A path planning method, device, equipment and medium

By combining the vehicle driving speed and coordinate values ​​in the target coordinate system and combined with horizontal and vertical planning, the problem of paths and speeds in the prior art is solved, and more accurate path planning and reduced calculation amount are achieved.

CN118565505BActive Publication Date: 2024-11-01IMOTION AUTOMOTIVE TECH (SUZHOU) CO LTD +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411020117.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-29
Publication Date
2024-11-01
Estimated Expiration
2044-07-29

AI Technical Summary

Technical Problem

The existing path planning algorithm separates horizontal planning from vertical planning, resulting in inconsistency between paths and speeds, and may cause deviations or no solution to path planning. At the same time, the algorithm for horizontal and vertical planning coupled has a large amount of calculation.

Method used

By combining the vehicle's driving speed, longitudinal and transverse coordinate values ​​in the target coordinate system, the bypass space area corresponding to the obstacle is determined and the path is re-planned, thereby combining horizontal and vertical planning, reducing the path planning area and reducing the calculation amount.

Benefits of technology

The path shape and vehicle driving speed are achieved simultaneously, which improves the accuracy of path planning, reduces the amount of calculation, and avoids the situation where path planning is unsolvable.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118565505B_ABST
    Figure CN118565505B_ABST
Patent Text Reader

Abstract

The present application discloses a path planning method, device, equipment and medium, which relates to the field of path planning, including: if an obstacle is detected on the current path during driving, then the detour space area corresponding to the obstacle is determined in the target coordinate system; the coordinates of each coordinate point in the target coordinate system include the vehicle's driving speed, the coordinate value in the first direction and the coordinate value in the second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle; the new path starting point and path end point of the vehicle when the obstacle is detected are determined in the target coordinate system; based on the path starting point, path end point and detour space area, the target path from the path starting point to the path end point is planned in the target coordinate system. The present application can simultaneously plan the path shape and the driving speed at each position on the path in combination with horizontal and vertical planning, and the introduction of the detour space area corresponding to the obstacle can reduce the path planning area and reduce the amount of calculation.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

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

[0002] The current path planning algorithm mainly separates lateral planning from longitudinal planning, that is, the shape of the path can be determined by lateral planning first, and the speed state of movement on this path shape can be determined by longitudinal planning. Then, the shape of the path and the speed state of movement on this path shape are combined to obtain the driving path and the movement speed at each position on the path. However, separating lateral planning from longitudinal planning can easily make the planned path and movement speed not correspond well, that is, there may be deviations, and even the situation where path planning has no solution. The current method of separating lateral planning from longitudinal planning is because the algorithm that couples lateral planning with longitudinal planning faces a relatively large amount of calculation. Summary of the invention

[0003] In view of this, the purpose of the present invention is to provide a path planning method, device, equipment and medium, which can combine horizontal and vertical planning to simultaneously plan the shape of the path and the vehicle speed at each position on the path, and introduce detour space areas corresponding to obstacles, which can reduce the area of ​​path planning, thereby reducing the calculation amount of path planning. The specific scheme is as follows:

[0004] In a first aspect, the present application provides a path planning method, comprising:

[0005] If an obstacle is detected on the current path during driving, a detour space area corresponding to the obstacle is determined in the target coordinate system; the coordinates of each coordinate point in the target coordinate system include the vehicle driving speed, the coordinate value in the first direction, and the coordinate value in the second direction; the first direction is parallel to the front direction of the vehicle when the obstacle is detected, and the second direction is perpendicular to the front direction of the vehicle;

[0006] Determining, in the target coordinate system, a new path start point and a path end point of the ego vehicle when an obstacle is detected;

[0007] In the target coordinate system, path planning areas from the path starting point to the detour space area and from the detour space area to the path end point are respectively determined, and a target path from the path starting point to the path end point is planned based on the path planning area and the detour space area.

[0008] Optionally, determining the path planning area from the path starting point to the detour space area and from the detour space area to the path ending point in the target coordinate system respectively includes:

[0009] Determine, from the bypass space area, a first spatial point with the smallest coordinate value and a second spatial point with the largest coordinate value in the first direction;

[0010] In the target coordinate system, a first path planning area is determined based on a first line from the path starting point to the first spatial point, and a second path planning area is determined based on a second line from the second spatial point to the path ending point.

[0011] Optionally, planning a target path from the path starting point to the path ending point based on the path planning area and the detour space area includes:

[0012] In the first path planning area, points are scattered based on the first connection line, and a first sub-path is determined based on the cost value of each path point obtained by the scattered points; in the second path planning area, points are scattered based on the second connection line, and a second sub-path is determined based on the cost value of each path point obtained by the scattered points;

[0013] Based on preset lateral and longitudinal acceleration and deceleration thresholds, points are scattered in the detour space area, so as to determine a third sub-path from the first spatial point to the second spatial point based on the cost value of each path point obtained by the scattered points;

[0014] A target path from the path start point to the path end point is determined based on the first sub-path, the second sub-path, and the third sub-path.

[0015] Optionally, scattering points in the detour space area based on preset lateral and longitudinal acceleration and deceleration thresholds to determine a third subpath from the first spatial point to the second spatial point based on the cost value of each path point obtained by scattering the points includes:

[0016] Determine the first spatial point as the current target spatial point, and trigger a plane determination operation to determine a current motion plane within a unit time at the current target spatial point based on preset lateral and longitudinal acceleration and deceleration thresholds;

[0017] Points are scattered in the overlapping area of ​​the bypass space area and the current motion plane, and the path point with the smallest cost value among the several path points obtained by scattering the points is determined as the new current target space point, and then the plane determination operation is jumped to until the current target space point is the second space point, so as to determine the third sub-path based on all target space points.

[0018] Optionally, the method further includes:

[0019] Determine a cost value of the waypoint based on a distance parameter and a speed parameter at the waypoint, a width of a lane where the waypoint is located, and a time loss corresponding to the waypoint;

[0020] Among them, the distance parameters include a first distance from the path point to the path end point, a second distance from the lane line when the vehicle is at the path point, and the minimum lateral and longitudinal distances from surrounding obstacles; the speed parameters include the preset lateral and longitudinal acceleration and deceleration thresholds, the upper limit of the road speed, the lateral and longitudinal acceleration of the vehicle at the path point, and the vehicle speed; the time loss is the difference between the driving time from the path starting point to the path end point through the path point and the driving time from the path starting point to the path end point along the current path.

[0021] Optionally, planning a target path from the path starting point to the path ending point based on the path planning area and the detour space area includes:

[0022] If the initial path from the path starting point to the path ending point planned based on the path planning area and the detour space area is offset in the second direction relative to the current path, determining an extreme path point with the largest offset from the initial path;

[0023] Performing path planning in a first plane region determined in the target coordinate system based on the extreme path point, the path starting point, and the initial path to obtain a first smooth path, and performing path planning in a second plane region determined in the target coordinate system based on the extreme path point, the path ending point, and the initial path to obtain a second smooth path;

[0024] The target path is determined based on the first smooth path and the second smooth path.

[0025] Optionally, the method further includes:

[0026] If the extreme value path point is located on an adjacent lane of the lane where the path end point is located, then determining an adjacent lane end point corresponding to the path end point on the adjacent lane;

[0027] Planning a first adjacent lane path from the extreme path point to the adjacent lane end point, and determining the adjacent lane path based on the first adjacent lane path and a second adjacent lane path on the target path from the path start point to the extreme path point;

[0028] A path with the smallest path cost is selected from the adjacent lane path and the target path as the optimal path, so as to control the vehicle to travel along the optimal path.

[0029] Optionally, determining the detour space area corresponding to the obstacle in the target coordinate system includes:

[0030] A speed difference between a travel speed of the obstacle and a travel speed of the vehicle corresponding to the path starting point is determined, and a detour space area corresponding to the obstacle is determined in a target coordinate system based on the speed difference.

[0031] In a second aspect, the present application provides a path planning device, comprising:

[0032] A detour area determination module, for determining a detour space area corresponding to an obstacle on the current path if the obstacle is detected during driving, in a target coordinate system; the coordinates of each coordinate point in the target coordinate system include the vehicle driving speed, a coordinate value in a first direction, and a coordinate value in a second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle;

[0033] A starting and ending point determination module, used to determine the new path starting point and path ending point of the vehicle in the target coordinate system when an obstacle is detected;

[0034] A path planning module is used to determine the path planning areas from the path starting point to the detour space area and from the detour space area to the path end point in the target coordinate system, and plan the target path from the path starting point to the path end point based on the path planning areas and the detour space area.

[0035] In a third aspect, the present application provides an electronic device, including:

[0036] Memory, used to store computer programs;

[0037] A processor is used to execute the computer program to implement the aforementioned path planning method.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, which implements the aforementioned path planning method when executed by a processor.

[0039] In the present application, if an obstacle is detected on the current path during driving, a detour space area corresponding to the obstacle is determined in the target coordinate system; the coordinates of each coordinate point in the target coordinate system include the vehicle's driving speed, a coordinate value in a first direction, and a coordinate value in a second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle; the new path starting point and path end point of the vehicle when the obstacle is detected are determined in the target coordinate system; the path planning areas from the path starting point to the detour space area and from the detour space area to the path end point are respectively determined in the target coordinate system, and the target path from the path starting point to the path end point is planned based on the path planning area and the detour space area. It can be seen that the present application constructs a target coordinate system based on the vehicle's driving speed, the coordinate value in the first direction and the coordinate value in the second direction, wherein the coordinate value in the first direction represents the longitudinal position of the vehicle in a direction parallel to the direction of the front of the vehicle when the obstacle is detected, and the coordinate value in the second direction represents the lateral position of the vehicle in a direction perpendicular to the direction of the front of the vehicle, thereby performing path planning in the target coordinate system to combine lateral planning and longitudinal planning, so that the decided target path has actual physical meaning, and the shape of the path and the vehicle driving speed at each position on the path can be planned at the same time, and the decided target path can be made more accurate; and the present application performs path planning in the target coordinate system based on the detour space area corresponding to the obstacle, thereby avoiding path planning in the entire coordinate system, and reducing the amount of calculation for path planning by reducing the area for path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0041] Figure 1 A flow chart of a path planning method disclosed in this application;

[0042] Figure 2 A scene diagram disclosed in the present application when a vehicle detects an obstacle during driving;

[0043] Figure 3 A schematic diagram of a target coordinate system vxy disclosed in this application;

[0044] Figure 4 A schematic diagram of a vy coordinate system disclosed in this application;

[0045] Figure 5 A schematic diagram of an xy coordinate system disclosed in this application;

[0046] Fig. 6A A schematic diagram of a vehicle longitudinal motion planning disclosed in this application;

[0047] Figure 6B A schematic diagram of a vehicle horizontal and vertical combination planning disclosed in this application;

[0048] Figure 7 A schematic diagram of a motion plane of a vehicle disclosed in the present application within a unit time;

[0049] Figure 8 A schematic diagram of a region disclosed in this application;

[0050] Fig. 9 A specific path planning method flow chart disclosed in this application;

[0051] Fig.10 A schematic diagram of path smoothing disclosed in this application;

[0052] Fig.11 This is a schematic diagram of the structure of a path planning device disclosed in this application;

[0053] Fig.12 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] Separating lateral planning from longitudinal planning can easily lead to the planned path and movement speed not being well matched, that is, there may be deviations, or even the situation where path planning has no solution; but the algorithm for coupling lateral planning with longitudinal planning faces a relatively large amount of calculation. To this end, the present application provides a path planning method, which can simultaneously plan the shape of the path and the vehicle speed at each position on the path by combining lateral and longitudinal planning, and introduces a detour space area corresponding to the obstacle, which can reduce the area of ​​path planning, thereby reducing the amount of calculation for path planning.

[0056] See also Figure 1 As shown, an embodiment of the present invention discloses a path planning method, including:

[0057] Step S11: If an obstacle is detected on the current path during driving, a detour space area corresponding to the obstacle is determined in the target coordinate system; the coordinates of each coordinate point in the target coordinate system include the vehicle's driving speed, a coordinate value in a first direction, and a coordinate value in a second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle.

[0058] In this embodiment, if the vehicle detects an obstacle on the current path during driving, and if the vehicle continues to drive along the current path, it is very likely to collide with the obstacle, then it is necessary to re-plan the path based on the obstacle. In order to reduce the amount of calculation for path planning, this embodiment determines the detour space area corresponding to the obstacle in the target coordinate system, and then performs path planning based on the detour space area, thereby narrowing the scope of path planning. It should be noted that if the vehicle does not detect an obstacle on the current path during driving, it will continue to drive along the current path.

[0059] Among them, when the vehicle is traveling along the current path, it can be traveling at a constant speed or at a variable speed; for constant speed driving, the vehicle speed can be either a pre-set speed or the maximum or minimum speed limit of the current road, which is not limited here.

[0060] by Figure 2 For example, Figure 2 In the figure, A is the vehicle, B is the obstacle, and the three dots are the center points of each lane. If vehicle A detects that obstacle B has changed lanes from the right lane to the middle lane while driving with the center point of the middle lane as the end point of the path, that is, the vehicle detects obstacle B on the current path during driving, then if vehicle A continues to drive along the current path, it is very likely to collide with obstacle B, so vehicle A needs to replan the path.

[0061] For the construction of the target coordinate system, such as Figure 3 As shown, the vehicle speed is the v axis; the first direction parallel to the front direction of the vehicle A when the obstacle B is detected is the y axis; the second direction perpendicular to the front direction of the vehicle A is the x axis; it should be noted that the x axis, y axis, and z axis in the target coordinate system are perpendicular to each other. Among them, the coordinate value in the first direction represents the longitudinal position of the vehicle in the first direction, and the coordinate value in the second direction represents the lateral position of the vehicle in the second direction. And, if the vehicle and the obstacle have the same driving speed when the vehicle detects an obstacle, the vehicle and the obstacle belong to the same speed plane.

[0062] like Figure 4As shown, the movement of the vehicle in the first direction (longitudinal) can be planned on the vy plane in the target coordinate system. For each vehicle speed (taking 80km / h as an example), points with an interval of Δt*v are evenly distributed. Among them, the physical reason for Δt*v is that the program operation has a cycle. Δt represents a cycle of program operation (for example, 20ms), v is the vehicle speed, and Δt*v represents the distance that can be traveled within Δt time at the vehicle speed v. Assuming that vehicle a is traveling at a constant speed of 80km / h, it should be expressed in the vy plane as a straight line parallel to the y-axis with a v scale of 80km / h. Therefore, Δt*v has actual physical meaning in the target coordinate system. Correspondingly, at different vehicle speeds, such as Figure 4 As shown in the figure, the vehicle speed v with a scale of 40km / h can also be divided into countless points, but the spacing is half of the spacing of the vehicle speed of 80km / h. Therefore, as v increases, the spacing between points in the macroscopic vy coordinate system will also increase.

[0063] Consider one of the working conditions, the vehicle is changing speed. Figure 4 For example, the vehicle's speed at time t0 is 80km / h, which corresponds to the starting point l1 in the vy coordinate system. The vehicle's speed at time t1 is 75km / h, which corresponds to point l2 in the vy coordinate system. When the vehicle's speed drops from 80km / h to 75km / h at time t1, it should descend from the starting point l1 to point l2 along arrow s1. The y coordinate of point l2 should be the y coordinate of the starting point l1 plus Δt*v (v=75km / h). Similarly, it can also descend from the starting point l1 to point l3 with a vehicle speed of v=40km / h along arrow s2. It should be noted that the direction of the arrow, that is, the slope, corresponds to the acceleration of the vehicle, which is the rate of change of speed per unit time (Δt). According to actual conditions, the general vehicle actuator has a maximum allowable acceleration and deceleration, which is the maximum slope of the arrow in the vy coordinate system.

[0064] Figure 4 The vehicle is described in the first direction, that is, in the longitudinal direction. Figure 5 As shown, adjusting the vy coordinate system to the yx coordinate system can represent the movement of the vehicle in the second direction, that is, the movement in the lateral direction. Taking l2 as the starting point, the inverse of the slope pointed by arrows s3 and s4 corresponds to the lateral acceleration of the vehicle per unit time (Δt).

[0065] Combining the vy coordinate system and the yx coordinate system, we can see that: Fig. 6AIt represents a unit time (Δt) plan that does not consider the lateral movement of the vehicle. The starting point (i.e., the point corresponding to y0) can reach point 1 and point 2. Point 1 corresponds to the maximum deceleration within the unit time allowed by the vehicle actuator, and point 2 corresponds to the maximum acceleration within the unit time allowed by the vehicle actuator. Theoretically, all values within this range can be任选 as the planned speed for the next unit time. It should be noted that since the y1 value corresponding to point 1 is different from the y2 value corresponding to point 2, the acceleration and deceleration corresponding to point 1 and point 2 are different, so the distances traveled within the unit time are also different, and the y2 value during acceleration is greater than the y1 value during deceleration. Figure 6B It is a unit time (Δt) plan that considers both the lateral movement and the longitudinal movement of the vehicle. Taking Figure 6B point 2 in [reference] as an example, project point 2 onto the xy coordinate system, and the longitudinal displacement of the vehicle within the unit time can be obtained as y2 - y0, and the lateral displacement is x0.

[0066] As Figure 7 shown, combining the preset lateral and longitudinal acceleration and deceleration thresholds (including the preset lateral acceleration and deceleration thresholds and the preset longitudinal acceleration and deceleration thresholds), the motion plane of the vehicle within the unit time can be obtained in the target coordinate system. Among them, the lower arcs corresponding to y1 and y2 are on the same speed plane, and the upper arcs corresponding to y3 and y4 are on the same speed plane, and y1 < y2 < y3 < y4. It should be noted that x1 < x2 < x3 < x4, but |x1| = |x4|, |x2| = |x3|, that is, the preset lateral acceleration threshold and the preset lateral deceleration threshold are the same. And y2 to y4 is the range of the longitudinal position interval that the vehicle can reach when traveling along the y-axis at the preset longitudinal acceleration and deceleration thresholds within the unit time. After combining the lateral movement and the longitudinal movement of the vehicle, if the vehicle travels at the preset lateral acceleration and deceleration thresholds and the preset longitudinal acceleration threshold within the unit time, it can reach the coordinate point corresponding to the y3 coordinate value; if the vehicle travels at the preset lateral acceleration and deceleration thresholds and the preset longitudinal deceleration threshold within the unit time, it can reach the coordinate point corresponding to the y1 coordinate value. Therefore, the motion plane of the vehicle within the unit time is approximately a curvilinear trapezoid as Figure 7 shown.

[0067] In this embodiment, for the bypass space area corresponding to the obstacle in the target coordinate system, the bypass space area corresponding to the obstacle can be determined in the target coordinate system based on the vehicle driving speed corresponding to the path starting point and the driving speed of the obstacle, that is, the bypass space area is a three-dimensional space area. For the convenience of understanding, the bypass space area can be mapped onto the xy plane in the target coordinate system, Figure 8 which is the mapped plane area obtained by mapping the bypass space area onto the xy plane in the target coordinate system. Figure 8 The rectangle in is an obstacle, the area between the obstacle and the blank ellipse is a dangerous area, and the area between the blank ellipse and the shaded ellipse is a detour area. The dangerous area indicates an area where the vehicle is not allowed to enter, that is, the vehicle is very likely to collide with an obstacle when driving in the dangerous area; the detour area indicates an area where the vehicle is allowed to enter. l1, l3 in the dangerous area and l2, l4 in the detour area can be calibrated quantities, that is, these four values ​​can be preset. d1, d3 in the dangerous area and d2, d4 in the detour area are quantities related to the speed difference, where the speed difference is the difference between the speed of the obstacle and the speed of the vehicle corresponding to the starting point of the path, and the larger the speed difference, the larger d1, d3, d2, d4, and the smaller the speed difference, the smaller d1, d3, d2, d4. It should be noted that the speed of the obstacle is lower than the speed of the vehicle. The main reason is that the obstacle is an obstacle on the current path detected by the vehicle during driving, and if the vehicle continues to drive along the current path, it is very likely to collide with the obstacle. The reason for the collision is that the speed of the obstacle is lower than that of the vehicle.

[0068] Step S12: determining in the target coordinate system the new path start point and path end point of the vehicle when an obstacle is detected.

[0069] In this embodiment, if an obstacle is detected on the current path during the driving of the vehicle, the new path start point and path end point of the vehicle when the obstacle is detected are determined in the target coordinate system. Specifically, the new path start point is determined based on the vehicle position when the obstacle is detected and the vehicle driving speed, wherein the vehicle position when the obstacle is detected includes the longitudinal coordinate value in the first direction and the transverse coordinate value in the second direction; at the same time, the path end point in the current path can be directly determined as the new path end point, and the path end point also corresponds to the vehicle driving speed, the longitudinal coordinate value in the first direction, and the transverse coordinate value in the second direction.

[0070] Step S13, determining in the target coordinate system the path planning areas from the path starting point to the detour space area and from the detour space area to the path end point, respectively, and planning the target path from the path starting point to the path end point based on the path planning areas and the detour space area.

[0071] In this embodiment, after obtaining the path starting point, path end point and detour space area, path planning is performed in the target coordinate system based on the path starting point, path end point and detour space area to obtain the target path from the path starting point to the path end point. Among them, the target path can be a deceleration and following, or it can be a lane change and detour. It should be noted that if another obstacle is detected during the process of path planning based on the path starting point, path end point and detour space area, the path planning will continue based on the detour space area corresponding to the other obstacle. In addition, there is no unsolvable situation in the path planning in this embodiment. The guaranteed target path is a path with the same shape as the current path but the vehicle driving speed at each position on the path may be different, that is, the vehicle decelerates along the target path to follow the obstacle.

[0072] Specifically, a first path planning area from the path starting point to the detour space area is determined in the target coordinate system, and a second path planning area from the detour space area to the path end point is determined in the target coordinate system, and then path planning is performed based on the first path planning area, the second path planning area and the detour space area to determine the target path from the path starting point to the path end point.

[0073] Among them, for determining the first path planning area and the second path planning area, first determine the first spatial point with the smallest coordinate value in the first direction from the detour space area, and determine the second spatial point with the largest coordinate value in the first direction from the detour space area. Then, in the target coordinate system, the first path planning area is determined based on a first connecting line from the path starting point to the first spatial point, and the second path planning area is determined based on a second connecting line from the second spatial point to the path end point.

[0074] For the planning of the target path, firstly, points are scattered in the first path planning area based on the first connecting line, and the first sub-path is determined based on the cost value of each path point obtained by the scattered points, and points are scattered in the second path planning area based on the second connecting line, and the second sub-path is determined based on the cost value of each path point obtained by the scattered points. Then, points are scattered in the detour space area based on the preset transverse and longitudinal acceleration and deceleration thresholds, and the third sub-path from the first spatial point to the second spatial point is determined based on the cost value of each path point obtained by the scattered points; finally, the first sub-path, the second sub-path and the third sub-path are combined to obtain the target path from the path starting point to the path end point. Among them, the preset transverse and longitudinal acceleration and deceleration thresholds include a preset transverse acceleration threshold, a preset transverse deceleration threshold, a preset longitudinal acceleration threshold and a preset longitudinal deceleration threshold. In addition, scattering points refers to marking some points randomly or at equal intervals in a certain area, which can be called path points in path planning, and each path point can calculate the corresponding cost value based on the preset cost function.

[0075] It should be noted that the first subpath and the second subpath can both be scattered based on the line between the two points. For example, the points can be directly scattered on the line between the two points, and then the corresponding subpath is determined based on the path points with the smallest cost corresponding to the coordinate values ​​in the first direction (longitudinal direction); that is, the first subpath and the second subpath are respectively the optimal paths with the smallest path cost from the path starting point to the first spatial point and the second spatial point to the path end point. In addition, the points of the first subpath and the second subpath can be scattered at equal intervals, and the interval can be set according to the actual path planning requirements, for example, it can be set to two meters, that is, one point is scattered every two meters.

[0076] It should be noted that for the third sub-path, points are scattered in the detour space area based on the preset horizontal and vertical acceleration and deceleration thresholds, and points can also be scattered at equal intervals, but the density of the points scattered in the detour space area is higher than the density of the points scattered based on the connection between two points; for example, the density of the points scattered in the detour space area can be set to one point every one meter. In this way, by increasing the density of the points scattered, the path planned in the detour space area can be made more accurate.

[0077] Among them, the corresponding sub-path is determined based on the path point with the smallest cost value corresponding to each coordinate value in the first direction (vertical direction), assuming that each coordinate value in the first direction includes y1, y2, y3, and each coordinate value corresponds to multiple path points. For the coordinate value y1, the y1 path point with the smallest cost value is determined from the multiple path points corresponding to the coordinate value y1; for the coordinate value y2, the y2 path point with the smallest cost value is determined from the multiple path points corresponding to the coordinate value y2; for the coordinate value y3, the y3 path point with the smallest cost value is determined from the multiple path points corresponding to the coordinate value y3; finally, the sub-path with the smallest path cost is determined based on the y1 path point, the y2 path point, and the y3 path point.

[0078] It should be noted that if the density of points scattered in the area is sparse, there may be a situation where the lateral and longitudinal acceleration and deceleration between two path points exceeds the preset lateral and longitudinal acceleration and deceleration thresholds. In this case, the lateral and longitudinal acceleration and deceleration that are allowed to overflow can be set to allow the lateral and longitudinal acceleration and deceleration between the two path points to exceed the preset lateral and longitudinal acceleration and deceleration thresholds, but not to exceed the maximum lateral and longitudinal acceleration and deceleration allowed by the vehicle actuator.

[0079] Moreover, for the third subpath, the first spatial point is first determined as the current target spatial point, and the plane determination operation is triggered to determine the current motion plane within a unit time at the current target spatial point based on the preset lateral and longitudinal acceleration and deceleration thresholds. The current motion plane is as follows: Figure 7As shown. Then, the overlapping area of ​​the detour space area and the current motion plane is determined, and points are scattered in the overlapping area to obtain a number of path points. The cost values ​​corresponding to the several path points are calculated based on the preset cost function, and then the path point with the smallest cost value among the several path points is determined as the new current target space point, and the plane determination operation is jumped again to re-determine the current motion plane per unit time at the current target space point based on the preset horizontal and vertical acceleration and deceleration thresholds, until the current target space point is the second space point, the point scattering operation in the detour space area is terminated, so that the third sub-path from the first space point to the second space point can be determined based on all the target space points; that is, the third sub-path is the optimal path with the smallest path cost from the first space point to the second space point in the detour space area.

[0080] Finally, the target path from the path start point to the path end point can be obtained by combining the first subpath, the second subpath and the third subpath. Since the first subpath, the second subpath and the third subpath are all optimal paths with the minimum path cost in the corresponding area, the target path is also the optimal path with the minimum path cost from the path start point to the path end point. In this way, by combining the point scattering based on the connection between two points and the point scattering in the detour space area, the amount of calculation for path planning in the target coordinate system can be greatly reduced, and the target path with the minimum path cost from the path start point to the path end point can be planned.

[0081] It should be noted that each path is composed of path points with relatively small cost values, so that the resource cost consumed by the vehicle in the process of traveling along the path is relatively small. In addition, each path corresponds to a path cost, which is a value determined based on the cost values ​​of the path points on the path. For example, the path cost of the path can be obtained by directly adding the cost values ​​of the path points on the path.

[0082] Among them, for the cost value of the path point, a preset cost function is constructed based on each distance parameter and each speed parameter at the path point, the width of the lane where the path point is located, and the time loss corresponding to the path point, and the cost value of the path point is calculated based on the preset cost function. Among them, each distance parameter includes a first distance from the path point to the end of the path, a second distance from the lane line when the vehicle is at the path point, and the minimum horizontal and vertical distances from the surrounding obstacles; wherein the lane line can be a solid lane line or a lane edge line. Each speed parameter includes a preset horizontal and vertical acceleration and deceleration threshold, an upper limit of the road speed, the horizontal and vertical acceleration of the vehicle at the path point, and the vehicle speed. The time loss is the difference between the first driving time and the second driving time; the first driving time is the driving time from the path starting point to the path end point through the path point; the second driving time is the driving time from the path starting point to the path end point along the current path when there are no obstacles.

[0083] It should be noted that the first distance, the second distance and the width of the lane where the waypoint is located can be given based on the center line of the lane detected by vision, or based on the center line of the lane on the map, and are not limited here. In addition, the minimum horizontal and vertical distances to the surrounding obstacles can be obtained by vehicle sensors, such as ultrasonic sensors.

[0084] ;

[0085] The preset cost function is shown above, where λ i Represents the proportional coefficient, which is used to adjust the influence of various parameters on the final output cost value f. c Indicates the distance from the path point to the end point of the path; d r Indicates the distance from the vehicle to the lane line when it is at the path point (taking the minimum value); W d Indicates the width of the lane where the path point is located; t c represents time loss; abs( ) is the absolute value function; δ and φ are preset values; a long and a lat They represent the longitudinal acceleration and lateral acceleration of the vehicle at the path point respectively; a as and a ds They represent the preset longitudinal acceleration threshold and the preset longitudinal deceleration threshold respectively; a Latc represents a preset lateral acceleration threshold or a preset lateral deceleration threshold, wherein the preset lateral acceleration threshold and the preset lateral deceleration threshold are the same; d long Indicates the minimum longitudinal distance between the vehicle and surrounding obstacles when it is at a path point; d lat Indicates the minimum lateral distance between the vehicle and surrounding obstacles when it is at the path point; v c represents the vehicle speed at the path point; v max Indicates the upper limit of road speed; tar R Indicates the right lane; tar L Indicates the left lane; tar ego Indicates the lane where the vehicle is located, through f(tar x ) to set different weights for each lane.

[0086] In this embodiment, after planning the target path from the path start point to the path end point, since the target path is planned in the target coordinate system, the vehicle speed at each position on the target path can be determined, and the vehicle can be controlled to travel along the target path based on the vehicle speed at each position on the target path. Alternatively, this embodiment can also decompose the vehicle longitudinal acceleration and vehicle lateral acceleration at each position based on the target path, so as to control the vehicle to travel along the target path based on the vehicle longitudinal acceleration and vehicle lateral acceleration at each position on the target path.

[0087] It can be seen that the present application constructs a target coordinate system based on the vehicle's driving speed, the coordinate value in the first direction and the coordinate value in the second direction, wherein the coordinate value in the first direction represents the longitudinal position of the vehicle in a direction parallel to the direction of the front of the vehicle when the obstacle is detected, and the coordinate value in the second direction represents the lateral position of the vehicle in a direction perpendicular to the direction of the front of the vehicle, thereby performing path planning in the target coordinate system to combine lateral planning and longitudinal planning, so that the decided target path has actual physical meaning, and the shape of the path and the vehicle driving speed at each position on the path can be planned at the same time, and the decided target path can be made more accurate; and the present application performs path planning in the target coordinate system based on the detour space area corresponding to the obstacle, thereby avoiding path planning in the entire coordinate system, and reducing the amount of calculation for path planning by reducing the area for path planning.

[0088] Based on the previous embodiment, it can be seen that the previous embodiment describes the overall process of constructing the target coordinate system and planning the target path. Next, this embodiment will elaborate on how to obtain a smooth target path. Fig. 9 As shown, the embodiment of the present invention discloses a path planning process, including:

[0089] Step S21: If the initial path from the path starting point to the path ending point planned based on the path planning area and the detour space area is offset in the second direction relative to the current path, determine the extreme path point with the largest offset from the initial path.

[0090] In this embodiment, a first spatial point with the smallest coordinate value in the first direction is determined from the detour space area, and a second spatial point with the largest coordinate value in the first direction is determined from the detour space area; then, in the target coordinate system, a first path planning area is determined based on a first line from the path starting point to the first spatial point, and a second path planning area is determined based on a second line from the second spatial point to the path end point. Path planning is performed based on the first path planning area, the second path planning area, and the detour space area to obtain an initial path from the path starting point to the path end point. Furthermore, if the initial path is offset in the second direction relative to the current path, an extreme path point with the largest offset from the current path in the second direction is determined from the initial path. Fig.10 For example, Fig.10 The solid line path from the path starting point through the extreme path point to the path end point in is the initial path; the current path is Fig.10 The dotted path from the path start point to the path end point in , and the extreme path point has the largest offset in the second direction (x-axis direction) relative to the current path.

[0091] Step S22: performing path planning in a first plane area determined in the target coordinate system based on the extreme path point, the path starting point and the initial path to obtain a first smooth path, and performing path planning in a second plane area determined in the target coordinate system based on the extreme path point, the path ending point and the initial path to obtain a second smooth path.

[0092] Step S23: determine the target path based on the first smooth path and the second smooth path.

[0093] It should be noted that if the initial path does not deviate from the current path in the second direction, the shape of the initial path is the same as the shape of the current path, but the vehicle speeds at various locations on the two paths may be different. If the initial path deviates from the current path in the second direction, the initial path needs to be smoothed based on the extreme path points to obtain a smoothed target path.

[0094] Taking into account that the initial path is the path with the minimum path cost obtained by scattering points in the detour space area, and is not the path with the minimum path cost from the path starting point to the path end point in the entire space, therefore, in this embodiment, when the initial path is offset in the second direction relative to the current path, the initial path is planned again based on the extreme path points, so as to obtain a target path from the path starting point to the path end point in the entire space that is smooth and has the minimum path cost.

[0095] Specifically, a first plane area is determined in the target coordinate system based on the extreme path point, the path starting point and the initial path. The first plane area is as follows: Fig.10As shown in the shaded area in , path planning is performed in the first plane area to obtain a first smooth path. At the same time, based on the extreme path point, the path end point and the initial path, a second plane area is determined in the target coordinate system, and path planning is performed in the second plane area to obtain a second smooth path. Finally, based on the first smooth path and the second smooth path, a target path from the path start point to the path end point with a smooth path cost minimum in the entire space can be obtained.

[0096] It should be noted that, for the path planning of the first plane area and the second plane area, points can be scattered at equal intervals in the plane area, and the corresponding cost value is calculated for each path point obtained by scattering the points, so as to determine a smooth path based on the path point with the smallest cost value corresponding to each coordinate value in the first direction.

[0097] Further, such as Fig.10 As shown in the figure, if the extreme value path point is located in the adjacent lane of the lane where the path end point is located, the adjacent lane end point corresponding to the path end point is determined on the adjacent lane, and the adjacent lane path with the minimum path cost from the path starting point to the adjacent lane end point is planned based on the extreme value path point. Then, the path with the minimum path cost is selected from the adjacent lane path and the target path as the optimal path, so as to control the vehicle to travel along the optimal path.

[0098] Among them, for the adjacent lane path planning, path planning is performed based on the extreme path point and the adjacent lane end point in the target coordinate system to obtain a first adjacent lane path from the extreme path point to the adjacent lane end point. Then, the second adjacent lane path from the path start point to the extreme path point is determined from the target path, and finally, the adjacent lane path from the path start point to the adjacent lane end point is determined based on the first adjacent lane path and the second adjacent lane path.

[0099] Among them, for the planning of the path of the first adjacent lane, points can be scattered based on the line between the extreme path point in the target coordinate system and the adjacent lane end point, and the corresponding cost value is calculated for each path point obtained by the scattering, and then the first adjacent lane path is determined based on the path point with the smallest cost value corresponding to each coordinate value in the first direction.

[0100] Since the first adjacent lane path is the path with the minimum path cost from the extreme path point to the adjacent lane end point, and the second adjacent lane path is also the path with the minimum path cost from the path starting point to the extreme path point, the adjacent lane path determined based on the first adjacent lane path and the second adjacent lane path is also the path with the minimum path cost from the path starting point to the adjacent lane end point.

[0101] It can be seen that the present application constructs a target coordinate system based on the vehicle's driving speed, the coordinate value in the first direction and the coordinate value in the second direction, wherein the coordinate value in the first direction represents the longitudinal position of the vehicle in a direction parallel to the direction of the front of the vehicle when the obstacle is detected, and the coordinate value in the second direction represents the lateral position of the vehicle in a direction perpendicular to the direction of the front of the vehicle, thereby performing path planning in the target coordinate system to combine lateral planning and longitudinal planning, so that the determined target path has actual physical meaning, and can simultaneously plan the shape of the path and the vehicle's driving speed at each position on the path, and can make the determined target path more accurate; and, the present application determines the path with the minimum path cost based on the path points with the minimum cost corresponding to each coordinate value in the first direction, so that the optimal path with less resource cost can be planned.

[0102] See also Fig.11 As shown, an embodiment of the present invention discloses a path planning device, including:

[0103] A detour area determination module 11 is used to determine a detour space area corresponding to an obstacle on the current path if the obstacle is detected during driving; the coordinates of each coordinate point in the target coordinate system include the vehicle driving speed, a coordinate value in a first direction, and a coordinate value in a second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle;

[0104] A starting and ending point determination module 12, used to determine a new path starting point and path ending point of the vehicle in the target coordinate system when an obstacle is detected;

[0105] The path planning module 13 is used to determine the path planning areas from the path starting point to the detour space area and from the detour space area to the path end point in the target coordinate system, and plan the target path from the path starting point to the path end point based on the path planning areas and the detour space area.

[0106] It can be seen that the present application constructs a target coordinate system based on the vehicle's driving speed, the coordinate value in the first direction and the coordinate value in the second direction, wherein the coordinate value in the first direction represents the longitudinal position of the vehicle in a direction parallel to the direction of the front of the vehicle when the obstacle is detected, and the coordinate value in the second direction represents the lateral position of the vehicle in a direction perpendicular to the direction of the front of the vehicle, thereby performing path planning in the target coordinate system to combine lateral planning and longitudinal planning, so that the decided target path has actual physical meaning, and the shape of the path and the vehicle driving speed at each position on the path can be planned at the same time, and the decided target path can be made more accurate; and the present application performs path planning in the target coordinate system based on the detour space area corresponding to the obstacle, thereby avoiding path planning in the entire coordinate system, and reducing the amount of calculation for path planning by reducing the area for path planning.

[0107] In some specific embodiments, the path planning module 13 includes:

[0108] A space point determination unit, configured to determine a first space point with a minimum coordinate value and a second space point with a maximum coordinate value in the first direction from the bypass space area;

[0109] A planning area determination unit is used to determine a first path planning area based on a first line from the path starting point to the first spatial point in the target coordinate system, and to determine a second path planning area based on a second line from the second spatial point to the path end point.

[0110] In some specific embodiments, the path planning module 13 includes:

[0111] A first point scattering unit is configured to scatter points in the first path planning area based on the first connecting line to determine a first sub-path based on the cost value of each path point obtained by scattering points; and scatter points in the second path planning area based on the second connecting line to determine a second sub-path based on the cost value of each path point obtained by scattering points;

[0112] a second point scattering unit, configured to scatter points in the detour space area based on preset lateral and longitudinal acceleration and deceleration thresholds, so as to determine a third sub-path from the first spatial point to the second spatial point based on a cost value of each path point obtained by scattering points;

[0113] The first target path determining unit is configured to determine a target path from the path starting point to the path ending point based on the first sub-path, the second sub-path, and the third sub-path.

[0114] In some specific embodiments, the second scattering unit includes:

[0115] a motion plane determination unit, configured to determine the first spatial point as a current target spatial point, and trigger a plane determination operation to determine a current motion plane within a unit time at the current target spatial point based on preset lateral and longitudinal acceleration and deceleration thresholds;

[0116] A sub-path determination unit is used to scatter points in the overlapping area between the bypass space area and the current motion plane, and determine the path point with the smallest cost value among the several path points obtained by scattering as the new current target space point, and then jump to the plane determination operation until the current target space point is the second space point, so as to determine the third sub-path based on all target space points.

[0117] In some specific embodiments, the path planning device further includes:

[0118] a cost value determining unit, configured to determine a cost value of the waypoint based on a distance parameter and a speed parameter at the waypoint, a width of a lane where the waypoint is located, and a time loss corresponding to the waypoint;

[0119] Among them, the distance parameters include a first distance from the path point to the path end point, a second distance from the lane line when the vehicle is at the path point, and the minimum lateral and longitudinal distances from surrounding obstacles; the speed parameters include the preset lateral and longitudinal acceleration and deceleration thresholds, the upper limit of the road speed, the lateral and longitudinal acceleration of the vehicle at the path point, and the vehicle speed; the time loss is the difference between the driving time from the path starting point to the path end point through the path point and the driving time from the path starting point to the path end point along the current path.

[0120] In some specific embodiments, the path planning module 13 includes:

[0121] an extreme point determining unit, configured to determine an extreme path point with the largest deviation from the initial path if an initial path from the path starting point to the path ending point planned based on the path planning area and the detour space area is offset in the second direction relative to the current path;

[0122] a smooth path planning unit, configured to perform path planning in a first plane region determined in the target coordinate system based on the extreme path point, the path starting point, and the initial path to obtain a first smooth path, and to perform path planning in a second plane region determined in the target coordinate system based on the extreme path point, the path ending point, and the initial path to obtain a second smooth path;

[0123] The second target path determining unit is configured to determine the target path based on the first smooth path and the second smooth path.

[0124] In some specific embodiments, the path planning device further includes:

[0125] an adjacent lane endpoint determination unit, configured to determine an adjacent lane endpoint corresponding to the path endpoint on the adjacent lane if the extreme value path point is located on the adjacent lane of the lane where the path endpoint is located;

[0126] an adjacent lane path determination unit, configured to plan a first adjacent lane path from the extreme path point to the adjacent lane end point, and determine the adjacent lane path based on the first adjacent lane path and a second adjacent lane path on the target path from the path start point to the extreme path point;

[0127] The optimal path selection unit is used to select a path with the smallest path cost from the adjacent lane path and the target path as the optimal path, so as to control the vehicle to travel along the optimal path.

[0128] In some specific embodiments, the detour area determination module 11 includes:

[0129] The detour area determination unit is used to determine the speed difference between the travel speed of the obstacle and the travel speed of the vehicle corresponding to the path starting point, and determine the detour space area corresponding to the obstacle in the target coordinate system based on the speed difference.

[0130] Furthermore, the present application also discloses an electronic device. Fig.12 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0131] Fig.12 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the path planning method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0132] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0133] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0134] The operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20, and can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the path planning method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0135] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein the computer program, when executed by a processor, implements the aforementioned disclosed path planning method. The specific steps of the method can refer to the corresponding contents disclosed in the aforementioned embodiments, and will not be repeated here.

[0136] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0137] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0138] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0139] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0140] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A path planning method, characterized in that: include: If an obstacle is detected on the current path during driving, a detour space area corresponding to the obstacle is determined in the target coordinate system; The coordinates of each coordinate point in the target coordinate system include the vehicle speed, the coordinate value in the first direction, and the coordinate value in the second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle; Determining, in the target coordinate system, a new path start point and a path end point of the ego vehicle when an obstacle is detected; Determining in the target coordinate system respectively a path planning area from the path starting point to the detour space area and a path planning area from the detour space area to the path end point, and planning a target path from the path starting point to the path end point based on the path planning area and the detour space area; The target path is a path determined based on the first subpath, the second subpath, and the third subpath; the first subpath and the second subpath are respectively the optimal paths with the minimum path cost from the path starting point to the first spatial point and the second spatial point to the path end point; the first spatial point and the second spatial point are respectively the spatial points with the smallest coordinate value and the largest coordinate value in the first direction in the detour space area; Furthermore, the process of determining the third sub-path includes: Determine the first spatial point as the current target spatial point, and trigger a plane determination operation to determine a current motion plane within a unit time at the current target spatial point based on preset lateral and longitudinal acceleration and deceleration thresholds; Points are scattered in the overlapping area of ​​the bypass space area and the current motion plane, and the path point with the smallest cost value among the several path points obtained by scattering the points is determined as the new current target space point, and then the plane determination operation is jumped to until the current target space point is the second space point, so as to determine the third sub-path based on all target space points.

2. The path planning method according to claim 1, characterized in that: The determining, in the target coordinate system, respectively the path planning area from the path starting point to the detour space area and from the detour space area to the path ending point includes: Determine, from the bypass space area, a first spatial point with the smallest coordinate value and a second spatial point with the largest coordinate value in the first direction; In the target coordinate system, a first path planning area is determined based on a first line from the path starting point to the first spatial point, and a second path planning area is determined based on a second line from the second spatial point to the path ending point.

3. The path planning method according to claim 2, characterized in that: The planning of a target path from the path starting point to the path ending point based on the path planning area and the detour space area includes: In the first path planning area, points are scattered based on the first connection line, and a first sub-path is determined based on the cost value of each path point obtained by the scattered points; in the second path planning area, points are scattered based on the second connection line, and a second sub-path is determined based on the cost value of each path point obtained by the scattered points; Based on preset lateral and longitudinal acceleration and deceleration thresholds, points are scattered in the detour space area, so as to determine a third sub-path from the first spatial point to the second spatial point based on the cost value of each path point obtained by the scattered points; A target path from the path start point to the path end point is determined based on the first sub-path, the second sub-path, and the third sub-path.

4. The path planning method according to claim 3, characterized in that: Also includes: Determine a cost value of the waypoint based on a distance parameter and a speed parameter at the waypoint, a width of a lane where the waypoint is located, and a time loss corresponding to the waypoint; Among them, the distance parameters include a first distance from the path point to the path end point, a second distance from the lane line when the vehicle is at the path point, and the minimum lateral and longitudinal distances from surrounding obstacles; the speed parameters include the preset lateral and longitudinal acceleration and deceleration thresholds, the upper limit of the road speed, the lateral and longitudinal acceleration of the vehicle at the path point, and the vehicle speed; the time loss is the difference between the driving time from the path starting point to the path end point through the path point and the driving time from the path starting point to the path end point along the current path.

5. The path planning method according to claim 1, characterized in that: The planning of a target path from the path starting point to the path ending point based on the path planning area and the detour space area includes: If the initial path from the path starting point to the path ending point planned based on the path planning area and the detour space area is offset in the second direction relative to the current path, determining an extreme path point with the largest offset from the initial path; Performing path planning in a first plane region determined in the target coordinate system based on the extreme path point, the path starting point, and the initial path to obtain a first smooth path, and performing path planning in a second plane region determined in the target coordinate system based on the extreme path point, the path ending point, and the initial path to obtain a second smooth path; The target path is determined based on the first smooth path and the second smooth path.

6. The path planning method according to claim 5, characterized in that: Also includes: If the extreme value path point is located on an adjacent lane of the lane where the path end point is located, then determining an adjacent lane end point corresponding to the path end point on the adjacent lane; Planning a first adjacent lane path from the extreme path point to the adjacent lane end point, and determining the adjacent lane path based on the first adjacent lane path and a second adjacent lane path on the target path from the path start point to the extreme path point; A path with the smallest path cost is selected from the adjacent lane path and the target path as the optimal path, so as to control the vehicle to travel along the optimal path.

7. The path planning method according to any one of claims 1 to 6, characterized in that: The step of determining the detour space area corresponding to the obstacle in the target coordinate system includes: A speed difference between a travel speed of the obstacle and a travel speed of the vehicle corresponding to the path starting point is determined, and a detour space area corresponding to the obstacle is determined in a target coordinate system based on the speed difference.

8. A path planning device, characterized in that: include: A detour area determination module, configured to determine a detour space area corresponding to the obstacle in a target coordinate system if an obstacle is detected on the current path during driving; The coordinates of each coordinate point in the target coordinate system include the vehicle speed, the coordinate value in the first direction, and the coordinate value in the second direction; the first direction is parallel to the direction of the front of the vehicle when the obstacle is detected, and the second direction is perpendicular to the direction of the front of the vehicle; A starting and ending point determination module, used to determine the new path starting point and path ending point of the vehicle in the target coordinate system when an obstacle is detected; A path planning module, used to determine the path planning areas from the path starting point to the detour space area and from the detour space area to the path end point in the target coordinate system, and plan a target path from the path starting point to the path end point based on the path planning areas and the detour space area; wherein the target path is a path determined based on a first subpath, a second subpath and a third subpath; the first subpath and the second subpath are respectively optimal paths with the minimum path cost between the path starting point to a first spatial point and a second spatial point to the path end point; the first spatial point and the second spatial point are respectively spatial points with the smallest coordinate value and the largest coordinate value in the first direction in the detour space area; Furthermore, the process of determining the third sub-path in the path planning module includes: a motion plane determination unit, configured to determine the first spatial point as a current target spatial point, and trigger a plane determination operation to determine a current motion plane within a unit time at the current target spatial point based on preset lateral and longitudinal acceleration and deceleration thresholds; A sub-path determination unit is used to scatter points in the overlapping area between the bypass space area and the current motion plane, and determine the path point with the smallest cost value among the several path points obtained by scattering as the new current target space point, and then jump to the plane determination operation until the current target space point is the second space point, so as to determine the third sub-path based on all target space points.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, configured to execute the computer program to implement the path planning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, which, when executed by a processor, implements the path planning method according to any one of claims 1 to 7.