Turn-around path planning method and device, equipment and storage medium

Through the methods of segmented path sampling and heading error inspection, the turn-on path is generated and filtered, which solves the problems of computing resource occupation and time-consuming of hybrid A* algorithms, and achieves more efficient turn-on path planning.

CN119935162APending Publication Date: 2025-05-06BEIJING ZHIXINGZHE TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311386425.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-10-24
Publication Date
2025-05-06

AI Technical Summary

Technical Problem

In the existing autonomous driving technology, the hybrid A* algorithm occupies a lot of computing resources when planning a turnaround path, and the search takes a long time, which affects the planning efficiency.

Method used

The segmented arc path is used to generate segmented arc paths, and heading error inspection and collision inspection are performed when generating the paths. The arc paths that meet the requirements are selected for connections to form a turn-on path.

Benefits of technology

This method can quickly plan turn-on paths, reduce computing resource usage, improve planning efficiency, and avoid dependence on heuristic functions and path cost weights, simplifying the screening process by performing collision tests during path generation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119935162A_ABST
    Figure CN119935162A_ABST
Patent Text Reader

Abstract

The invention relates to a U-turn path planning method and device, equipment and a storage medium. The method comprises the steps that after it is determined that the mobile device needs to turn around, segmented arc paths are generated in a segmented path sampling mode, and course error checking and collision checking are conducted when the segmented arc paths are generated; selecting an arc path from each segment of the segmented arc paths meeting the heading error test and collision test requirements; and taking a path formed by connecting the selected arc paths as a planned U-turn path. According to the scheme provided by the invention, the U-turn path can be quickly planned, the occupation of computing resources is reduced, and the planning efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a U-turn path planning method, device, equipment and storage medium. Background Art

[0002] With the development and progress of science and technology, controlling the driving of vehicles through automatic control systems can bring convenience to people's travel. In recent years, autonomous driving (also known as unmanned driving) as an application scenario of artificial intelligence has become a new development direction for various transportation (especially automobile) industries.

[0003] The vehicle may encounter a scenario where it needs to turn around while performing an autonomous driving task. When the driving area available for U-turns on the road is large enough, a U-turn can be performed (that is, the vehicle drives from the current position to the U-turn target position in one go) to complete the U-turn task. When the driving area available for U-turns on the road is not large enough, the U-turn may not be able to complete the U-turn task. In this case, a multi-point U-turn is required (that is, the vehicle turns the vehicle around to the target position by alternating a combination of driving in multiple directions forward and backward in multiple directions) to complete the U-turn task. When performing a multi-point U-turn, if the intermediate parking position, driving path and / or forward-backward action switching timing are not selected reasonably, the U-turn task may not be completed or take too long.

[0004] In the related technology, a solution for U-turn using the Hybrid A* algorithm has emerged. The Hybrid A* algorithm adds the vehicle kinematic constraint (i.e., the maximum curvature constraint) to the A* search algorithm, and can search for a path connecting the start point and the end point that satisfies the vehicle kinematic constraint while considering obstacles, so that it can be applied to the U-turn task of the vehicle's automatic driving while considering obstacles.

[0005] However, the hybrid A* algorithm takes up a lot of computing resources and takes a long time to search, which affects the planning efficiency of autonomous driving tasks. Summary of the invention

[0006] In order to solve or partially solve the problems existing in the related technology, the present application provides a U-turn path planning method, device, equipment and storage medium, which can quickly plan the U-turn path, reduce computing resource usage and improve planning efficiency.

[0007] The first aspect of the present application provides a U-turn path planning method, comprising:

[0008] After determining that the mobile device needs to turn around, a segmented arc path is generated by adopting a segmented path sampling method, wherein a heading error check and a collision check are performed when the segmented arc path is generated;

[0009] Selecting an arc path for each segment of the segmented arc path that meets the requirements of the heading error test and the collision test;

[0010] The path formed by connecting the selected arc paths is used as the planned U-turn path.

[0011] In one embodiment, the step of generating a segmented arc path by adopting a segmented path sampling method includes:

[0012] The preset starting point is used as the starting point of the U-turn path, and the U-turn target point selected on the driving reference path is used as the end point. The segmented path sampling is performed based on the preset turning radius to generate a segmented arc path.

[0013] In one embodiment, the heading error check and collision check are performed when the segmented arc path is generated, including:

[0014] When generating the segmented circular arc path, it is checked that the heading error between the end point heading of the end point of the circular arc path and the reference path heading of the driving reference path is reduced;

[0015] The end point of the arc path is connected to the U-turn target point using a preset curve, and it is checked that the preset curve does not collide with an obstacle or a road boundary.

[0016] In one embodiment, the step of connecting the end point of the arc path with the U-turn target point using a preset curve includes:

[0017] The end point of the arc path is connected with the U-turn target point by using a Dubins curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve.

[0018] In one embodiment, each path segment is sampled with the end point of the last selected arc path as the starting point.

[0019] In one embodiment, each path segment is sampled to generate different arc paths along different preset directions of the mobile device.

[0020] In one embodiment, generating different arc paths along different preset directions of the mobile device respectively includes:

[0021] Four arc paths are generated along the left front, right front, left rear and right rear directions of the mobile device respectively.

[0022] In one embodiment, the step of selecting an arc path for each segment of the segmented arc path that meets the heading error check and the collision check requirements includes:

[0023] In the segmented arc path that meets the requirements of heading error inspection and collision inspection, a circular arc path with a long path length is selected for each segment.

[0024] In one embodiment, the method of taking a preset starting point as the starting point of the U-turn path and taking a U-turn target point selected on the driving reference path as the end point includes:

[0025] Taking the rear axle center of the mobile device as the starting point of the turning path,

[0026] A waypoint on the driving reference path whose distance from the starting point of the U-turn path is a preset multiple of the preset turning radius is selected as the U-turn target point, and the U-turn target point is taken as the end point.

[0027] In one embodiment, it is determined that the mobile device needs to turn around based on the heading difference between the reference path heading of the driving reference path and the heading of the mobile device itself being greater than a preset heading error threshold.

[0028] A second aspect of the present application provides a U-turn path planning device, comprising:

[0029] A sampling module, for generating a segmented arc path by adopting a segmented path sampling method after determining that the mobile device needs to turn around, wherein a heading error check and a collision check are performed when generating the segmented arc path;

[0030] A selection module, used for selecting a circular arc path in each segment of the segmented circular arc path that meets the requirements of the heading error inspection and the collision inspection;

[0031] A generation module is used to use a path formed by connecting the selected arc paths as a planned U-turn path.

[0032] In one embodiment, the sampling module comprises:

[0033] The segmented arc generation submodule is used to generate a segmented arc path by using a segmented path sampling method after determining that the mobile device needs to turn around;

[0034] The verification submodule is used to perform heading error verification and collision verification when the segmented arc generation submodule generates a segmented arc path.

[0035] In one embodiment, the segmented arc generation submodule uses a preset starting point as the starting point of the U-turn path, uses a U-turn target point selected on the driving reference path as the end point, performs segmented path sampling based on a preset turning radius, and generates a segmented arc path.

[0036] In one embodiment, when the segmented arc generation submodule generates a segmented arc path, the verification submodule verifies that the heading error between the end point heading of the arc path and the reference path heading of the driving reference path is reduced; the end point of the arc path is connected to the U-turn target point using a preset curve, and verifies that the preset curve does not collide with an obstacle or a road boundary.

[0037] In one embodiment, the check submodule connects the end point of the arc path with the U-turn target point using a preset curve, including: the check submodule connects the end point of the arc path with the U-turn target point using a Dubins curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve.

[0038] In one embodiment, the segmented arc generation submodule samples each path segment, taking the end point of the last selected arc path as the starting point.

[0039] In one embodiment, the segmented arc generation submodule samples each path segment and generates different arc paths along different preset directions of the mobile device.

[0040] In one embodiment, the segmented arc generation submodule generates different arc paths along different preset directions of the mobile device, including:

[0041] Four arc paths are generated along the left front, right front, left rear and right rear directions of the mobile device respectively.

[0042] In one embodiment, the selection module selects an arc path for each segment of the segmented arc path that meets the heading error check and the collision check requirements, including:

[0043] The selection module selects an arc path with a long path length in each segment of the segmented arc path that meets the requirements of the heading error check and the collision check.

[0044] In one embodiment, the segmented arc generation submodule uses a preset starting point as the starting point of the U-turn path and uses a U-turn target point selected on the driving reference path as the end point, including:

[0045] The segmented arc generation submodule uses the rear axle center of the mobile device as the starting point of the U-turn path.

[0046] A waypoint on the driving reference path whose distance from the starting point of the U-turn path is a preset multiple of the preset turning radius is selected as the U-turn target point, and the U-turn target point is taken as the end point.

[0047] In one embodiment, the device further comprises:

[0048] The U-turn judgment module is used to determine that the mobile device needs to turn around according to the heading difference between the reference path heading of the driving reference path and the heading of the mobile device itself being greater than a preset heading error threshold.

[0049] A third aspect of the present application provides an electronic device, including:

[0050] Processor; and

[0051] The memory stores executable codes thereon, and when the executable codes are executed by the processor, the processor is caused to execute the method as described above.

[0052] A fourth aspect of the present application provides a mobile device, comprising at least one detection device and the electronic device as described above.

[0053] A fifth aspect of the present application provides a computer-readable storage medium having executable code stored thereon. When the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described above.

[0054] The technical solution provided by this application may have the following beneficial effects:

[0055] The solution provided by the present application, after determining that the mobile device needs to turn around, is to generate a segmented arc path by using a segmented path sampling method, wherein a heading error check and a collision check are performed when the segmented arc path is generated; an arc path is selected for each segment of the segmented arc path that meets the heading error check and collision check requirements; and the path formed by connecting the selected arc paths is used as the planned turning path. The solution of the present application is to plan the turning path based on heading inspiration, and a segmented path sampling method is used to generate a segmented arc path, and then the selected arc paths are connected, and a collision check is performed when the segmented arc path is generated. The collision check does not need to rely on the heuristic function and the path cost weight, so that the turning path can be planned more quickly, and the computing resources occupied are reduced, thereby improving the planning efficiency.

[0056] Furthermore, the present application scheme is to screen the arc path based on the reduction of the heading error between the terminal heading of the arc path and the reference path heading of the driving reference path, and the screening method is simpler; a segmented arc path is generated based on a preset turning radius, such as a minimum turning radius, which simulates the operation of the driver turning the steering wheel to the limit when turning the car, and can minimize the number of turns and gear changes; in the process of generating the arc path, the end point of the arc path is connected with the turning target point using a Dubins curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve, which can further improve the efficiency of the arc path search.

[0057] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and other objects, features and advantages of the present application will become more apparent by describing in more detail exemplary embodiments of the present application in conjunction with the accompanying drawings, wherein the same reference numerals generally represent the same components in the exemplary embodiments of the present application.

[0059] Figure 1 is a flowchart of a U-turn path planning method shown in an embodiment of the present application;

[0060] Figure 2 is another flowchart of a U-turn path planning method shown in an embodiment of the present application;

[0061] Figure 3 is a schematic diagram of a heading difference between a reference path heading and a heading of a mobile device in a U-turn path planning method shown in an embodiment of the present application;

[0062] Figure 4 is a schematic diagram of selecting a preset turning radius in a U-turn path planning method shown in an embodiment of the present application;

[0063] Figure 5 It is a schematic diagram of generating different arc paths along different preset directions in the U-turn path planning method shown in an embodiment of the present application;

[0064] Figure 6 is a schematic diagram of selecting an arc path with a long path length in each segment in the U-turn path planning method shown in an embodiment of the present application;

[0065] Figure 7 is a schematic diagram of a collision with a road boundary during a collision check in a U-turn path planning method shown in an embodiment of the present application;

[0066] Figure 8 is a schematic diagram of selecting an arc path according to a heading error check and a collision check in a U-turn path planning method shown in an embodiment of the present application;

[0067] Fig. 9 is a schematic diagram of a U-turn path that is finally generated and planned in the U-turn path planning method shown in an embodiment of the present application;

[0068] Fig.10 is a structural schematic diagram of a U-turn path planning device shown in an embodiment of the present application;

[0069] Fig.11 is another structural schematic diagram of the U-turn path planning device shown in an embodiment of the present application;

[0070] Fig.12 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0071] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. Although the embodiments of the present application are shown in the accompanying drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to make the present application more thorough and complete, and to fully convey the scope of the present application to those skilled in the art.

[0072] The terms used in this application are for the purpose of describing specific embodiments only and are not intended to limit this application. The singular forms of "a", "said" and "the" used in this application and the appended claims are also intended to include plural forms unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used herein refers to and includes any or all possible combinations of one or more associated listed items.

[0073] It should be understood that although the terms "first", "second", "third", etc. may be used in this application to describe various information, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of this application, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of this application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0074] In the related art, the U-turn path planning can be realized by using the hybrid A* algorithm and other methods, but the hybrid A* algorithm occupies a lot of computing resources, the search takes a long time, and affects the planning efficiency of the autonomous driving task. In view of the above problems, the embodiment of the present application provides a U-turn path planning method, which can quickly plan the U-turn path, reduce the computing resource occupation, and improve the planning efficiency.

[0075] The technical solution of the embodiment of the present application can be applied to different products, for example, to mobile devices. Mobile devices can be, for example, vehicle devices or robot devices with the following functions: (1) Devices with manned functions, such as family cars, buses, etc. (2) Devices with cargo functions, such as ordinary trucks, vans, trailers, closed trucks, tank trucks, flatbed trucks, container trucks, dump trucks, special structure trucks, etc. (3) Devices with tool functions, such as logistics distribution vehicles, AGVs (Automated Guided Vehicles), patrol cars, cranes, cranes, excavators, bulldozers, forklifts, road rollers, loaders, off-road engineering vehicles, armored engineering vehicles, sewage treatment vehicles, sanitation vehicles, vacuum trucks, floor washing vehicles, watering trucks, sweeping robots, food delivery robots, shopping guide robots, lawn mowers, golf carts, etc. (4) Devices with entertainment functions, such as entertainment vehicles, playground automatic driving devices, balance cars, etc. (5) Devices with special rescue functions, such as fire trucks, ambulances, power repair vehicles, engineering rescue vehicles, etc. For ease of description, the following embodiments are described using the mobile device as an example of an intelligent driving or autonomous driving vehicle.

[0076] The technical solution of the embodiments of the present application is described in detail below with reference to the accompanying drawings.

[0077] Figure 1 It is a flowchart of a U-turn path planning method shown in an embodiment of the present application.

[0078] See also Figure 1 , the method comprising:

[0079] S11. After determining that the mobile device needs to turn around, a segmented circular arc path is generated by adopting a segmented path sampling method, wherein a heading error check and a collision check are performed when the segmented circular arc path is generated.

[0080] Wherein, according to the fact that the heading difference between the reference path heading of the driving reference path and the heading of the mobile device itself is greater than a preset heading error threshold, it is determined that the mobile device needs to turn around.

[0081] The segmented arc path is generated by adopting the segmented path sampling method, including: taking a preset starting point as the starting point of the U-turn path, taking a U-turn target point selected on the driving reference path as the end point, performing segmented path sampling based on a preset turning radius, and generating a segmented arc path. For example, taking the rear axle center of the mobile device as the starting point of the U-turn path, selecting a waypoint on the driving reference path that is a preset multiple of the preset turning radius from the starting point of the U-turn path as the U-turn target point, and taking the U-turn target point as the end point. The preset multiple can be, for example, 4 times but is not limited thereto.

[0082] When generating a segmented circular arc path, a heading error check and a collision check are performed, including: when generating a segmented circular arc path, checking whether the heading error between the end point heading of the end point of the circular arc path and the reference path heading of the driving reference path is reduced; connecting the end point of the circular arc path with the turning target point using a preset curve, and checking whether the preset curve collides with an obstacle or a road boundary.

[0083] The end point of the arc path is connected with the U-turn target point by using a preset curve, including: the end point of the arc path is connected with the U-turn target point by using a Dubinsi curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve.

[0084] Each path segment is sampled, with the end point of the previously selected arc path as the starting point.

[0085] Each path segment is sampled to generate different arc paths along different preset directions of the mobile device. For example, four arc paths are generated along the four directions of the mobile device, namely, the left front, the right front, the left rear, and the right rear.

[0086] S12. Select an arc path for each segment of the segmented arc path that meets the requirements of the heading error test and the collision test.

[0087] Among the segmented arc paths that meet the requirements of heading error inspection and collision inspection, a circular arc path with a long path length is selected for each segment.

[0088] S13. Use a path formed by connecting the selected arc paths as a planned U-turn path.

[0089] Since an arc path is selected for each segment of the segmented arc path, a path formed by connecting the selected arc paths can be used as a planned U-turn path.

[0090] It can be seen from this embodiment that the solution provided by the present application, after determining that the mobile device needs to turn around, uses a segmented path sampling method to generate a segmented arc path, wherein a heading error check and a collision check are performed when the segmented arc path is generated; an arc path is selected for each segment of the segmented arc path that meets the heading error check and collision check requirements; and the path formed by connecting the selected arc paths is used as the planned U-turn path. The solution of the present application is based on heading inspiration for U-turn path planning, and uses a segmented path sampling method to generate a segmented arc path, which is then connected according to the selected arc paths, and a collision check is performed when the segmented arc path is generated. The collision check does not need to rely on the heuristic function and the path cost weight, so that the U-turn path can be planned more quickly, and the computing resources occupied are also reduced, thereby improving planning efficiency.

[0091] Figure 2is another flowchart of a U-turn path planning method shown in an embodiment of the present application; Figure 2 relatively Figure 1 The solution of the present application is described in more detail. In this embodiment, the mobile device is taken as an example of a vehicle but is not limited thereto.

[0092] The present application provides a U-turn path planning method based on heading inspiration, which takes the center position of the rear axle of the vehicle as the starting point, performs segmented path sampling with a preset turning radius, such as a minimum turning radius, takes the heading difference between the vehicle and the reference path or the U-turn target point as inspiration, takes the length of the segmented arc path as a cost, and takes the road boundary or interfering obstacles as constraints, and finally generates the optimal U-turn path. The present application scheme can improve the efficiency of U-turn path planning in both general road scenarios and narrow road scenarios.

[0093] See also Figure 2 , the method comprising:

[0094] S21. Obtain information on a driving reference path of the vehicle.

[0095] This application establishes a vehicle coordinate system, in which the center of the rear axle of the vehicle is the coordinate origin, the center of the rear axle along the longitudinal direction of the front axle is the positive x direction, and the center of the rear axle along the left side of the axle is the positive y direction. At this time, the vehicle position in the vehicle coordinate system is x=0, y=0, and heading=0. Heading indicates the direction of the vehicle in the vehicle coordinate system.

[0096] In this step, the vehicle can obtain a driving reference path for the vehicle's current mission, where the driving reference path may include multiple waypoints, and information on each waypoint includes but is not limited to coordinates and heading in the vehicle coordinate system.

[0097] S22: Obtain information about obstacles or road boundaries of the vehicle.

[0098] In this step, the surrounding obstacles or road boundary information of the vehicle in the vehicle coordinate system may be obtained, and the surrounding obstacles or road boundary information may be input and represented in the form of an occupancy grid.

[0099] S23. Determine, based on the heading difference, whether the vehicle needs to turn around.

[0100] Wherein, it can be determined that the mobile device needs to turn around according to the heading difference between the reference path heading of the driving reference path and the vehicle's own heading being greater than a preset heading error threshold.

[0101] For example, the heading difference α between the reference path heading and the vehicle heading can be used to determine whether a U-turn is required. If the heading difference α exceeds the heading error threshold, a U-turn is determined to be required. Otherwise, a U-turn is not required. The heading error threshold can be determined based on experience and is not limited in this application. Figure 3 as shown in .

[0102] S24: Determine the starting point of the U-turn path and the U-turn target point.

[0103] The application may use a preset starting point as the starting point of the U-turn path, and use a U-turn target point selected on the driving reference path as the end point. For example, the center of the rear axle of the mobile device is used as the starting point of the U-turn path, and a waypoint on the driving reference path that is a preset multiple of the preset turning radius from the starting point of the U-turn path is selected as the U-turn target point, and the U-turn target point is used as the end point.

[0104] For example, the center of the rear axle of the vehicle is taken as the starting point of the U-turn path, and the U-turn target point is selected on the vehicle driving reference path, wherein the U-turn target point can be a waypoint on the vehicle driving reference path that is 4 times the minimum turning radius away from the starting point of the U-turn path, such as Figure 4 As shown in , R represents the minimum turning radius. It should be noted that 4 times is an empirical value, and other multiples can be selected, usually between 1 and 4 times.

[0105] S25. Based on the preset turning radius, different arc paths are generated along different preset directions of the vehicle, during which a heading error check and a collision check are performed.

[0106] This application can generate four arc paths based on a preset turning radius, respectively, along the left front, right front, left rear, and right rear directions of the vehicle. Among them, it can be based on the minimum turning radius of the vehicle model, and generate segmented arc paths point by point along the left front, right front, left rear, and right rear directions of the vehicle. It should be noted that the minimum turning radius varies with different vehicle models. Figure 5 As shown, the center of the rear axle of the vehicle is used as the starting point of the U-turn path. Based on the minimum turning radius of the vehicle type, an arc path is generated point by point along the left front, right front, left rear and right rear.

[0107] During the generation of the circular arc path along the four directions of the vehicle's left front, right front, left rear, and right rear, the heading error check and collision check can be performed, including: when generating a segmented circular arc path, checking that the heading error between the end heading of the end point of the circular arc path and the reference path heading of the driving reference path is reduced; connecting the end point of the circular arc path with the U-turn target point using a preset curve, and checking that the preset curve does not collide with an obstacle or a road boundary.

[0108] For example, a Dubins curve is tried to connect the end point of the arc path with the U-turn target point. If the connection is successful and the curve has no collision with the occupied grid points (ie, no collision with obstacles or road boundaries), the generation of the arc path is completed.

[0109] In the process of generating the path point by point, each generated point is checked to see if the heading error with the reference path is decreasing and a collision check is performed. Among them, the termination condition for generating the segmented arc path point by point is that the vehicle frame of the waypoint collides with the occupied grid (obstacle or road boundary) or the heading error between the waypoint and the reference path diverges. For example, when generating the path point by point, compare the heading error values ​​of the kth point and the k+1th point with the reference path heading. If the heading error △k+1 between the k+1th waypoint and the reference path is greater than the heading error △k between the kth waypoint and the reference path, then the heading error is considered to be divergent and the point-by-point path generation is terminated. Otherwise, it is considered that the heading error is continuously converging to 0 and the waypoint generation continues.

[0110] That is, the conditions for generating the arc path termination include:

[0111] 1) Path collision occurs, such as the car model at the waypoint collides with the edge of the road boundary, for example Figure 5 The path shown by the green arc path 51 collides with the edge of the road boundary.

[0112] During this period, you can try to connect the U-turn target point with the Dubins curve every 0.5 meters. If there is no collision with the Dubins curve, the U-turn is successful, otherwise continue to generate an arc path. Figure 7 The path shown by the red path 71 is a path that collides with the road side, that is, the road boundary. It should be noted that 0.5 meters is an empirical value and can be other values.

[0113] 2) The error between the heading of the arc path end point and the heading of the reference path increases, such as Figure 5 In the path shown by the red arc path 52, the heading error between the end point of the arc path and the reference path heading increases.

[0114] S26. Select an arc path with a long path length from the arc paths that meet the requirements of the heading error test and the collision test.

[0115] Among them, if all of the four generated arc paths meet the requirements of heading error check and collision check, the arc path with the longer length among the four paths can be selected, for example, the longest path can be selected. It should be noted that among the arc paths that meet the requirements of heading error check and collision check, the arc path with the second longest path length can also be selected. If only three of the four generated arc paths meet the requirements of heading error check and collision check, the arc path with the longer length can be selected from the three paths, for example, the longest path can be selected.

[0116] Among them, Figure 6 As shown, the circular arc path 61 with the longest length can be selected as the local path of the U-turn path among the circular arc paths that meet the requirements of the heading error check and the collision check.

[0117] S27, taking the end point of the arc path selected in the previous section as the starting point, continue to generate different arc paths along different preset directions of the vehicle, perform heading error check and collision check, and return to S26, wherein after the arc path generation is completed, enter S28.

[0118] The end point of the arc path selected in S26 may be used as the starting point of the new segmented arc path. That is, the end point of the arc path selected in the previous segment is used as the starting point of the next segment of the arc path, and the arc paths are generated point by point along the left front, right front, left rear and right rear, and the heading error check and collision check are performed at the same time. The longest arc path is selected, such as Figure 8 Path 81 is shown by the green dashed line. Figure 8 In the figure, both the right rear and left rear arc paths collide, and the heading error between the right front arc path and the reference path increases, so the left front arc path 81 is selected.

[0119] S28. After the arc path generation is completed, a path formed by connecting the selected arc paths is used as a planned U-turn path.

[0120] Through the above process, a complete U-turn path can be finally generated, such as Fig. 9 The green path 91 in the middle is the final planned U-turn path. That is, after the arc path generation is completed, the path formed by connecting the selected arc paths is used as the planned U-turn path.

[0121] It should be noted that, in addition to the Dubinsi curve connection method, the curve type used to connect the U-turn endpoints in this application can also be connected by other forms of smooth curves such as Bezier curves, Reeds-Shepp curves, polynomial curves (such as quintic polynomial curves), etc. The Reeds-Shepp curve is composed of several arcs or straight line segments with fixed radii, and the radius of the arc is generally the minimum turning radius of the car.

[0122] To summarize the above description, the present application is inspired by the reduction of the heading error value between the arc path and the reference path to screen the U-turn arc path; the U-turn arc path is generated with the minimum turning radius, which is the key point to minimize the number of U-turn gear shifts; in the process of generating the arc path, the Dubins curve is tried to connect the U-turn end points to improve the search efficiency. Therefore, the U-turn path planning method based on heading inspiration is adopted to generate the arc path according to the minimum turning radius, which can simulate the operation of the driver turning the steering wheel to the end when turning the car, thereby minimizing the number of reverse gear shifts. Using the present application scheme, theoretically all roads that are greater than the vehicle length + collision safety distance width can complete the U-turn path planning, so it is more advantageous to turn around in narrow roads; compared with the search algorithm of the related technology, the planning efficiency is higher.

[0123] Corresponding to the aforementioned application function implementation method embodiment, the present application also provides a U-turn path planning device, an electronic device and corresponding embodiments.

[0124] Fig.10 It is a schematic diagram of the structure of the U-turn path planning device shown in an embodiment of the present application.

[0125] See also Fig.10 The present application provides a U-turn path planning device 100, comprising: a sampling module 101, a selection module 102, and a generation module 103.

[0126] The sampling module 101 is used to generate a segmented arc path by adopting a segmented path sampling method after determining that the mobile device needs to turn around, wherein a heading error check and a collision check are performed when the segmented arc path is generated;

[0127] A selection module 102, configured to select an arc path from each segment of the segmented arc path that meets the requirements of the heading error test and the collision test;

[0128] The generating module 103 is used to use a path formed by connecting the selected arc paths as a planned U-turn path.

[0129] Fig.11 It is another structural schematic diagram of the U-turn path planning device shown in an embodiment of the present application.

[0130] See also Fig.11 The present application provides a U-turn path planning device 100, comprising: a sampling module 101, a selection module 102, a generation module 103, and a U-turn judgment module 104.

[0131] The sampling module 101 includes: a segmented arc generation submodule 1011 and a verification submodule 1012 .

[0132] The segmented arc generation submodule 1011 is used to generate a segmented arc path by adopting a segmented path sampling method after determining that the mobile device needs to turn around;

[0133] The verification submodule 1012 is used to perform heading error verification and collision verification when the segmented arc generation submodule generates the segmented arc path.

[0134] The segmented arc generation submodule 1011 uses a preset starting point as the starting point of the U-turn path, uses a U-turn target point selected on the driving reference path as the end point, performs segmented path sampling based on a preset turning radius, and generates a segmented arc path.

[0135] Among them, when the segmented arc generation submodule 1011 generates a segmented arc path, the verification submodule 1012 checks whether the heading error between the end point heading of the arc path and the reference path heading of the driving reference path is reduced; the end point of the arc path is connected to the turning target point with a preset curve, and checks whether the preset curve collides with an obstacle or a road boundary.

[0136] The check submodule 1012 connects the end point of the arc path with the U-turn target point using a preset curve, including: the check submodule connects the end point of the arc path with the U-turn target point using a Dubinsi curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve.

[0137] The segmented arc generation submodule 1011 samples each path segment, taking the end point of the last selected arc path as the starting point.

[0138] The segmented arc generation submodule 1011 samples each path segment and generates different arc paths along different preset directions of the mobile device.

[0139] The segmented arc generation submodule 1011 generates different arc paths along different preset directions of the mobile device, including: generating four arc paths along the four directions of the mobile device: left front, right front, left rear, and right rear.

[0140] Among them, the selection module 102 selects an arc path for each segment of the segmented arc path that meets the heading error test and collision test requirements, including: the selection module 102 selects an arc path with a long path length for each segment of the segmented arc path that meets the heading error test and collision test requirements.

[0141] The segmented arc generation submodule 1011 uses the preset starting point as the starting point of the U-turn path and the U-turn target point selected on the driving reference path as the end point, including: the segmented arc generation submodule 1011 uses the rear axle center of the mobile device as the starting point of the U-turn path, selects a waypoint on the driving reference path that is a preset multiple of the preset turning radius from the starting point of the U-turn path as the U-turn target point, and uses the U-turn target point as the end point. For example, the waypoint on the driving reference path of the vehicle that is 4 times the minimum turning radius away from the starting point of the U-turn path can be used as the U-turn target point.

[0142] The U-turn judgment module 104 is used to determine that the mobile device needs to turn around according to the difference between the reference path heading of the driving reference path and the heading of the mobile device itself being greater than a preset heading error threshold. Among them, it can be determined whether a U-turn is needed based on the heading difference α between the reference path heading and the heading of the vehicle. If the heading difference α exceeds the heading error threshold, it is determined that a U-turn is needed, otherwise, a U-turn is not needed. The heading error threshold can be determined based on experience, and this application does not limit it.

[0143] From the above embodiments, it can be seen that the device provided by the present application, after determining that the mobile device needs to turn around, uses a segmented path sampling method to generate a segmented arc path, wherein a heading error check and a collision check are performed when the segmented arc path is generated; an arc path is selected for each segment of the segmented arc path that meets the heading error check and collision check requirements; and the path formed by connecting the selected arc paths is used as the planned turning path. The present application scheme is based on heading inspiration for U-turn path planning, and uses a segmented path sampling method to generate a segmented arc path, which is then connected according to the selected arc paths, and a collision check is performed when the segmented arc path is generated. The collision check does not need to rely on the heuristic function and the path cost weight, so that the U-turn path can be planned more quickly, and the computing resources occupied are also reduced, thereby improving planning efficiency. Furthermore, the present application scheme is to screen the arc path based on the reduction of the heading error between the terminal heading of the arc path and the reference path heading of the driving reference path, and the screening method is simpler; a segmented arc path is generated based on a preset turning radius, such as a minimum turning radius, which simulates the operation of the driver turning the steering wheel to the limit when turning the car, and can minimize the number of turns and gear changes; in the process of generating the arc path, the end point of the arc path and the turning target point are connected using a Dubinsi curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve, which can further improve the efficiency of the arc path search.

[0144] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated again here.

[0145] Fig.12 It is a schematic diagram of the structure of an electronic device shown in an embodiment of the present application.

[0146] See also Fig.12 , the electronic device 1000 includes a memory 1010 and a processor 1020 .

[0147] The processor 1020 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0148] The memory 1010 may include various types of storage units, such as system memory, read-only memory (ROM), and permanent storage devices. Among them, ROM can store static data or instructions required by the processor 1020 or other modules of the computer. The permanent storage device may be a readable and writable storage device. The permanent storage device may be a non-volatile storage device that does not lose the stored instructions and data even after the computer is powered off. In some embodiments, the permanent storage device uses a large-capacity storage device (such as a magnetic or optical disk, flash memory) as a permanent storage device. In some other embodiments, the permanent storage device may be a removable storage device (such as a floppy disk, optical drive). The system memory may be a readable and writable storage device or a volatile readable and writable storage device, such as a dynamic random access memory. The system memory may store some or all instructions and data required by the processor at run time. In addition, the memory 1010 may include any combination of computer-readable storage media, including various types of semiconductor storage chips (such as DRAM, SRAM, SDRAM, flash memory, programmable read-only memory), and disks and / or optical disks may also be used. In some embodiments, the memory 1010 may include a readable and / or writable removable storage device, such as a laser disc (CD), a read-only digital versatile disc (such as a DVD-ROM, a double-layer DVD-ROM), a read-only Blu-ray disc, an ultra-density optical disc, a flash memory card (such as an SD card, a mini SD card, a Micro-SD card, etc.), a magnetic floppy disk, etc. The computer-readable storage medium does not include carrier waves and transient electronic signals transmitted wirelessly or wired.

[0149] The memory 1010 stores executable codes, and when the executable codes are processed by the processor 1020 , the processor 1020 can execute part or all of the methods described above.

[0150] The present application also provides a mobile device, comprising at least one detection device and the electronic device 1000 as described above.

[0151] In addition, the method according to the present application may also be implemented as a computer program or a computer program product, which includes computer program code instructions for executing some or all of the steps in the above method of the present application.

[0152] Alternatively, the present application can also be implemented as a computer-readable storage medium (or non-transitory machine-readable storage medium or machine-readable storage medium) on which executable code (or computer program or computer instruction code) is stored. When the executable code (or computer program or computer instruction code) is executed by a processor of an electronic device (or server, etc.), the processor executes part or all of the steps of the above-mentioned method according to the present application.

[0153] The embodiments of the present application have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A U-turn path planning method, characterized in that: include: After determining that the mobile device needs to turn around, a segmented arc path is generated by adopting a segmented path sampling method, wherein a heading error check and a collision check are performed when the segmented arc path is generated; Selecting an arc path for each segment of the segmented arc path that meets the requirements of the heading error test and the collision test; The path formed by connecting the selected arc paths is used as the planned U-turn path.

2. The method according to claim 1, characterized in that The step of generating a segmented arc path by adopting a segmented path sampling method includes: The preset starting point is used as the starting point of the U-turn path, and the U-turn target point selected on the driving reference path is used as the end point. The segmented path sampling is performed based on the preset turning radius to generate a segmented arc path.

3. The method according to claim 2, characterized in that The heading error check and collision check are performed when the segmented arc path is generated, including: When generating the segmented circular arc path, it is checked that the heading error between the end point heading of the end point of the circular arc path and the reference path heading of the driving reference path is reduced; The end point of the arc path is connected to the U-turn target point using a preset curve, and it is checked that the preset curve does not collide with an obstacle or a road boundary.

4. The method according to claim 3, characterized in that The step of connecting the end point of the arc path with the U-turn target point by using a preset curve comprises: The end point of the arc path is connected with the U-turn target point by using a Dubins curve, a Bezier curve, a Reeds-Shepp curve or a polynomial curve.

5. The method according to claim 1, characterized in that: Each path segment is sampled, with the end point of the previously selected arc path as the starting point.

6. The method according to claim 1, characterized in that: Each path segment is sampled to generate different arc paths along different preset directions of the mobile device.

7. The method according to claim 6, characterized in that The generating different arc paths along different preset directions of the mobile device respectively includes: Four arc paths are generated along the left front, right front, left rear and right rear directions of the mobile device respectively.

8. The method according to claim 1, characterized in that The step of selecting an arc path for each segment of the segmented arc path that meets the heading error inspection and collision inspection requirements comprises: In the segmented arc path that meets the requirements of heading error inspection and collision inspection, a circular arc path with a long path length is selected for each segment.

9. The method according to any one of claims 2 to 8, characterized in that: The method of taking the preset starting point as the starting point of the U-turn path and taking the U-turn target point selected on the driving reference path as the end point includes: Taking the rear axle center of the mobile device as the starting point of the turning path, A waypoint on the driving reference path whose distance from the starting point of the U-turn path is a preset multiple of the preset turning radius is selected as the U-turn target point, and the U-turn target point is taken as the end point.

10. The method according to any one of claims 2 to 8, characterized in that: According to the heading difference between the reference path heading of the driving reference path and the heading of the mobile device itself being greater than a preset heading error threshold, it is determined that the mobile device needs to turn around.

11. A U-turn path planning device, characterized in that: include: A sampling module, for generating a segmented arc path by adopting a segmented path sampling method after determining that the mobile device needs to turn around, wherein a heading error check and a collision check are performed when generating the segmented arc path; A selection module, used for selecting a circular arc path in each segment of the segmented circular arc path that meets the requirements of the heading error inspection and the collision inspection; A generation module is used to use a path formed by connecting the selected arc paths as a planned U-turn path.

12. An electronic device, characterized in that: include: processor; as well as A memory having executable codes stored thereon, which, when executed by the processor, causes the processor to execute the method according to any one of claims 1 to 10.

13. A mobile device, characterized in that: The electronic device comprises at least one detection device and the electronic device as claimed in claim 12.

14. A computer-readable storage medium having executable codes stored thereon, which, when executed by a processor of an electronic device, causes the processor to execute the method according to any one of claims 1 to 10.