planning trajectory by receiving an adjustment operation of a user on the initial parking planning trajectory, and all trajectory points in the target parking planning trajectory are located in a drivable area.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and more specifically, to a trajectory generation method and apparatus for testing the control performance of an automatic parking system. Background Technology

[0002] In automated parking systems, to test the controller's performance, it's necessary to repeatedly provide a single input, or different typical inputs, allowing the vehicle to park according to that input, thus testing and evaluating the controller's performance. This input consists of trajectory information, including the parking planning path and speed curve. Conventional methods for this testing require manually constructing the input, and for different vehicles, due to variations in parameters such as turning radius and steering wheel speed, the input needs to be reconstructed based on these parameters. Therefore, improving the efficiency of trajectory generation is a crucial issue that needs to be addressed. Summary of the Invention

[0003] This application provides a trajectory generation method and apparatus for testing the control performance of an automatic parking system, which can solve the problem of low efficiency in manually generating the required input information for testing in the performance testing scenario of an automatic parking system controller.

[0004] The specific technical solution is as follows:

[0005] In a first aspect, embodiments of this application provide a trajectory generation method for testing the control performance of an automatic parking system, the method comprising:

[0006] Obtain a planning problem description file generated by the first vehicle in an actual parking scenario, wherein the planning problem description file includes information required for parking trajectory planning based on the environmental information perceived by the first vehicle;

[0007] Parking trajectory planning is performed based on the vehicle parameter information of the second vehicle and the planning problem description file to generate an initial parking planning trajectory. The second vehicle is a test vehicle used to test the performance of the controller in the automatic parking system, and the second vehicle is located in a road environment used to test the performance of the controller.

[0008] In the interactive trajectory adjustment interface, the initial parking planning trajectory is rendered from a top-down perspective. By overlaying the environmental information currently perceived by the second vehicle with the initial parking planning trajectory when the current pose information of the second vehicle coincides with the pose information of the starting point in the initial parking planning trajectory, the pose information includes position and heading.

[0009] If there are undrivable trajectory points in the initial parking planning trajectory after overlaying environmental information, a target parking planning trajectory is obtained by receiving user adjustment operations on the initial parking planning trajectory, wherein all trajectory points in the target parking planning trajectory are in drivable areas.

[0010] As can be seen from the above scheme, the embodiments of this application can not only automatically generate the initial parking planning trajectory using the vehicle parameter information of the second vehicle (i.e., the test vehicle) and the planning problem description file generated by the first vehicle in the actual parking scenario, without spending a lot of time relying on manual construction, but also overlay the initial parking planning trajectory with the environmental information currently perceived by the second vehicle in the interactive trajectory adjustment interface. Through human-computer interaction, the user can adjust the initial parking planning trajectory so that the final target parking planning trajectory is in the drivable area. This ensures that the target parking planning trajectory used for controller performance testing is in a safe environment, avoiding interference with control performance testing due to unsafe trajectories, thereby improving the safety and accuracy of performance testing.

[0011] In one possible implementation, the adjustment operation includes rotation and / or translation.

[0012] In one possible implementation, when the starting point of the target parking planning trajectory differs from the starting point of the initial parking planning trajectory, after obtaining the target parking planning trajectory and before testing the performance of the controller during parking according to the target parking planning trajectory, the method further includes:

[0013] Based on the current pose information of the second vehicle and the pose information of the starting point of the target parking planning trajectory, trajectory planning is performed on the second vehicle to obtain the target movement trajectory of the second vehicle from the current position to the starting point of the target parking planning trajectory.

[0014] The second vehicle is controlled to travel along the target movement trajectory to the starting point of the target parking planning trajectory, so that the pose information of the second vehicle after movement is the same as the pose information of the starting point of the target parking planning trajectory.

[0015] As can be seen from the above scheme, when the starting point of the target parking planning trajectory is different from the starting point of the initial parking planning trajectory, the embodiments of this application can automatically plan a transitional trajectory (i.e., the target movement trajectory) from the current position of the second vehicle to the starting point of the target parking planning trajectory, so that the second vehicle can smoothly drive to the starting point of the target parking planning trajectory.

[0016] In one possible implementation, before obtaining the target parking planning trajectory by receiving an adjustment operation from the user on the initial parking planning trajectory, the method further includes:

[0017] It distinguishes between drivable and non-drivable trajectory points.

[0018] As can be seen from the above solution, by distinguishing between non-drivable trajectory points and drivable trajectory points, this embodiment of the application is more conducive to users intuitively and quickly adjusting the initial parking planning trajectory, thereby improving the efficiency of obtaining the target parking planning trajectory.

[0019] In one possible implementation, obtaining the target parking planning trajectory by receiving an adjustment operation from the user on the initial parking planning trajectory includes:

[0020] Receive each adjustment operation from the user on the initial parking planning trajectory, and adjust the initial parking planning trajectory accordingly based on the adjustment operation;

[0021] After each adjustment operation is completed, a safety check is performed on the current adjusted initial parking planning trajectory. If the check result indicates that there are undrivable trajectory points, the operation of distinguishing between undrivable and drivable trajectory points is updated until all trajectory points are in the drivable area, at which point the target parking planning trajectory is obtained.

[0022] As can be seen from the above solution, the embodiments of this application can improve the user experience and the efficiency of obtaining the target parking planning trajectory by updating the trajectory point position changes caused by each adjustment operation of the user in real time.

[0023] Secondly, embodiments of this application provide a trajectory generation device for testing the control performance of an automatic parking system, the device comprising:

[0024] The acquisition unit is used to acquire a planning problem description file generated by the first vehicle in an actual parking scenario, wherein the planning problem description file includes information required for parking trajectory planning based on the environmental information perceived by the first vehicle;

[0025] The planning unit is used to plan a parking trajectory based on the vehicle parameter information of the second vehicle and the planning problem description file, and generate an initial parking planning trajectory. The second vehicle is a test vehicle used to test the performance of the controller in the automatic parking system, and the second vehicle is located in a road environment used to test the performance of the controller.

[0026] The output display unit renders the initial parking planning trajectory from a top-down angle in the interactive trajectory adjustment interface, and overlays the environmental information currently perceived by the second vehicle with the initial parking planning trajectory when the current pose information of the second vehicle coincides with the pose information of the starting point in the initial parking planning trajectory. The pose information includes position and heading.

[0027] The adjustment unit is used to obtain a target parking planning trajectory by receiving user adjustment operations on the initial parking planning trajectory when there are undrivable trajectory points in the initial parking planning trajectory after superimposing environmental information. The target parking planning trajectory contains all trajectory points in the drivable area.

[0028] In one possible implementation, the adjustment operation includes rotation and / or translation.

[0029] In one possible implementation, the planning unit is further configured to, when the starting point of the target parking planning trajectory is different from the starting point of the initial parking planning trajectory, after obtaining the target parking planning trajectory and before testing the performance of the controller during parking according to the target parking planning trajectory, perform trajectory planning for the second vehicle based on the current pose information of the second vehicle and the pose information of the starting point of the target parking planning trajectory, to obtain the target movement trajectory of the second vehicle from its current position to the starting point of the target parking planning trajectory;

[0030] The device further includes:

[0031] A control movement unit is used to control the second vehicle to travel to the starting point of the target parking planning trajectory according to the target movement trajectory, so that the pose information of the second vehicle after movement is the same as the pose information of the starting point of the target parking planning trajectory.

[0032] In one possible implementation, the output display unit is further configured to distinguish between drivable and non-drivable trajectory points before obtaining the target parking planning trajectory by receiving the user's adjustment operation on the initial parking planning trajectory.

[0033] In one possible implementation, the adjustment unit includes:

[0034] The receiving module is used to receive each adjustment operation by the user on the initial parking planning trajectory;

[0035] An adjustment module is used to adjust the initial parking planning trajectory accordingly according to the adjustment operation;

[0036] The detection module is used to perform a safety check on the adjusted initial parking planning trajectory after each adjustment operation is completed.

[0037] The output display unit is also used to update the operation of distinguishing between displaying non-drivable trajectory points and drivable trajectory points when the detection result indicates the existence of non-drivable trajectory points, until all trajectory points are in the drivable area, and then obtain the target parking planning trajectory.

[0038] As can be seen from the above scheme, the embodiments of this application can not only automatically generate the initial parking planning trajectory using the vehicle parameter information of the second vehicle (i.e., the test vehicle) and the planning problem description file generated by the first vehicle in the actual parking scenario, without spending a lot of time relying on manual construction, but also overlay the initial parking planning trajectory with the environmental information currently perceived by the second vehicle in the interactive trajectory adjustment interface. Through human-computer interaction, the user can adjust the initial parking planning trajectory so that the final target parking planning trajectory is in the drivable area. This ensures that the target parking planning trajectory used for controller performance testing is in a safe environment, avoiding interference with control performance testing due to unsafe trajectories, thereby improving the safety and accuracy of performance testing.

[0039] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the method as described in any possible implementation of the first aspect.

[0040] Fourthly, embodiments of this application provide an electronic device, which includes:

[0041] One or more processors;

[0042] The processor is coupled to a storage device for storing one or more programs;

[0043] When one or more programs are executed by one or more processors, the electronic device performs the method as described in any possible implementation of the first aspect.

[0044] Fifthly, embodiments of this application provide a vehicle that includes the means as described in any possible implementation of the second aspect, or includes electronic equipment as described in the fourth aspect.

[0045] In a sixth aspect, embodiments of this application provide a computer program product containing instructions that, when executed on a computer or processor, cause the computer or processor to perform the method described in any possible implementation of the first aspect. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0047] Figure 1 A flowchart illustrating a trajectory generation method for testing the control performance of an automatic parking system, provided in an embodiment of this application;

[0048] Figure 2 An example diagram showing the overlay display of an initial parking planning trajectory and environmental information provided in this application embodiment;

[0049] Figure 3 An example diagram comparing the initial parking planning trajectory before and after adjustment, provided as an embodiment of this application;

[0050] Figure 4 An example diagram of a functional module organizational structure provided in an embodiment of this application;

[0051] Figure 5 A block diagram of a trajectory generation device for testing the control performance of an automatic parking system, provided in an embodiment of this application;

[0052] Figure 6 This is a schematic diagram of the structure of an electronic device or computer device provided in an embodiment of this application. Detailed Implementation

[0053] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0054] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The terms "comprising" and "having," and any variations thereof, in the embodiments and drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices.

[0055] To improve the efficiency of generating the input information required for performance testing of automatic parking system controllers, embodiments of this application provide a trajectory generation method for testing the control performance of automatic parking systems, such as... Figure 1 As shown, this method can be applied to electronic devices or computer equipment, specifically to vehicles (specifically, the second vehicle described below) or servers, and the method includes:

[0056] S110: Obtain the planning problem description file generated by the first vehicle in the actual parking scenario.

[0057] The planning problem description document includes the information required for parking trajectory planning generated based on the environmental information perceived by the first vehicle. The perceived environmental information includes parking lines, obstacles, etc., with obstacles including other vehicles and other obstacles besides the vehicle itself. Specifically, the planning problem description document includes the pose information of the first vehicle at the start and end of the automatic parking process, obstacles represented by discrete points, and the bounding box surrounding these elements. This bounding box is generally the smallest rectangle surrounding these elements, or a rectangle slightly enlarged from the smallest rectangle. The pose information includes position and heading, with heading referring to the direction the vehicle is facing.

[0058] The planning problem description file is an exported file from the planning problem description information generated by the planning module in the first vehicle. Specifically, the planning problem description information is generated by the planning problem generator within this planning module, based on the environmental information output from the perception module. The planning module includes a planning problem generator, a trajectory planner, and a speed planner. The first vehicle also includes a controller and a vehicle chassis module.

[0059] The planning problem description information generated by the planning problem generator and the exported planning problem description file contain the same content, only the format is different. The planning problem description information generated by the planning problem generator is sequentially input into the trajectory planner and speed planner to perform parking path planning and speed planning at the location points. After obtaining the parking planned path and speed curve, it is transmitted to the controller and vehicle chassis module to control the first vehicle to park.

[0060] S120: Based on the vehicle parameter information of the second vehicle and the planning problem description file, perform parking trajectory planning and generate an initial parking planning trajectory.

[0061] The second vehicle is a test vehicle used to test the performance of the controller in the automatic parking system. The second vehicle is located in a road environment used for testing the controller performance. The second vehicle can be a real vehicle or a virtual vehicle in a simulation environment. That is, the controller performance test in this embodiment can be a real vehicle test or a simulation test. When the second vehicle is a real vehicle, the first vehicle and the second vehicle can be the same vehicle or different vehicles.

[0062] Vehicle parameter information includes minimum turning radius, vehicle size, steering wheel rotation speed, etc. Since some vehicle parameter information differs between different vehicles, and parking trajectory planning requires combining vehicle parameter information such as minimum turning radius, this embodiment uses the result of parking planning with only the planning problem description file containing the information needed for parking planning and the vehicle parameter information of the second vehicle as the initial parking planning trajectory, instead of directly using the parking planning trajectory generated by the first vehicle in an actual parking scenario as the initial parking planning trajectory.

[0063] When the embodiments of this application are applied to a server, the second vehicle can upload its own vehicle parameter information and the planning problem description file obtained from the first vehicle to the server so that the server can execute the method provided in the embodiments of this application.

[0064] S130: In the interactive trajectory adjustment interface, the initial parking planning trajectory is rendered from a top-down angle, and the environmental information currently perceived by the second vehicle is overlaid on the initial parking planning trajectory when the current pose information of the second vehicle coincides with the pose information of the starting point in the initial parking planning trajectory.

[0065] In the interactive trajectory adjustment interface, only the parking planning path in the initial parking planning trajectory is displayed, that is, the position curve of the trajectory points, while the speed curve can be hidden.

[0066] To facilitate testing the controller's performance, the second vehicle can be placed in a relatively open environment, generally within a radius of 10 meters. The current pose information of the second vehicle should coincide with the pose information of the starting point in the initial parking planning trajectory. This allows the second vehicle to start from the starting point of the initial parking planning trajectory and drive along it, thus enabling the testing of the controller's performance during the driving process.

[0067] S140: If there are undrivable trajectory points in the initial parking planning trajectory after superimposing environmental information, the target parking planning trajectory is obtained by receiving the user's adjustment operation on the initial parking planning trajectory.

[0068] All trajectory points in the target parking planning trajectory are located within the drivable area.

[0069] During use, there are often situations where the parking space is not open enough, resulting in non-drivable trajectory points in the initial parking planning trajectory after overlaying environmental information. Therefore, it is necessary to adjust the initial parking planning trajectory so that every trajectory point on the target parking planning trajectory used in the final performance test can be safely driven. Non-drivable trajectory points are those located in non-drivable areas, while drivable trajectory points are those located in drivable areas.

[0070] The method for detecting whether there are undrivable trajectory points in the initial parking planning trajectory after overlaying environmental information includes: calculating the distance between each trajectory point in the initial parking planning trajectory after overlaying environmental information and each obstacle in the environmental information perceived by the second vehicle; when there is a trajectory point whose distance to an obstacle is less than a preset safety distance, the trajectory point is determined to be an undrivable trajectory point. The preset safety distance can be determined based on practical experience.

[0071] Since this application embodiment primarily focuses on testing the controller's performance in a parking scenario, it is necessary to ensure that the second vehicle parks along the shape of the initial parking planning trajectory while maintaining its original shape. Therefore, the adjustment operations in this application embodiment include rotation and / or translation, which do not alter the overall shape of the parking planning trajectory.

[0072] It should be added that in practical applications, there are various parking scenarios, such as perpendicular parking with multiple turns, perpendicular parking with one turn, and horizontal parking with one turn. The planning problem description files of the first vehicle under different parking scenarios can be obtained separately to generate different target parking planning trajectories required for the second vehicle to perform controller performance testing, so as to improve the comprehensiveness of controller performance testing.

[0073] The trajectory generation method for testing the control performance of an automatic parking system provided in this application embodiment can automatically generate an initial parking planning trajectory using the vehicle parameter information of the second vehicle (i.e., the test vehicle) and the planning problem description file generated by the first vehicle in an actual parking scenario, without having to spend a lot of time on manual construction. Furthermore, the initial parking planning trajectory can be overlaid with the environmental information currently perceived by the second vehicle in an interactive trajectory adjustment interface. Through human-computer interaction, the user can adjust the initial parking planning trajectory so that the final target parking planning trajectory is always within the drivable area. This ensures that the target parking planning trajectory used for controller performance testing is always in a safe environment, avoiding interference with control performance testing due to unsafe trajectories, thereby improving the safety and accuracy of performance testing.

[0074] In one possible implementation, in order to facilitate intuitive viewing of whether there are undrivable trajectory points in the initial parking planning trajectory, and thus quickly adjust the initial parking trajectory, this embodiment of the application distinguishes between undrivable and drivable trajectory points before obtaining the target parking planning trajectory by receiving the user's adjustment operation on the initial parking planning trajectory.

[0075] The methods for distinguishing between drivable and non-drivable trajectory points include, but are not limited to, color, thickness, highlighting, and dashed lines. To highlight non-drivable trajectory points, for example, they can be made thicker, brighter, or dashed.

[0076] like Figure 2 As shown, the gray area represents the non-drivable area, the white area represents the drivable area, and the trajectory in the middle is the initial parking planning trajectory. After rendering, some trajectory segments of the initial parking planning trajectory are located in the non-drivable area (i.e., the trajectory segment is a non-drivable trajectory segment). Therefore, this part of the trajectory segment can be displayed differently from the remaining trajectory segments. For example, the non-drivable trajectory segment is represented by a thicker and darker line.

[0077] To further facilitate user adjustments, after distinguishing between drivable and non-drivable trajectory points in the initial parking planning trajectory, the system can first receive each adjustment operation from the user on the initial parking planning trajectory and adjust the initial parking planning trajectory accordingly. After each adjustment operation is completed, a safety check is performed on the current adjusted initial parking planning trajectory. If the check result indicates the presence of drivable trajectory points, the operation distinguishing between drivable and non-drivable trajectory points is updated until all trajectory points are within the drivable area, at which point the target parking planning trajectory is obtained.

[0078] The safety detection method includes: statistically analyzing the distances between each trajectory point in the currently adjusted initial parking planning trajectory and each obstacle in the environmental information perceived by the second vehicle; when a trajectory point is found to be less than a preset safety distance from an obstacle, that trajectory point is determined to be a non-drivable trajectory point. The preset safety distance can be determined based on practical experience.

[0079] In one possible implementation, if the starting point of the target parking planning trajectory differs from the starting point of the initial parking planning trajectory due to adjustment operations, the current position of the second vehicle may also differ from the starting point of the target parking planning trajectory, resulting in the second vehicle being unable to park according to the target parking planning trajectory. To solve this technical problem, in this embodiment, after obtaining the target parking planning trajectory and before testing the controller's performance during parking according to the target parking planning trajectory, trajectory planning can be performed on the second vehicle based on its current pose information and the pose information of the starting point of the target parking planning trajectory. This obtains the target movement trajectory of the second vehicle from its current position to the starting point of the target parking planning trajectory. Then, the second vehicle is controlled to move according to the target movement trajectory to the starting point of the target parking planning trajectory, so that the pose information of the second vehicle after movement is the same as the pose information of the starting point of the target parking planning trajectory.

[0080] like Figure 3 As shown, the thinner line represents the initial parking planning trajectory, and the thicker line represents the target parking planning trajectory. Since the two start points are different, trajectory planning can be performed to obtain the target movement trajectory from the initial parking planning trajectory to the starting point of the target parking planning trajectory, which is represented by dashed lines in the figure.

[0081] It should be added that when the target movement trajectory planning fails, a prompt message can be output on the interactive trajectory adjustment interface to indicate that the user should continue to adjust, so that the target movement trajectory can be planned again until the planning is successful.

[0082] As can be seen from the above scheme, when the starting point of the target parking planning trajectory is different from the starting point of the initial parking planning trajectory, the embodiments of this application can automatically plan a transitional trajectory (i.e., the target movement trajectory) from the current position of the second vehicle to the starting point of the target parking planning trajectory, so that the second vehicle can smoothly drive to the starting point of the target parking planning trajectory.

[0083] In one possible implementation, such as Figure 4 As shown, the first vehicle includes a first perception module 210, a planning module 220, a first controller 230, and a first vehicle chassis module 240. The planning module 220 includes a planning problem generator 221, a first trajectory planner 222, and a first speed planner 223.

[0084] After the first perception module 210 perceives the environmental information around the first vehicle, it transmits the perceived environmental information to the planning problem generator 221. The planning problem generator 221 generates planning problem description information based on the environmental information. The planning problem description information generated by the planning problem generator 221 is sequentially input into the first trajectory planner 222 and the first speed planner 223 to perform parking path planning and speed planning at the location point. After obtaining the parking planning path and speed curve, it is transmitted to the first controller 230. Based on the first controller 230 and the first vehicle chassis module 240, the first vehicle is controlled to park.

[0085] The second vehicle includes a second perception module 250, a controller performance test module 260, a second controller 270, and a second vehicle chassis module 280. The controller performance test module 260 includes a planning problem loader 261, a second trajectory planner 262, a second speed planner 263, and an interactive trajectory adjustment interface 264.

[0086] The planning problem loader 261 is used to export a planning problem description file from the planning problem generator 221, and then sequentially inputs this planning problem description file into the second trajectory planner 262 and the second speed planner 263 for parking path planning and speed planning, obtaining an initial parking planning trajectory including the parking planning path and speed curve. When the second vehicle is placed in a relatively open environment, the second perception module 250 of the second vehicle can perceive the surrounding environmental information and input the perceived environmental information and the initial parking planning trajectory into the interactive trajectory adjustment interface 264. The interactive trajectory adjustment interface 264 overlays the two and displays them. If there are undrivable trajectory points in the initial parking planning trajectory after overlaying the environmental information, the target parking planning trajectory is obtained by receiving the user's adjustment operation on the initial parking planning trajectory. After obtaining the target parking planning trajectory, the target parking planning trajectory can be sent to the second controller 270 so that the controller performance can be tested during the process of controlling the second vehicle parking based on the target parking planning trajectory, the second controller 270, and the second vehicle chassis module 280.

[0087] The first sensing module 210 and the second sensing module 250 are essentially the same. Similarly, the first trajectory planner 222 and the second trajectory planner 262, the first speed planner 223 and the second speed planner 263, the first controller 230 and the second controller 270, the first vehicle chassis module 240 and the second vehicle chassis module 280 are also the same.

[0088] Based on the above method embodiments, another embodiment of this application provides a trajectory generation device for testing the control performance of an automatic parking system, such as... Figure 5 As shown, the device includes:

[0089] The acquisition unit 310 is used to acquire a planning problem description file generated by the first vehicle in an actual parking scenario, wherein the planning problem description file includes information required for parking trajectory planning generated based on the environmental information perceived by the first vehicle.

[0090] Planning unit 320 is used to plan a parking trajectory based on the vehicle parameter information of the second vehicle and the planning problem description file, and generate an initial parking planning trajectory. The second vehicle is a test vehicle used to test the performance of the controller in the automatic parking system, and the second vehicle is located in a road environment used to test the performance of the controller.

[0091] The output display unit 330 renders the initial parking planning trajectory from a top-down angle in the interactive trajectory adjustment interface, and overlays the environmental information currently perceived by the second vehicle with the initial parking planning trajectory when the current pose information of the second vehicle coincides with the pose information of the starting point in the initial parking planning trajectory. The pose information includes position and heading.

[0092] The adjustment unit 340 is used to obtain a target parking planning trajectory by receiving the user's adjustment operation on the initial parking planning trajectory when there are undrivable trajectory points in the initial parking planning trajectory after superimposing environmental information. The target parking planning trajectory contains all trajectory points in the drivable area.

[0093] In one possible implementation, the adjustment operation includes rotation and / or translation.

[0094] In one possible implementation, the planning unit 320 is further configured to, when the starting point of the target parking planning trajectory is different from the starting point of the initial parking planning trajectory, after obtaining the target parking planning trajectory and before testing the performance of the controller during parking according to the target parking planning trajectory, perform trajectory planning for the second vehicle based on the current pose information of the second vehicle and the pose information of the starting point of the target parking planning trajectory, to obtain the target movement trajectory of the second vehicle from the current position to the starting point of the target parking planning trajectory;

[0095] The device further includes:

[0096] A control movement unit is used to control the second vehicle to travel to the starting point of the target parking planning trajectory according to the target movement trajectory, so that the pose information of the second vehicle after movement is the same as the pose information of the starting point of the target parking planning trajectory.

[0097] In one possible implementation, the output display unit 330 is further configured to distinguish between drivable and non-drivable trajectory points before obtaining the target parking planning trajectory by receiving the user's adjustment operation on the initial parking planning trajectory.

[0098] In one possible implementation, the adjustment unit 340 includes:

[0099] The receiving module is used to receive each adjustment operation by the user on the initial parking planning trajectory;

[0100] An adjustment module is used to adjust the initial parking planning trajectory accordingly according to the adjustment operation;

[0101] The detection module is used to perform a safety check on the adjusted initial parking planning trajectory after each adjustment operation is completed.

[0102] The output display unit 330 is also used to update the operation of distinguishing between displaying non-drivable trajectory points and drivable trajectory points when the detection result indicates the existence of non-drivable trajectory points, until all trajectory points are in the drivable area, and then obtain the target parking planning trajectory.

[0103] The trajectory generation device for testing the control performance of an automatic parking system provided in this application embodiment can automatically generate an initial parking planning trajectory using the vehicle parameter information of the second vehicle (i.e., the test vehicle) and the planning problem description file generated by the first vehicle in an actual parking scenario, without having to spend a lot of time on manual construction. Furthermore, the initial parking planning trajectory can be overlaid with the environmental information currently perceived by the second vehicle in an interactive trajectory adjustment interface. Through human-computer interaction, the user can adjust the initial parking planning trajectory so that the final target parking planning trajectory is always within the drivable area. This ensures that the target parking planning trajectory used for controller performance testing is always in a safe environment, avoiding interference with control performance testing due to unsafe trajectories, thereby improving the safety and accuracy of performance testing.

[0104] Based on the above method embodiments, another embodiment of this application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any of the above embodiments.

[0105] Based on the above method embodiments, another embodiment of this application provides an electronic device or computer device, such as... Figure 6 As shown, it includes:

[0106] One or more processors 410;

[0107] The processor 410 is coupled to a storage device 420, the storage device 420 being used to store one or more programs;

[0108] When the one or more programs are executed by the one or more processors 410, the electronic device or computer device performs the method as described in any of the above embodiments.

[0109] Based on the above method embodiments, another embodiment of this application provides a vehicle that includes the device as described in any of the above embodiments, or includes the electronic device as described above.

[0110] Based on the above embodiments, another embodiment of this application provides a computer program product, which includes instructions that, when executed on a computer or processor, cause the computer or processor to perform the method described in any of the above embodiments.

[0111] The above-described apparatus embodiments correspond to the method embodiments and have the same technical effects. For detailed descriptions, please refer to the method embodiments. The apparatus embodiments are derived from the method embodiments; detailed descriptions can be found in the method embodiments section, and will not be repeated here. Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of one embodiment, and the modules or processes shown in the drawings are not necessarily essential for implementing this application.

[0112] Those skilled in the art will understand that the modules in the apparatus of the embodiments can be distributed in the apparatus of the embodiments as described in the embodiments, or they can be located in one or more devices different from this embodiment with corresponding changes. The modules of the above embodiments can be combined into one module, or they can be further divided into multiple sub-modules.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A trajectory generation method for testing the control performance of an automatic parking system, characterized in that, The method includes: Obtain a planning problem description file generated by the first vehicle in an actual parking scenario, wherein the planning problem description file includes information required for parking trajectory planning based on the environmental information perceived by the first vehicle; Parking trajectory planning is performed based on the vehicle parameter information of the second vehicle and the planning problem description file to generate an initial parking planning trajectory. The second vehicle is a test vehicle used to test the performance of the controller in the automatic parking system, and the second vehicle is located in a road environment used to test the performance of the controller. In the interactive trajectory adjustment interface, the initial parking planning trajectory is rendered from a top-down perspective. By overlaying the environmental information currently perceived by the second vehicle with the initial parking planning trajectory when the current pose information of the second vehicle coincides with the pose information of the starting point in the initial parking planning trajectory, the pose information includes position and heading. If there are undrivable trajectory points in the initial parking planning trajectory after overlaying environmental information, a target parking planning trajectory is obtained by receiving user adjustment operations on the initial parking planning trajectory, wherein all trajectory points in the target parking planning trajectory are in drivable areas.

2. The method according to claim 1, characterized in that, The adjustment operations include rotation and / or translation.

3. The method according to claim 2, characterized in that, When the starting point of the target parking planning trajectory differs from the starting point of the initial parking planning trajectory, after obtaining the target parking planning trajectory and before testing the performance of the controller during parking according to the target parking planning trajectory, the method further includes: Based on the current pose information of the second vehicle and the pose information of the starting point of the target parking planning trajectory, trajectory planning is performed on the second vehicle to obtain the target movement trajectory of the second vehicle from the current position to the starting point of the target parking planning trajectory. The second vehicle is controlled to travel along the target movement trajectory to the starting point of the target parking planning trajectory, so that the pose information of the second vehicle after movement is the same as the pose information of the starting point of the target parking planning trajectory.

4. The method according to any one of claims 1-3, characterized in that, Before obtaining the target parking planning trajectory by receiving the user's adjustment operation on the initial parking planning trajectory, the method further includes: It distinguishes between drivable and non-drivable trajectory points.

5. The method according to claim 4, characterized in that, By receiving user adjustments to the initial parking planning trajectory, the target parking planning trajectory is obtained, including: Receive each adjustment operation from the user on the initial parking planning trajectory, and adjust the initial parking planning trajectory accordingly based on the adjustment operation; After each adjustment operation is completed, a safety check is performed on the current adjusted initial parking planning trajectory. If the check result indicates that there are undrivable trajectory points, the operation of distinguishing between undrivable and drivable trajectory points is updated until all trajectory points are in the drivable area, at which point the target parking planning trajectory is obtained.

6. A trajectory generation device for testing the control performance of an automatic parking system, characterized in that, The device includes: The acquisition unit is used to acquire a planning problem description file generated by the first vehicle in an actual parking scenario, wherein the planning problem description file includes information required for parking trajectory planning based on the environmental information perceived by the first vehicle; The planning unit is used to plan a parking trajectory based on the vehicle parameter information of the second vehicle and the planning problem description file, and generate an initial parking planning trajectory. The second vehicle is a test vehicle used to test the performance of the controller in the automatic parking system, and the second vehicle is located in a road environment used to test the performance of the controller. The output display unit renders the initial parking planning trajectory from a top-down angle in the interactive trajectory adjustment interface, and overlays the environmental information currently perceived by the second vehicle with the initial parking planning trajectory when the current pose information of the second vehicle coincides with the pose information of the starting point in the initial parking planning trajectory. The pose information includes position and heading. The adjustment unit is used to obtain a target parking planning trajectory by receiving user adjustment operations on the initial parking planning trajectory when there are undrivable trajectory points in the initial parking planning trajectory after superimposing environmental information. The target parking planning trajectory contains all trajectory points in the drivable area.

7. The apparatus according to claim 6, characterized in that, The adjustment operations include rotation and / or translation.

8. The apparatus according to claim 7, characterized in that, The planning unit is further configured to, when the starting point of the target parking planning trajectory is different from the starting point of the initial parking planning trajectory, after obtaining the target parking planning trajectory and before testing the performance of the controller during the parking process according to the target parking planning trajectory, perform trajectory planning for the second vehicle based on the current pose information of the second vehicle and the pose information of the starting point of the target parking planning trajectory, to obtain the target movement trajectory of the second vehicle from the current position to the starting point of the target parking planning trajectory; The device further includes: A control movement unit is used to control the second vehicle to travel to the starting point of the target parking planning trajectory according to the target movement trajectory, so that the pose information of the second vehicle after movement is the same as the pose information of the starting point of the target parking planning trajectory.

9. The apparatus according to any one of claims 6-8, characterized in that, The output display unit is also used to distinguish between drivable and non-drivable trajectory points before obtaining the target parking planning trajectory by receiving the user's adjustment operation on the initial parking planning trajectory.

10. The apparatus according to claim 9, characterized in that, The adjustment unit includes: The receiving module is used to receive each adjustment operation by the user on the initial parking planning trajectory; An adjustment module is used to adjust the initial parking planning trajectory accordingly according to the adjustment operation; The detection module is used to perform a safety check on the adjusted initial parking planning trajectory after each adjustment operation is completed. The output display unit is also used to update the operation of distinguishing between displaying non-drivable trajectory points and drivable trajectory points when the detection result indicates the existence of non-drivable trajectory points, until all trajectory points are in the drivable area, and then obtain the target parking planning trajectory.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-5.

12. An electronic device, characterized in that, The electronic device includes: One or more processors; The processor is coupled to a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the electronic device performs the method as described in any one of claims 1-5.

13. A vehicle, characterized in that, The vehicle includes the device as described in any one of claims 6-10, or the electronic device as described in claim 12.

Images