Path planning method, device, electronic device and storage medium

Abstract

The present invention relates to the field of autonomous driving, and specifically to a path planning method, device, electronic device and storage medium. It includes: obtaining the first position information corresponding to the target vehicle in the target coordinate system and the second position information corresponding to each obstacle within the preset range of the target vehicle's driving direction; dividing the area within the preset range of the target vehicle's driving direction using grids of different sizes; according to the grid division results, performing different path planning for areas of different grid sizes, and generating a target planning path within the preset range of the target vehicle's driving direction; according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, planning the speed corresponding to the target planning path, and determining the target speed corresponding to the target planning path of the target vehicle. The accuracy of the target planning path is guaranteed, and the amount of calculation is reduced, which is suitable for path planning of autonomous driving vehicles in closed scenes.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a path planning method, device, electronic device and storage medium. Background Art

[0002] With the continuous improvement of human living standards and the rapid development of industrial automation and intelligence, the application of autonomous driving technology is becoming more and more extensive, and the research is becoming more and more in-depth. Autonomous driving technology has developed rapidly and is widely used in different fields such as agriculture, industry, service industry, aerospace, medical care, and military, and has great social value. Autonomous driving vehicles will encounter many obstacles during their movement, and how to plan a collision-free path from the starting point to the end point in a complex and changing working environment is a major topic in the research of autonomous driving technology.

[0003] In the prior art, an autonomous driving vehicle usually obtains perception data within a preset range each time, and then plans a path within the preset range with a certain step length using a preset path planning algorithm based on the perception data.

[0004] The above method has a large amount of calculation and requires a high computing power consumption. It is suitable for more complex driving scenarios. In the case of vehicle autonomous driving in closed scenes, since the scene is relatively simple, there are not a large number of obstacles and decision-making scenarios. At the same time, we expect the vehicle to be equipped with a lightweight computing platform and be able to drive, stop, and bypass obstacles under different road conditions. Therefore, the above method is not suitable for path planning of autonomous driving vehicles in closed scenes. Summary of the invention

[0005] In view of this, an embodiment of the present invention provides a path planning method, which aims to solve the problem that the path planning method in the prior art is not suitable for path planning of autonomous driving vehicles in closed scenes.

[0006] According to a first aspect, an embodiment of the present invention provides a path planning method, the method comprising:

[0007] Acquire first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction;

[0008] According to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided into grids of different sizes;

[0009] According to the grid division results, different path planning is performed for areas of different grid sizes to generate a target planning path within a preset range of the target vehicle's driving direction;

[0010] According to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, the speed corresponding to the target planning path is planned to determine the target speed corresponding to the target planning path for the target vehicle.

[0011] The path planning method provided by the embodiment of the present invention obtains the first position information corresponding to the target vehicle in the target coordinate system and the second position information corresponding to each obstacle within the preset range of the target vehicle's driving direction, thereby ensuring the accuracy of the first position information and the second position information. Then, according to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided using grids of different sizes, thereby ensuring the accuracy of the obtained grid division result. According to the grid division result, different path planning is performed for areas of different grid sizes respectively, and a target planning path within the preset range of the target vehicle's driving direction is generated, thereby ensuring the accuracy of the target planning path within the preset range of the generated target vehicle's driving direction. Then, according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, the speed corresponding to the target planning path is planned, and the target speed corresponding to the target vehicle's driving target planning path is determined, thereby ensuring the accuracy of the target speed corresponding to the determined target planning path. In the above method, according to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided using grids of different sizes, thereby, according to the grid division result, different path planning can be performed for areas of different grid sizes respectively, thereby generating a target planning path within the preset range of the target vehicle's driving direction. This allows for simple path planning for paths without obstacles and more detailed path planning for paths with obstacles. This not only ensures the accuracy of the planned target path, but also reduces the amount of calculation required for path planning, saves as much computing platform space as possible, and provides valuable computing resources for a large number of perception sensor data processing and AI reasoning. The above method is more suitable for path planning for autonomous driving vehicles in closed scenarios.

[0012] In combination with the first aspect, in a first implementation of the first aspect, obtaining first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction includes:

[0013] Get the center point of the target vehicle, take the center point as the origin of the target coordinate system, take the target vehicle's driving direction as the longitudinal axis, and take the axis perpendicular to the target vehicle's driving direction as the transverse axis to establish the target coordinate system;

[0014] Determining first position information according to a relationship between the target coordinate system and the target vehicle;

[0015] Obtain the driving trajectory corresponding to each obstacle, project the driving trajectory corresponding to each obstacle into the target coordinate system, and obtain the projection list of each obstacle in the target coordinate system;

[0016] The projection list is analyzed to determine the second position information corresponding to each obstacle in the target coordinate system.

[0017] The path planning method provided by the embodiment of the present invention obtains the center point of the target vehicle, takes the center point as the origin of the target coordinate system, takes the target vehicle's driving direction as the longitudinal axis, and takes the axis perpendicular to the target vehicle's driving direction as the transverse axis to establish a target coordinate system, thereby ensuring the accuracy of the established target coordinate system. Then, based on the relationship between the target coordinate system and the target vehicle, the first position information is determined, thereby ensuring the accuracy of the determined first position information. The driving trajectory corresponding to each obstacle is obtained, and the driving trajectory corresponding to each obstacle is projected into the target coordinate system, and a projection list of each obstacle in the target coordinate system is obtained, thereby ensuring the accuracy of the projection list of each obstacle in the target coordinate system. The projection list is analyzed to determine the second position information corresponding to each obstacle in the target coordinate system, thereby ensuring the accuracy of the determined second position information corresponding to each obstacle in the target coordinate system.

[0018] In combination with the first aspect, in a second implementation of the first aspect, based on the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided using grids of different sizes, including:

[0019] Get the minimum turning distance corresponding to the target vehicle;

[0020] Determine, according to each piece of second position information, a first coordinate range occupied by each obstacle in the target coordinate system;

[0021] The first coordinate range is widened by the minimum turning distance on both sides along the horizontal axis of the target coordinate system to obtain a second coordinate range occupied by each obstacle in the target coordinate system;

[0022] Determine, based on the first position information and the positional relationship between the second coordinate ranges, a first area between the target vehicle and the second coordinate range closest to the target vehicle, or / and a second area between the second coordinate ranges, or / and a third area between the second coordinate range closest to the end point of the preset range and the end point;

[0023] Using the first grid to divide the first area and / or the second area and / or the third area into grids;

[0024] Determine, based on the first position information and the positional relationship between the second coordinate ranges, that the target vehicle passes through a fourth area corresponding to each second coordinate range;

[0025] The fourth area is divided into grids using a second grid, and the size of the second grid is smaller than that of the first grid.

[0026] The path planning method provided by the embodiment of the present invention obtains the minimum turning distance corresponding to the target vehicle. According to each second position information, the first coordinate range occupied by each obstacle in the target coordinate system is determined, and the accuracy of the first coordinate range occupied by each obstacle in the target coordinate system is ensured. Then, the first coordinate range is widened along the horizontal axis of the target coordinate system to both sides by the minimum turning distance, and the second coordinate range occupied by each obstacle in the target coordinate system is obtained, which ensures the accuracy of the second coordinate range occupied by each obstacle in the target coordinate system, and ensures that the target vehicle can safely pass through the second coordinate range. Then, according to the first position information and the positional relationship between each second coordinate range, the first area between the target vehicle and the nearest second coordinate range or / and the second area between each second coordinate range or / and the third area between the second coordinate range closest to the end point of the preset range is determined, which ensures the accuracy of the determined first area or / and the second area or / and the third area. The first area or / and the second area or / and the third area are meshed using the first grid, which ensures the accuracy of the meshing of the first area or / and the second area or / and the third area. According to the first position information and the positional relationship between each second coordinate range, it is determined that the target vehicle passes through the fourth area corresponding to each second coordinate range, thereby ensuring the accuracy of the determined fourth area, and the fourth area is grid-divided using the second grid, thereby ensuring the accuracy of the grid division of the fourth area.

[0027] In combination with the second implementation of the first aspect, in the third implementation of the first aspect, different path planning is performed for areas of different grid sizes according to the grid division result, and a target planning path within a preset range of the target vehicle's driving direction is generated;

[0028] For the fourth area divided by the second grid, the area occupied by the obstacles in each second grid is removed;

[0029] Calculate the grid cost corresponding to each second grid according to the relationship between the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the road boundary, and the third distance from each second grid to the end point;

[0030] Obtaining the steering constraint cost of the target vehicle, and performing a grid path search on the fourth area using a preset path planning algorithm according to the relationship between the steering constraint cost and each grid cost, to obtain a first candidate planning path;

[0031] Perform polynomial interpolation processing on the first candidate planning path to obtain a first reference planning path.

[0032] The path planning method provided by the embodiment of the present invention eliminates the area occupied by obstacles in each second grid for the fourth area divided by the second grid, thereby avoiding collision between the target vehicle and the obstacle. According to the relationship between the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the road boundary, and the third distance from each second grid to the end point, the grid cost corresponding to each second grid is calculated, thereby ensuring the accuracy of the calculated grid cost. Then, the steering constraint cost of the target vehicle is obtained, and according to the relationship between the steering constraint cost and each grid cost, a preset path planning algorithm is used to search the grid path in the fourth area to obtain the first candidate planning path, thereby ensuring the accuracy of the obtained first candidate planning path. Then, the first candidate planning path is subjected to polynomial interpolation processing to obtain the first reference planning path, thereby ensuring the accuracy of the obtained first reference planning path.

[0033] In combination with the third implementation of the first aspect, in the fourth implementation of the first aspect, different path planning is performed for areas of different grid sizes according to the grid division result, and a target planning path within a preset range of the target vehicle's driving direction is generated;

[0034] For the first area or / and the second area or / and the third area divided by the first grid, obtaining a preset path of the target vehicle in a preset range;

[0035] Using the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area;

[0036] The first reference path and the second reference path are spliced ​​together to generate a target planning path within a preset range of the target vehicle's driving direction.

[0037] The path planning method provided by the embodiment of the present invention obtains the preset path of the target vehicle in the preset range for the first area or / and the second area or / and the third area divided by the first grid, and uses the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area, thereby ensuring the accuracy of the second reference path corresponding to the determined first area or / and the second area or / and the third area, splicing the first reference path and the second reference path to generate the target planning path within the preset range of the driving direction of the target vehicle, thereby ensuring the accuracy of the generated target planning path. The above method uses the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area, thereby not only ensuring the accuracy of the planned second reference path, but also reducing the calculation amount of the path planning, saving the occupancy of the computing platform as much as possible, and providing valuable computing resources to a large number of perception sensor data processing and AI reasoning parts.

[0038] In combination with the first aspect, in a fifth implementation of the first aspect, planning a speed corresponding to the target planned path according to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, and determining a target speed corresponding to the target planned path for the target vehicle to travel, including:

[0039] Using the preset speed planning algorithm, the speed corresponding to the target planning path is planned to obtain the reference speed;

[0040] According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the reference speed is corrected to determine the target speed corresponding to the target planned path for the target vehicle to travel.

[0041] The path planning method provided by the embodiment of the present invention uses a preset speed planning algorithm to plan the speed corresponding to the target planning path to obtain a reference speed, thereby ensuring the accuracy of the obtained reference speed. Then, according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, the reference speed is corrected to determine the target speed corresponding to the target planning path of the target vehicle, thereby ensuring the accuracy of the generated target speed.

[0042] In combination with the first aspect, in a sixth implementation of the first aspect, the method further includes:

[0043] When the preset condition for re-planning the driving path corresponding to the target vehicle is met, the second position information corresponding to the last unprocessed obstacle is added to the next cycle for path planning.

[0044] The path planning method provided by the embodiment of the present invention, when the preset conditions for re-planning the driving path corresponding to the target vehicle are met, adds the second position information corresponding to the last unprocessed obstacle to the next cycle for path planning, thereby ensuring the accuracy of the path planning for the next cycle.

[0045] According to the second aspect, an embodiment of the present invention further provides a path planning device, the device comprising:

[0046] An acquisition module, used to acquire first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction;

[0047] A grid division module, used to divide the area within a preset range of the target vehicle's driving direction into grids of different sizes according to the relationship between the first position information and the second position information;

[0048] A path planning module is used to perform different path planning for areas of different grid sizes according to the grid division results, and generate a target planning path within a preset range of the target vehicle's driving direction;

[0049] The speed planning module is used to plan the speed corresponding to the target planning path according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, and determine the target speed corresponding to the target planning path for the target vehicle to travel.

[0050] The path planning device provided by the embodiment of the present invention obtains the first position information corresponding to the target vehicle in the target coordinate system and the second position information corresponding to each obstacle within the preset range of the target vehicle's driving direction, thereby ensuring the accuracy of the first position information and the second position information. Then, according to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided using grids of different sizes, thereby ensuring the accuracy of the obtained grid division result. According to the grid division result, different path planning is performed for areas of different grid sizes respectively, and a target planning path within the preset range of the target vehicle's driving direction is generated, thereby ensuring the accuracy of the target planning path within the preset range of the generated target vehicle's driving direction. Then, according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, the speed corresponding to the target planning path is planned, and the target speed corresponding to the target vehicle's driving target planning path is determined, thereby ensuring the accuracy of the target speed corresponding to the determined target planning path. The above device divides the area within the preset range of the target vehicle's driving direction using grids of different sizes according to the relationship between the first position information and the second position information. Therefore, according to the grid division result, different path planning can be performed for areas of different grid sizes respectively, thereby generating a target planning path within the preset range of the target vehicle's driving direction. This allows for simple path planning for paths without obstacles and more detailed path planning for paths with obstacles. This not only ensures the accuracy of the planned target path, but also reduces the amount of calculation required for path planning, saves as much computing platform space as possible, and provides valuable computing resources for a large number of perception sensor data processing and AI reasoning. The above method is more suitable for path planning for autonomous driving vehicles in closed scenarios.

[0051] According to the third aspect, an embodiment of the present invention provides an electronic device, including a memory and a processor, the memory and the processor are communicatively connected to each other, computer instructions are stored in the memory, and the processor executes the path planning method in the first aspect or any one of the embodiments of the first aspect by executing the computer instructions.

[0052] According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores computer instructions, and the computer instructions are used to enable a computer to execute the path planning method in the first aspect or any one of the embodiments of the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0054] Figure 1 is a flow chart of a path planning method provided by an embodiment of the present invention;

[0055] Figure 2 is a flow chart of a path planning method provided by another embodiment of the present invention;

[0056] Figure 3 is a flow chart of a path planning method provided by another embodiment of the present invention;

[0057] Figure 4 is a flow chart of a path planning method provided by another embodiment of the present invention;

[0058] Figure 5 It is a functional module diagram of a path planning device provided by an embodiment of the present invention;

[0059] Figure 6 It is a functional module diagram of a path planning device provided by an embodiment of the present invention;

[0060] Figure 7 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0062] It should be noted that the execution subject of the path planning method provided in the embodiment of the present application can be a path planning device, and the path planning device can be implemented as part or all of an electronic device through software, hardware, or a combination of software and hardware, wherein the electronic device can be a control device in an intelligent driving vehicle, or a terminal device or server device connected to the intelligent driving vehicle but independent of the intelligent driving vehicle, wherein the server in the embodiment of the present application can be a single server or a server cluster composed of multiple servers, and the terminal in the embodiment of the present application can be a smart phone, a personal computer, a tablet computer, a wearable device, and other intelligent hardware devices such as an intelligent robot. In the following method embodiments, the execution subject is an electronic device as an example for explanation.

[0063] In one embodiment of the present application, Figure 1 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0064] S11, obtaining first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction.

[0065] In an optional implementation of the present application, the electronic device can use the positioning system to obtain the first position information corresponding to the target vehicle in the target coordinate system, and detect each obstacle within a preset range of the target vehicle's driving direction through sensors, radars and other equipment, and obtain the second position information corresponding to each obstacle.

[0066] In another optional embodiment of the present application, the electronic device can also receive first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction sent by a target vehicle or other device connected to the electronic device.

[0067] The embodiment of the present application does not specifically limit the manner in which the electronic device obtains the first position information corresponding to the target vehicle in the target coordinate system and the second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction.

[0068] This step will be described in detail below.

[0069] S12. Divide the area within a preset range of the target vehicle's driving direction into grids of different sizes according to the relationship between the first position information and the second position information.

[0070] Specifically, after acquiring the first position information and the second position information, the electronic device can divide the area within a preset range of the target vehicle's driving direction according to the positional relationship between the first position information and the second position information, and then divide different areas into grids using grids of different sizes based on the area division results.

[0071] This step will be described in detail below.

[0072] S13. According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planned path within a preset range of the target vehicle's driving direction.

[0073] Specifically, after the electronic device divides the area within a preset range of the target vehicle's driving direction into grids of different sizes, it performs different path planning for areas of different grid sizes based on the grid division results, and then splices the planned paths corresponding to each area to generate different path planning.

[0074] This step will be described in detail below.

[0075] S14. According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the speed corresponding to the target planned path is planned to determine the target speed corresponding to the target planned path for the target vehicle to travel.

[0076] Specifically, after the electronic device plans and obtains the target planned path within a preset range of the target vehicle's driving direction, it can calculate the distance between each path point on the target planned path and the second position information according to the second position information corresponding to each obstacle, and then add the distance between each path point and the second position information and the curvature of each path point in the target planned path to the path point speed constraint for speed planning, thereby determining the target speed corresponding to the target planned path for the target vehicle.

[0077] The path planning method provided by the embodiment of the present invention obtains the first position information corresponding to the target vehicle in the target coordinate system and the second position information corresponding to each obstacle within the preset range of the target vehicle's driving direction, thereby ensuring the accuracy of the first position information and the second position information. Then, according to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided using grids of different sizes, thereby ensuring the accuracy of the obtained grid division result. According to the grid division result, different path planning is performed for areas of different grid sizes respectively, and a target planning path within the preset range of the target vehicle's driving direction is generated, thereby ensuring the accuracy of the target planning path within the preset range of the generated target vehicle's driving direction. Then, according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, the speed corresponding to the target planning path is planned, and the target speed corresponding to the target vehicle's driving target planning path is determined, thereby ensuring the accuracy of the target speed corresponding to the determined target planning path. In the above method, according to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided using grids of different sizes, thereby, according to the grid division result, different path planning can be performed for areas of different grid sizes respectively, thereby generating a target planning path within the preset range of the target vehicle's driving direction. This allows for simple path planning for paths without obstacles and more detailed path planning for paths with obstacles. This not only ensures the accuracy of the planned target path, but also reduces the amount of calculation required for path planning, saves as much computing platform space as possible, and provides valuable computing resources for a large number of perception sensor data processing and AI reasoning. The above method is more suitable for path planning for autonomous driving vehicles in closed scenarios.

[0078] In one embodiment of the present application, Figure 2 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0079] S21. Acquire first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction.

[0080] In an optional implementation of the present application, the above S21 "obtaining the first position information corresponding to the target vehicle in the target coordinate system and the second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction" may include the following steps:

[0081] S211. Acquire the center point of the target vehicle, establish a target coordinate system with the center point as the origin of the target coordinate system, the target vehicle driving direction as the longitudinal axis, and the axis perpendicular to the target vehicle driving direction as the transverse axis.

[0082] Specifically, the electronic device can locate the target vehicle through the positioning system, and then determine the center point of the target vehicle based on the positioning information after locating the target vehicle. After determining the center point of the target vehicle, the electronic device can establish the target coordinate system with the center point of the target vehicle as the origin of the target coordinate system, the target vehicle driving direction as the longitudinal axis, and the axis perpendicular to the target vehicle driving direction as the transverse axis.

[0083] S212: Determine first position information according to the relationship between the target coordinate system and the target vehicle.

[0084] Specifically, after determining the target coordinate system, the electronic device may determine the first position information of the target vehicle in the target coordinate system according to the relationship that the origin of the target coordinate system is the center point of the target vehicle.

[0085] S213: Acquire the driving trajectory corresponding to each obstacle, project the driving trajectory corresponding to each obstacle into the target coordinate system, and acquire a projection list of each obstacle in the target coordinate system.

[0086] Specifically, the electronic device can obtain perception data within a preset time period based on the perception system, and then study and analyze the perception data to obtain the driving trajectory corresponding to each obstacle. Then, the electronic device projects the driving trajectory of each vertex corresponding to each obstacle to the target coordinate system, and then obtains the projection list of each obstacle in the target coordinate system based on the projection results.

[0087] Exemplarily, configuration is performed according to actual needs. Assume that the current position of the target vehicle is represented as P, obstacle i is represented as Obs(i), and the jth vertex of Obs(i) is represented as Obs(i)(j). Obs(i)(j) is projected to the target coordinate system as Obs_SL(i)(j), and P is projected to the target coordinate system as P_SL.

[0088] S214: Analyze the projection list to determine the second position information corresponding to each obstacle in the target coordinate system.

[0089] Specifically, after the electronic device obtains the projection list of each obstacle in the target coordinate system, the electronic device may read and analyze the projection list to determine the second position information corresponding to each obstacle in the target coordinate system.

[0090] S22. Divide the area within the preset range of the target vehicle's driving direction into grids of different sizes according to the relationship between the first position information and the second position information.

[0091] For more information about this step, see Figure 1 The introduction of S12 will not be elaborated here.

[0092] S23. According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planned path within a preset range of the target vehicle's driving direction.

[0093] For more information about this step, see Figure 1 The introduction of S13 will not be elaborated here.

[0094] S24. According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the speed corresponding to the target planned path is planned to determine the target speed corresponding to the target planned path for the target vehicle to travel.

[0095] For more information about this step, see Figure 1 The introduction of S14 will not be elaborated here.

[0096] The path planning method provided by the embodiment of the present invention obtains the center point of the target vehicle, takes the center point as the origin of the target coordinate system, takes the target vehicle's driving direction as the longitudinal axis, and takes the axis perpendicular to the target vehicle's driving direction as the transverse axis to establish a target coordinate system, thereby ensuring the accuracy of the established target coordinate system. Then, based on the relationship between the target coordinate system and the target vehicle, the first position information is determined, thereby ensuring the accuracy of the determined first position information. The driving trajectory corresponding to each obstacle is obtained, and the driving trajectory corresponding to each obstacle is projected into the target coordinate system, and a projection list of each obstacle in the target coordinate system is obtained, thereby ensuring the accuracy of the projection list of each obstacle in the target coordinate system. The projection list is analyzed to determine the second position information corresponding to each obstacle in the target coordinate system, thereby ensuring the accuracy of the determined second position information corresponding to each obstacle in the target coordinate system.

[0097] In one embodiment of the present application, Figure 3 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0098] S31, obtaining first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction.

[0099] For more information about this step, see Figure 2 The introduction of S21 will not be elaborated here.

[0100] S32. Divide the area within the preset range of the target vehicle's driving direction into grids of different sizes according to the relationship between the first position information and the second position information.

[0101] In an optional implementation of the present application, S32 “dividing the area within the preset range of the target vehicle's driving direction using grids of different sizes according to the relationship between the first position information and the second position information” may include the following steps:

[0102] S321. Obtain the minimum turning distance corresponding to the target vehicle.

[0103] In an optional implementation, the electronic device may obtain parameter information of the target vehicle, and then calculate the minimum turning distance corresponding to the target vehicle according to the parameters of the target vehicle, wherein the parameter information may include information such as the length, width, front axle length, and rear axle length of the target vehicle.

[0104] S322: Determine, according to each piece of second position information, a first coordinate range occupied by each obstacle in the target coordinate system.

[0105] Specifically, the electronic device analyzes the second position information of each obstacle in the target coordinate system to determine the first coordinate range occupied by each obstacle in the target coordinate system.

[0106] S323: widen the first coordinate range by the minimum turning distance on both sides along the horizontal axis of the target coordinate system to obtain a second coordinate range occupied by each obstacle in the target coordinate system.

[0107] Specifically, after determining the first coordinate range occupied by each obstacle in the target coordinate system, the first coordinate range is widened by the minimum turning distance on both sides along the horizontal axis of the target coordinate system to obtain the second coordinate range occupied by each obstacle in the target coordinate system.

[0108] Exemplarily, assuming that the horizontal axis range of the first coordinate range under the target coordinates is [1m, 5m], and the minimum turning distance corresponding to the target vehicle is 1m, the electronic device widens the first coordinate range by 1m on both sides along the horizontal axis of the target coordinate system to obtain the second coordinate range, and the horizontal axis range of the obtained second coordinate range under the target coordinates is [0m, 6m].

[0109] S324. Determine, based on the first position information and the positional relationship between each second coordinate range, a first area between the target vehicle and the nearest second coordinate range or / and a second area between each second coordinate range or / and a third area between the second coordinate range closest to the end point of the preset range and the end point.

[0110] Specifically, the electronic device determines, based on the first position information and the positional relationship between each second coordinate range, a first area between the target vehicle and the nearest second coordinate range or / and a second area between each second coordinate range or / and a third area between the second coordinate range closest to the end point of the preset range and the end point.

[0111] S325: Use the first grid to divide the first area and / or the second area and / or the third area into grids.

[0112] Specifically, the electronic device may use the first grid to divide the first area and / or the second area and / or the third area into grids.

[0113] Exemplarily, the electronic device may regard the first area and / or the second area and / or the third area as a grid, and the size of the grid may be determined according to the size of the first area and / or the second area and / or the third area.

[0114] S326. Determine, based on the first position information and the positional relationship between the second coordinate ranges, that the target vehicle passes through a fourth area corresponding to each second coordinate range.

[0115] Specifically, the electronic device determines that the target vehicle passes through the fourth area corresponding to each second coordinate range according to the first position information and the positional relationship between each second coordinate range.

[0116] S327: Use the second grid to divide the fourth area into grids.

[0117] The size of the second grid is smaller than that of the first grid.

[0118] Specifically, the electronic device can use the second grid to divide the fourth area into grids, wherein the size of the second grid can be set according to user needs.

[0119] Exemplarily, the electronic device may perform sampling in the horizontal and vertical directions of the target coordinate system according to a certain step length step (0.5 m), thereby forming a grid space of Obs(i).

[0120] S33. According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planned path within a preset range of the target vehicle's driving direction.

[0121] In an optional implementation of the present application, S33 "performing different path planning for areas of different grid sizes according to the grid division result to generate a target planned path within a preset range of the target vehicle's driving direction" may include the following steps:

[0122] S331. For the fourth area divided by the second grids, remove the areas occupied by obstacles in each second grid.

[0123] Specifically, for the fourth area divided by the second grid, the electronic device may remove the area occupied by the obstacles in each second grid according to the second position information of each obstacle in the target coordinate system.

[0124] S332, calculating the grid cost corresponding to each second grid according to the relationship between the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the road boundary, and the third distance from each second grid to the end point.

[0125] In an optional embodiment of the present application, for each second grid, the electronic device can calculate the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the left and right road boundaries, and the third distance from each second grid to the end point within a preset range of the target vehicle's driving direction. The electronic device can add the first minimum distance, the second minimum distance and the third distance to calculate the grid cost corresponding to each second grid.

[0126] For each second grid, the electronic device can calculate the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the left and right road boundaries, and the third distance from each second grid to the end point within a preset range of the target vehicle's driving direction, and then multiply the first minimum distance, the second minimum distance and the third distance by the corresponding weight coefficient and add them together to calculate the grid cost corresponding to each second grid.

[0127] Exemplarily, the second grid i is represented as grid(i), the first minimum distance of grid(i) from the obstacle is grid(i)_d_obs, the second minimum distance of grid(i) from the left and right road boundaries is grid(i)_d_l, and the distance of grid(i) from the end point within the preset range of the vehicle's driving direction is grid(i)_d_tar. The electronic device can calculate the grid cost corresponding to the second grid based on the following formula:

[0128] grid(i)_f=a*grid(i)_d_obs+b*grid(i)_d_l+c*grid(i)_d_tar (1)

[0129] Among them, a, b, and c respectively ensure the weight coefficients corresponding to the first distance, the second distance, and the third distance.

[0130] S333, obtaining the steering constraint cost of the target vehicle, and performing a grid path search on the fourth area using a preset path planning algorithm according to the relationship between the steering constraint cost and each grid cost, to obtain a first candidate planning path.

[0131] Specifically, after calculating the grid costs corresponding to each second grid, the electronic device obtains the steering constraint cost of the target vehicle, and then uses a preset path planning algorithm to perform a grid path search on the fourth area based on the relationship between the steering constraint cost and each grid cost to obtain a first candidate planned path.

[0132] Among them, the path planning algorithm can be an A* search algorithm or other path planning algorithms. The embodiment of the present application does not specifically limit the path planning algorithm.

[0133] Exemplarily, when performing a grid path search on the fourth area using a preset path planning algorithm, in the search process from the second grid grid(i) to the second grid grid(j), the cost to the next grid is: f=grid(j)_f+theta, where theta is the steering angle.

[0134] S334. Perform polynomial interpolation processing on the first candidate planning path to obtain a first reference planning path.

[0135] Specifically, after generating the first candidate planned path, the electronic device may perform polynomial interpolation processing on the first candidate planned path to obtain the first reference planned path.

[0136] S335. For the first area and / or the second area and / or the third area divided by the first grid, obtain a preset path of the target vehicle within a preset range.

[0137] Specifically, for the first area and / or the second area and / or the third area divided by the first grid, the electronic device can obtain candidate paths of the target vehicle within a preset range, smooth the candidate paths, and generate a preset path.

[0138] S336: Use the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area.

[0139] Specifically, the electronic device may use the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area.

[0140] S337: Connect the first reference path and the second reference path to generate a target planning path within a preset range of the target vehicle's driving direction.

[0141] Specifically, the electronic device splices the first reference path and the second reference path to generate a target planning path within a preset range of the target vehicle's driving direction.

[0142] S34. According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the speed corresponding to the target planned path is planned to determine the target speed corresponding to the target planned path for the target vehicle to travel.

[0143] For more information about this step, see Figure 2 The introduction of S24 will not be elaborated here.

[0144] The path planning method provided by the embodiment of the present invention obtains the minimum turning distance corresponding to the target vehicle. According to each second position information, the first coordinate range occupied by each obstacle in the target coordinate system is determined, and the accuracy of the first coordinate range occupied by each obstacle in the target coordinate system is ensured. Then, the first coordinate range is widened along the horizontal axis of the target coordinate system to both sides by the minimum turning distance, and the second coordinate range occupied by each obstacle in the target coordinate system is obtained, which ensures the accuracy of the second coordinate range occupied by each obstacle in the target coordinate system, and ensures that the target vehicle can safely pass through the second coordinate range. Then, according to the first position information and the positional relationship between each second coordinate range, the first area between the target vehicle and the nearest second coordinate range or / and the second area between each second coordinate range or / and the third area between the second coordinate range closest to the end point of the preset range is determined, which ensures the accuracy of the determined first area or / and the second area or / and the third area. The first area or / and the second area or / and the third area are meshed using the first grid, which ensures the accuracy of the meshing of the first area or / and the second area or / and the third area. According to the first position information and the positional relationship between each second coordinate range, it is determined that the target vehicle passes through the fourth area corresponding to each second coordinate range, thereby ensuring the accuracy of the determined fourth area, and the fourth area is grid-divided using the second grid, thereby ensuring the accuracy of the grid division of the fourth area.

[0145] In addition, for the fourth area divided by the second grid, the area occupied by the obstacle in each second grid is eliminated to avoid collision between the target vehicle and the obstacle. According to the relationship between the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the road boundary, and the third distance from each second grid to the end point, the grid cost corresponding to each second grid is calculated to ensure the accuracy of the calculated grid cost. Then, the steering constraint cost of the target vehicle is obtained, and according to the relationship between the steering constraint cost and each grid cost, the preset path planning algorithm is used to search the grid path of the fourth area to obtain the first candidate planning path, thereby ensuring the accuracy of the obtained first candidate planning path. Then, the first candidate planning path is subjected to polynomial interpolation processing to obtain the first reference planning path, thereby ensuring the accuracy of the obtained first reference planning path.

[0146] For the first area or / and the second area or / and the third area that is grid-divided using the first grid, a preset path of the target vehicle in a preset range is obtained, and the preset path corresponding to the first area or / and the second area or / and the third area is used as the second reference path corresponding to the first area or / and the second area or / and the third area, thereby ensuring the accuracy of the second reference path corresponding to the determined first area or / and the second area or / and the third area, and splicing the first reference path and the second reference path to generate a target planning path within the preset range of the driving direction of the target vehicle, thereby ensuring the accuracy of the generated target planning path. The above method uses the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area, thereby not only ensuring the accuracy of the planned second reference path, but also reducing the amount of calculation for path planning, saving the occupancy of the computing platform as much as possible, and providing precious computing resources to a large number of perception sensor data processing and AI reasoning parts.

[0147] In one embodiment of the present application, Figure 4 As shown, a path planning method is provided, which is described by taking the method applied to an electronic device as an example, and includes the following steps:

[0148] S41, acquiring first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction.

[0149] For more information about this step, see Figure 3 The introduction of S31 will not be elaborated here.

[0150] S42: Divide the area within the preset range of the target vehicle's driving direction into grids of different sizes according to the relationship between the first position information and the second position information.

[0151] For more information about this step, see Figure 3 The introduction of S32 will not be elaborated here.

[0152] S43. According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planned path within a preset range of the target vehicle's driving direction.

[0153] For more information about this step, see Figure 3 The introduction of S33 will not be elaborated here.

[0154] S44. According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the speed corresponding to the target planned path is planned to determine the target speed corresponding to the target planned path for the target vehicle to travel.

[0155] In an optional embodiment of the present application, the above S44 "planning the speed corresponding to the target planned path according to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, and determining the target speed corresponding to the target planned path for the target vehicle to travel" may include the following steps:

[0156] S441. Using a preset speed planning algorithm, plan the speed corresponding to the target planning path to obtain a reference speed.

[0157] Specifically, the electronic device may utilize a preset speed planning algorithm to plan the speed corresponding to the target planning path to obtain a reference speed.

[0158] Among them, the speed planning algorithm can be a T-type speed planning algorithm or other speed planning algorithms. The embodiment of the present application does not specifically limit the speed planning algorithm.

[0159] S442: According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the reference speed is corrected to determine the target speed corresponding to the target planned path for the target vehicle.

[0160] Specifically, after obtaining the reference speed, the electronic device can calculate the distance from each path point in the target planned path to the nearest obstacle based on the second position information corresponding to each obstacle, and then, based on the distance from each path point in the target planned path to the nearest obstacle and the curvature of each path point in the target planned path, perform speed correction on the reference speed to determine the target speed corresponding to the target planned path of the target vehicle.

[0161] Exemplarily, the path point i in the target planning path is represented as traj(i), and its speed can be corrected using the following formula:

[0162] traj(i).v=1 / exp(d_obs)*1 / exp(kappa)*traj(i).v (2)

[0163] Among them, d_obs is the distance from the path point to the nearest obstacle, and kappa is the curvature of the path point.

[0164] S45: When a preset condition for re-planning the driving path corresponding to the target vehicle is met, the second position information corresponding to the last unprocessed obstacle is added to the next cycle for path planning.

[0165] Specifically, the electronic device can also detect in real time whether the preset conditions for re-planning the driving path corresponding to the target vehicle are met, or can periodically detect whether the preset conditions for re-planning the driving path corresponding to the target vehicle are met. Among them, the preset conditions can include the electronic device detecting again the presence of obstacles in the driving direction of the target vehicle, and can also include that the distance from the target vehicle to the end point within the preset range of the driving direction is less than or equal to a preset distance threshold, and can also include other conditions. The embodiments of the present application do not specifically limit the preset conditions.

[0166] When a preset condition for re-planning the driving path corresponding to the target vehicle is met, the electronic device adds the second position information corresponding to the last unprocessed obstacle to the next cycle for path planning.

[0167] The path planning method provided by the embodiment of the present invention uses a preset speed planning algorithm to plan the speed corresponding to the target planning path to obtain a reference speed, thereby ensuring the accuracy of the obtained reference speed. Then, according to the curvature of each path point in the target planning path and the second position information corresponding to each obstacle, the reference speed is corrected to determine the target speed corresponding to the target planning path of the target vehicle, thereby ensuring the accuracy of the generated target speed.

[0168] In addition, the path planning method provided by an embodiment of the present invention, when the preset conditions for re-planning the driving path corresponding to the target vehicle are met, adds the second position information corresponding to the last unprocessed obstacle to the next cycle for path planning, thereby ensuring the accuracy of the path planning for the next cycle.

[0169] It should be understood that although Figure 1-4 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-4 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0170] like Figure 5 As shown, this embodiment provides a path planning device, including:

[0171] An acquisition module 51 is used to acquire first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction;

[0172] A grid division module 52, used to divide the area within a preset range of the target vehicle's driving direction into grids of different sizes according to the relationship between the first position information and the second position information;

[0173] The path planning module 53 is used to perform different path planning for areas of different grid sizes according to the grid division result, and generate a target planned path within a preset range of the target vehicle's driving direction;

[0174] The speed planning module 54 is used to plan the speed corresponding to the target planned path according to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, and determine the target speed corresponding to the target planned path for the target vehicle to travel.

[0175] In one embodiment of the present application, the above-mentioned acquisition module 51 is specifically used to obtain the center point of the target vehicle, and establish a target coordinate system with the center point as the origin of the target coordinate system, the driving direction of the target vehicle as the longitudinal axis, and the horizontal axis perpendicular to the driving direction of the target vehicle; determine the first position information according to the relationship between the target coordinate system and the target vehicle; obtain the driving trajectory corresponding to each obstacle, project the driving trajectory corresponding to each obstacle to the target coordinate system, and obtain a projection list of each obstacle in the target coordinate system; analyze the projection list to determine the second position information corresponding to each obstacle in the target coordinate system.

[0176] In one embodiment of the present application, the above-mentioned grid division module 52 is specifically used to obtain the minimum turning distance corresponding to the target vehicle; determine the first coordinate range occupied by each obstacle in the target coordinate system according to each second position information; widen the first coordinate range by the minimum turning distance on both sides along the horizontal axis of the target coordinate system to obtain the second coordinate range occupied by each obstacle in the target coordinate system; determine the first area between the target vehicle and the nearest second coordinate range or / and the second area between each second coordinate range or / and the third area between the second coordinate range closest to the end point of the preset range to the end point according to the first position information and the positional relationship between each second coordinate range; grid the first area or / and the second area or / and the third area using the first grid; determine the fourth area corresponding to each second coordinate range that the target vehicle passes through according to the first position information and the positional relationship between each second coordinate range; grid the fourth area using the second grid, and the size of the second grid is smaller than the first grid.

[0177] In one embodiment of the present application, the above-mentioned path planning module 53 is specifically used to eliminate the areas occupied by obstacles in each second grid for the fourth area divided by the second grid; calculate the grid cost corresponding to each second grid according to the relationship between the first minimum distance from each second grid to the obstacle, the second minimum distance from each second grid to the road boundary, and the third distance from each second grid to the end point; obtain the steering constraint cost of the target vehicle, and according to the relationship between the steering constraint cost and the grid costs, use a preset path planning algorithm to perform a grid path search on the fourth area to obtain a first candidate planned path; perform polynomial interpolation processing on the first candidate planned path to obtain a first reference planned path.

[0178] In one embodiment of the present application, the above-mentioned path planning module 53 is specifically used to obtain a preset path of the target vehicle within a preset range for the first area or / and the second area or / and the third area divided by the first grid; use the preset path corresponding to the first area or / and the second area or / and the third area as the second reference path corresponding to the first area or / and the second area or / and the third area; splice the first reference path and the second reference path to generate a target planned path within a preset range of the target vehicle's driving direction.

[0179] In one embodiment of the present application, the speed planning module 54 is specifically used to use a preset speed planning algorithm to plan the speed corresponding to the target planned path to obtain a reference speed; based on the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the reference speed is corrected to determine the target speed corresponding to the target planned path of the target vehicle.

[0180] In one embodiment of the present application, Figure 6 As shown, the above-mentioned path planning device also includes:

[0181] The adding module 55 is used to add the second position information corresponding to the last unprocessed obstacle to the next cycle for path planning when the preset condition for re-planning the driving path corresponding to the target vehicle is met.

[0182] For the specific limitations and beneficial effects of the path planning device, please refer to the limitations of the path planning method above, which will not be repeated here. Each module in the above-mentioned path planning device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the electronic device in the form of hardware, or can be stored in the memory of the electronic device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0183] The embodiment of the present invention also provides an electronic device having the above Figure 6The path planning device shown.

[0184] like Figure 7 As shown, Figure 7 is a schematic diagram of the structure of an electronic device provided by an optional embodiment of the present invention, such as Figure 7 As shown, the electronic device may include: at least one processor 61, such as a CPU (Central Processing Unit), at least one communication interface 63, a memory 64, and at least one communication bus 62. The communication bus 62 is used to realize the connection and communication between these components. The communication interface 63 may include a display screen (Display), a keyboard (Keyboard), and the optional communication interface 63 may also include a standard wired interface and a wireless interface. The memory 64 may be a high-speed RAM memory (Random Access Memory) or a non-volatile memory (non-volatile memory), such as at least one disk storage. The memory 64 may optionally be at least one storage device located away from the aforementioned processor 61. The processor 61 may be combined with Figure 5 or Figure 6 In the described device, the memory 64 stores an application program, and the processor 61 calls the program code stored in the memory 64 to execute any of the above method steps.

[0185] The communication bus 62 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The communication bus 62 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0186] Among them, the memory 64 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviated: RAM); the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory), a hard disk drive (English: hard disk drive, abbreviated: HDD) or a solid-state drive (English: solid-state drive, abbreviated: SSD); the memory 64 may also include a combination of the above types of memory.

[0187] The processor 61 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and a NP.

[0188] The processor 61 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0189] Optionally, the memory 64 is also used to store program instructions. The processor 61 can call the program instructions to implement the present application Figures 1 to 4 The path planning method shown in the embodiment.

[0190] The embodiment of the present invention also provides a non-transitory computer storage medium, wherein the computer storage medium stores computer executable instructions, and the computer executable instructions can execute the path planning method in any of the above method embodiments. The storage medium can be a disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk (HDD) or a solid-state drive (SSD), etc.; the storage medium can also include a combination of the above types of memory.

[0191] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A path planning method, characterized in that: The method comprises: Acquire first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction; According to the relationship between the first position information and the second position information, the area within the preset range of the target vehicle's driving direction is divided into grids of different sizes; According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planning path within a preset driving direction of the target vehicle; According to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, the speed corresponding to the target planned path is planned to determine the target speed corresponding to the target vehicle traveling on the target planned path; Wherein, dividing the area within the preset range of the target vehicle's driving direction using grids of different sizes according to the relationship between the first position information and the second position information includes: Obtaining a minimum turning distance corresponding to the target vehicle; Determine, according to each of the second position information, a first coordinate range occupied by each of the obstacles in the target coordinate system; Expanding the first coordinate range by the minimum turning distance on both sides along the horizontal axis of the target coordinate system to obtain a second coordinate range occupied by each obstacle in the target coordinate system; Determine, according to the first position information and the positional relationship between each of the second coordinate ranges, a first area between the target vehicle and the second coordinate range that is closest to the target vehicle, or / and a second area between each of the second coordinate ranges, or / and a third area between the second coordinate range that is closest to the end point of the preset range and the end point; Using a first grid to divide the first area and / or the second area and / or the third area into grids; Determining, based on the first position information and the positional relationship between each of the second coordinate ranges, that the target vehicle passes through a fourth area corresponding to each of the second coordinate ranges; The fourth area is divided into grids using a second grid, wherein the size of the second grid is smaller than that of the first grid.

2. The method according to claim 1, characterized in that The obtaining of first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction includes: Obtain the center point of the target vehicle, take the center point as the origin of the target coordinate system, take the target vehicle driving direction as the longitudinal axis, and take the axis perpendicular to the target vehicle driving direction as the transverse axis to establish the target coordinate system; Determining the first position information according to the relationship between the target coordinate system and the target vehicle; Acquire the driving trajectory corresponding to each obstacle, project the driving trajectory corresponding to each obstacle to the target coordinate system, and acquire a projection list of each obstacle in the target coordinate system; The projection list is analyzed to determine the second position information corresponding to each obstacle in the target coordinate system.

3. The method according to claim 1, characterized in that According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planning path within a preset range of the target vehicle's driving direction, including: For the fourth area divided by the second grid, removing the area occupied by the obstacle in each of the second grids; Calculate the grid cost corresponding to each of the second grids according to the relationship between the first minimum distance from each of the second grids to the obstacle, the second minimum distance from each of the second grids to the road boundary, and the third distance from each of the second grids to the end point; Obtaining a steering constraint cost of the target vehicle, and performing a grid path search on the fourth area using a preset path planning algorithm according to a relationship between the steering constraint cost and each of the grid costs, to obtain a first candidate planning path; Perform polynomial interpolation processing on the first candidate planning path to obtain a first reference planning path.

4. The method according to claim 3, characterized in that According to the grid division result, different path planning is performed for areas of different grid sizes to generate a target planning path within a preset range of the target vehicle's driving direction, including: For the first area or / and the second area or / and the third area divided by the first grid, obtaining a preset path of the target vehicle within the preset range; Using the preset path corresponding to the first area or / and the second area or / and the third area as a second reference path corresponding to the first area or / and the second area or / and the third area; The first reference planned path and the second reference path are spliced ​​to generate the target planned path within a preset range of the target vehicle's driving direction.

5. The method according to claim 1, characterized in that: The method of planning a speed corresponding to the target planned path according to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, and determining a target speed corresponding to the target vehicle traveling on the target planned path, includes: Using a preset speed planning algorithm, the speed corresponding to the target planning path is planned to obtain a reference speed; The reference speed is corrected according to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, so as to determine the target speed corresponding to the target vehicle traveling along the target planned path.

6. The method according to claim 1, characterized in that The method further comprises: When a preset condition for re-planning the driving path corresponding to the target vehicle is met, the second position information corresponding to the last unprocessed obstacle is added to the next cycle for path planning.

7. A path planning device, characterized in that: The device comprises: An acquisition module, used to acquire first position information corresponding to the target vehicle in the target coordinate system and second position information corresponding to each obstacle within a preset range of the target vehicle's driving direction; A grid division module, for dividing an area within a preset range of the target vehicle's driving direction using grids of different sizes according to the relationship between the first position information and the second position information; wherein, the division of an area within a preset range of the target vehicle's driving direction using grids of different sizes according to the relationship between the first position information and the second position information comprises: obtaining a minimum turning distance corresponding to the target vehicle; determining a first coordinate range occupied by each obstacle in the target coordinate system according to each of the second position information; widening the first coordinate range to both sides along the horizontal axis of the target coordinate system by the minimum turning distance, and obtaining a second coordinate range occupied by each obstacle in the target coordinate system. According to the first position information and the positional relationship between each of the second coordinate ranges, determine the first area between the target vehicle and the second coordinate range closest to the target vehicle or / and the second area between each of the second coordinate ranges or / and the third area between the second coordinate range closest to the end point of the preset range and the end point; use the first grid to grid the first area or / and the second area or / and the third area; according to the first position information and the positional relationship between each of the second coordinate ranges, determine that the target vehicle passes through a fourth area corresponding to each of the second coordinate ranges; use the second grid to grid the fourth area, and the size of the second grid is smaller than the first grid; A path planning module, used to perform different path planning for areas of different grid sizes according to the grid division results, and generate a target planning path within a preset range of the target vehicle's driving direction; The speed planning module is used to plan the speed corresponding to the target planned path according to the curvature of each path point in the target planned path and the second position information corresponding to each obstacle, and determine the target speed corresponding to the target vehicle traveling on the target planned path.

8. An electronic device, characterized in that: It comprises a memory and a processor, wherein the memory stores computer instructions, and the processor executes the path planning method according to any one of claims 1 to 6 by executing the computer instructions.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the path planning method according to any one of claims 1 to 6.

Images