Vehicle path decision post-processing method and system, vehicle and equipment

Abstract

The invention discloses a vehicle path decision post-processing method and system, a vehicle and equipment. The vehicle path decision post-processing method comprises the steps that a lane boundary and an obstacle boundary are obtained, the lane boundary is used for constraining wheels, the obstacle boundary is used for constraining a vehicle body, and the obstacle boundary is obtained according to outward expansion of the lane boundary; acquiring an obstacle distribution condition on the lane boundary; according to the distribution condition of the obstacles and the minimum width required value of the lane, whether the expansion condition of the lane boundary is met or not is judged, and the minimum width required value of the lane is obtained according to the vehicle parameters and the road parameters; if yes, the lane boundary is expanded. By the adoption of the method and device, the vehicle wheels and the vehicle body are restrained during path optimization, the optimized solution space is expanded, the soft boundary and the hard boundary are expanded to a certain degree, so that the driving space boundary is more tidy, the optimized path is smoother, and the flexibility of the truck under the road condition with the large curvature is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to a vehicle path decision post-processing method, system, vehicle and equipment. Background Art

[0002] Based on the Frenet coordinate system, the unmanned driving trajectory planning adopts the method of time-space decoupling to reduce the planning complexity. Spatial planning is mainly divided into path decision and path optimization. The task of path decision is to find a drivable space in space. With the help of the Frenet coordinate system, the drivable space is a convex space and is also the optimal solution space for path optimization, thus converting the path optimization problem into a QP (quadratic programming) problem.

[0003] In the process of finding the optimal solution space, the path decision should comprehensively consider the lane width, the state of the vehicle, the distribution of static obstacles, and find the passable area; timely determine whether the road ahead is passable, and timely cut off the impassable area to avoid path optimization failure. The lane width is the target lane width output by the lane change decision, which is the initial optimal solution space. The state of the vehicle includes the coordinates (s, l, i) of the vehicle in the Frenet coordinate system, and the length and width. Among them, i is the derivative of l in time, which means that the vehicle has a speed in the l direction, and a certain space is needed to eliminate the speed. In addition, for safety, a certain margin needs to be added to the width of the vehicle.

[0004] The distribution of static obstacles is the static obstacles that are distributed around the target lane and affect the shape of the drivable space. The path decision needs to ensure that the optimal solution space searched does not contain static obstacles. The optimal solution space is based on the target lane reference line. The width range of the drivable space on both sides is composed of a series of sampling points. The sampling points contain three attributes: the s value corresponding to the sampling point, the left width and the right width of the drivable space at the sampling point, where the left width is a positive value and the right width is a negative value to distinguish. After the drivable space is generated, it is necessary to check the space, that is, to check whether the vehicle is passable when the above constraints are met. The simplest method is to check whether the width of the sampling points is greater than the width of the vehicle one by one. If it is less than the width of the vehicle, it is considered that the vehicle is not passable. The sampling point is a block point, and the space after the block point needs to be deleted from the drivable space to ensure that the path optimization has a solution.

[0005] However, the existing technology mainly targets smaller vehicles such as passenger cars. When verifying the bound, a particle model is used and only a single sampling point is verified, ignoring the geometric constraints and status of the vehicle. The space obtained after verification cannot guarantee that the path optimization has a solution. Summary of the invention

[0006] Based on this, it is necessary to provide a vehicle path decision post-processing method, system, vehicle and equipment to address the above-mentioned technical problems, which are used to constrain the wheels and the vehicle body respectively during path optimization, thereby expanding the optimization solution space. By expanding the soft and hard boundaries to a certain extent, the boundaries of the drivable space are made more orderly, thereby making the path at the optimized location smoother, thereby improving the flexibility of the truck on roads with large curvature.

[0007] In a first aspect, a vehicle path decision post-processing method is provided, comprising:

[0008] Obtaining a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary;

[0009] Obtain the obstacle distribution on the lane boundary;

[0010] Determining whether the lane boundary expansion condition is met according to the distribution of the obstacles and the required minimum lane width, wherein the required minimum lane width is obtained according to vehicle parameters and road parameters;

[0011] If yes, the lane boundary is extended, wherein the extended lane boundary is located within the obstacle boundary.

[0012] In some examples, the vehicle parameters include vehicle length, wheelbase, and vehicle width, the road parameters include road curvature, and the method further includes:

[0013] Obtaining a turning radius according to the road curvature;

[0014] The minimum lane width requirement value is obtained according to the vehicle length, wheelbase, vehicle width and turning radius.

[0015] In some examples, judging whether the lane boundary expansion condition is met based on the distribution of the obstacles and the lane minimum width requirement value includes:

[0016] If there is an obstacle on one side of the lane boundary, further determining whether the width of the lane boundary after expansion is less than or equal to the required minimum lane width;

[0017] If yes, it is determined that the extension condition of the lane boundary is satisfied.

[0018] In some examples, if there are obstacles on both sides of the lane boundary, the obstacles on both sides are longitudinally extended according to the leftmost position and the rightmost position of the obstacles on both sides in the longitudinal direction;

[0019] After longitudinally extending the obstacles on both sides, determining whether the width of the lane boundary after expansion is less than or equal to the required minimum lane width;

[0020] If yes, further determine whether the longitudinal distance between the obstacles on both sides after expansion and the adjacent obstacles in the lateral direction is greater than a threshold;

[0021] If yes, it is determined that the extension condition of the lane boundary is satisfied.

[0022] In some examples, the threshold is related to the longitudinal distance between the obstacles on both sides.

[0023] In some examples, this also includes:

[0024] When it is determined that the lane boundary extension condition is not met, the path planning is performed again.

[0025] In a second aspect, a vehicle path decision post-processing system is provided, comprising:

[0026] An acquisition module, used to obtain a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary;

[0027] Obstacle detection module, used to obtain the distribution of obstacles on the lane boundary;

[0028] A judgment module, used to judge whether the lane boundary expansion condition is met according to the distribution of the obstacles and the lane minimum width requirement value, wherein the lane minimum width requirement value is obtained according to vehicle parameters and road parameters;

[0029] An expansion module is used to expand the lane boundary when the expansion condition of the lane boundary is met, wherein the expanded lane boundary is located within the obstacle boundary.

[0030] In a third aspect, a vehicle is provided, comprising: a path decision post-processing system for the vehicle according to the second aspect.

[0031] In a fourth aspect, a computer device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the vehicle path decision post-processing method of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0032] In a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the vehicle path decision post-processing method of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0033] In a sixth aspect, a computer program product is provided, on which a computer program is stored. When the program is executed by a processor, the steps of the vehicle path decision post-processing method of the above-mentioned first aspect and any possible implementation method of the first aspect are implemented.

[0034] According to the embodiment of the present application, after obtaining the lane boundary, obstacle boundary and the distribution of obstacles on the lane boundary, it is determined whether the lane boundary expansion condition is met according to the distribution of obstacles and the required value of the minimum lane width. When the expansion condition is met, the lane boundary is expanded. Therefore, for vehicles, especially for vehicles with larger body sizes such as driving, the constraints of path planning are divided into two types of soft and hard constraints, which are used to constrain wheels and body respectively during path optimization, thereby expanding the optimized solution space. By expanding the soft and hard boundaries to a certain extent, the boundaries of the drivable space are made more orderly, thereby making the optimized path smoother. The two boundaries are used to generate the drivable space boundaries of the truck, which expands the drivable space of the truck and improves the flexibility of the truck on roads with large curvature. On the other hand, by post-processing the boundaries, the left and right boundaries are made more consistent, providing a more reasonable solution space for subsequent path optimization, ensuring that the generated path is smoother and reducing unnecessary left and right detours. The size of the vehicle is taken into consideration, so it is more reasonable and reliable when judging the sampling point block. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Other features, objects and advantages of the present application will become more apparent by reading the detailed description of non-limiting embodiments made with reference to the following drawings:

[0036] Figure 1 A flowchart of a path decision post-processing method for a vehicle provided in an embodiment of the present application;

[0037] Figure 2 A schematic diagram of a lane boundary and an obstacle boundary in a path decision post-processing method for a vehicle provided in an embodiment of the present application;

[0038] Figure 3 A schematic diagram of another lane boundary and obstacle boundary in the path decision post-processing method for a vehicle provided in an embodiment of the present application;

[0039] Figure 4 A schematic diagram of obstacle distribution in a vehicle path decision post-processing method provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of a turning path in a path decision post-processing method for a vehicle provided in an embodiment of the present application;

[0041] Figure 6 A schematic diagram of lane boundary extension in a path decision post-processing method for a vehicle provided in an embodiment of the present application;

[0042] Figure 7 A schematic diagram of another lane boundary extension in the vehicle path decision post-processing method provided in an embodiment of the present application;

[0043] Figure 8 A schematic diagram of another lane boundary extension in the vehicle path decision post-processing method provided in an embodiment of the present application;

[0044] Fig. 9 This is a structural block diagram of a vehicle path decision post-processing system according to a specific embodiment of the present application;

[0045] Fig.10 A structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The present application is further described in detail below in conjunction with the embodiments and drawings. It is to be understood that the specific embodiments described herein are only used to explain the relevant application, rather than to limit the application. It is also necessary to explain that, for ease of description, only the parts related to the application are shown in the drawings.

[0047] It should be noted that, in the absence of conflict, the embodiments of the present application, that is, the features of the embodiments, can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0048] The following describes in detail the path decision post-processing method, system, vehicle and equipment of the vehicle according to the embodiments of the present application in conjunction with the accompanying drawings.

[0049] Figure 1 FIG. 1 is a flow chart of a vehicle path decision post-processing method according to an embodiment of the present application. Figure 1 As shown, a vehicle path decision post-processing method according to an embodiment of the present application includes the following steps:

[0050] S101: Obtaining a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary.

[0051] In the embodiments of the present application, lane boundaries are also referred to as soft boundaries, and obstacle boundaries are also referred to as hard boundaries. Generally, the vehicle body is allowed to exceed the lane to a certain extent, thereby improving the ability of vehicles, especially large trucks, to cope with complex road conditions on narrow roads and large curvature sections.

[0052] like Figure 2 and Figure 3 As shown, the lane boundary lane_bound is located between the obstacle boundaries obstacle_bound. Figure 3 In , when one side is the outermost lane, the lane boundary lane_bound and the obstacle boundary obstacle_bound cannot exceed the road boundary of the outermost lane, such as cannot exceed the Road boundary; Figure 2 If it is not the outermost lane or the innermost lane, such as the middle lane, in this case, the lane boundary lane_bound is located at the obstacle boundary obstacle_bound, which allows the lane line to exceed this lane.

[0053] S102: Obtain the obstacle distribution on the lane boundary.

[0054] like Figure 4 As shown, the obstacles correspond to segments l1, l2, l3, r1 and r2. Use start_index and end_index to represent the road segments where obstacles appear. Start_index and end_index are the index values ​​of s corresponding to the starting point and end point of the road segment, respectively. They are distinguished from left and right and stored separately:

[0055] std::vector <std::pair<int,int> >left_obstacle_bound_sections;

[0056] std::vector <std::pair<int,int> >right_obstacle_bound_sections.

[0057] S103: judging whether the lane boundary expansion condition is satisfied according to the distribution of the obstacles and the required minimum lane width, wherein the required minimum lane width is obtained according to vehicle parameters and road parameters.

[0058] In one embodiment of the present application, vehicle parameters include but are not limited to vehicle length, wheelbase and vehicle width, and road parameters include but are not limited to road curvature. The minimum lane width requirement value is obtained based on the vehicle parameters and road parameters, including: obtaining a turning radius based on the road curvature; obtaining the minimum lane width requirement value based on the vehicle length, wheelbase, vehicle width and the turning radius.

[0059] That is to say, the minimum lane width requirement is determined based on road parameters such as road curvature and vehicle parameters such as vehicle length, wheelbase, and vehicle width, so that the vehicle can better adapt to road conditions with large curvature. Figure 5 As shown, get s i The curvature k of the road corresponding to the vehicle reference position i , thus obtaining the turning radius r i =1 / k i Taking a semi-trailer truck as an example, the length of the vehicle is the distance from the center of the rear axle to the front of the vehicle without a trailer lf + the distance from the center of the rear axle to the parking space lr, and the wheelbase is recorded as l base , the vehicle width is recorded as w, then the minimum lane width requirement (i.e., the minimum lane width requirement) is obtained by passing it into the following formula:

[0060]

[0061] Among them, w margin It is a safety margin and can be set in advance.

[0062] In one embodiment of the present application, whether the expansion condition of the lane boundary is met is determined based on the distribution of the obstacles and the minimum lane width requirement value, including: if there is an obstacle on one side of the lane boundary, further determining whether the width of the lane boundary after expansion is less than or equal to the minimum lane width requirement value; if so, determining that the expansion condition of the lane boundary is met.

[0063] In addition, if there are obstacles on both sides of the lane boundary, the obstacles on both sides are longitudinally expanded according to the leftmost position and the rightmost position of the obstacles on both sides in the longitudinal direction; after the obstacles on both sides are longitudinally expanded, it is determined whether the width of the lane boundary after expansion is less than or equal to the required value of the minimum lane width; if so, it is further determined whether the longitudinal distance between the obstacles on both sides and the adjacent obstacles in the lateral direction after expansion is greater than a threshold; if so, it is determined that the expansion condition of the lane boundary is met.

[0064] In this example, the threshold is related to the longitudinal distance between the obstacles on both sides.

[0065] Specifically, if Figure 6As shown, taking the l3 and r2 segments as examples, for soft boundaries, expansion in the l direction is possible when necessary. Generally speaking, expansion in the l direction is not allowed for hard boundaries.

[0066] When an obstacle appears on one side, the soft boundary on the other side can be extended to the outside of the lane to ensure the passage width.

[0067] Of course, before expansion, it should be determined whether the minimum width (i.e., the minimum lane width requirement) limit can be met after expansion. If not, expansion will not be performed.

[0068] In order not to affect the traffic of vehicles in other lanes, the expanded width should not be too large and should generally be within the hard boundary on the same side.

[0069] like Figure 7 As shown in Figure 1, in order to ensure the stability of the boundary and reduce unnecessary detours, the obstacle is expanded in the necessary s direction. s -3,end s +2,start l -0.4,end l +0.4), so for a road section with obstacles on one side, such as Figure 6 The l3 and r2 shown in the figure do not need to be extended longitudinally. For a road section with obstacles on both sides, such as Figure 7 l2 and r1 shown in the upper part are as follows Figure 7 Expand in the manner shown in the lower half.

[0070] like Figure 8 As shown, it is divided into two aspects of inspection: left and right width, that is: s i Whether the width of the left and right boundaries corresponding to the location is greater than the minimum width (i.e., the minimum lane width requirement). i Similar, except that the minimum lane width requirement is relatively conservative. Front and rear length: When you need to avoid obstacles in different directions continuously, you need to ensure that there is enough distance between two consecutive obstacle avoidances to adjust the vehicle posture. Figure 8 In the above example, the distance between the two sections l1 and r1 must meet the set threshold.

[0071] The threshold ds is related to the boundary difference dl between the two road sections. The value of ds is determined based on dl, and the relationship is as follows:

[0072] ds=-k*dl+d,k>0,d>0.

[0073] S104: If yes, then the lane boundary is extended, wherein the extended lane boundary is located within the obstacle boundary. Of course, when it is determined that the lane boundary extension condition is not met, the path planning is re-performed.

[0074] According to the path decision post-processing method of the vehicle in the embodiment of the present application, after obtaining the lane boundary, obstacle boundary and the obstacle distribution on the lane boundary, it is determined whether the lane boundary expansion condition is met according to the obstacle distribution and the lane minimum width requirement value. When the expansion condition is met, the lane boundary is expanded. Therefore, for vehicles, especially for vehicles with larger body sizes such as driving, the path planning constraints are divided into two types of soft and hard constraints, which are used to constrain the wheels and the body respectively during path optimization, expanding the optimized solution space, and by expanding the soft and hard boundaries to a certain extent, the drivable space boundaries are made more neat, thereby making the optimized path smoother. The two boundaries are used to generate the drivable space boundaries of the truck, which expands the drivable space of the truck and improves the flexibility of the truck on roads with large curvature. On the other hand, by post-processing the boundaries, the left and right boundaries are made more consistent, providing a more reasonable solution space for subsequent path optimization, ensuring that the generated path is smoother and reducing unnecessary left and right detours. The size of the vehicle is taken into consideration, so it is more reasonable and reliable when judging the sampling point block.

[0075] Fig. 9 FIG. 1 is a structural block diagram of a vehicle path decision post-processing system according to an embodiment of the present application. Fig. 9 As shown, a path decision post-processing system for a vehicle according to an embodiment of the present application includes: an acquisition module 910, an obstacle detection module 920, a judgment module 930 and an expansion module 940, wherein:

[0076] An acquisition module 910 is used to obtain a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary;

[0077] The obstacle detection module 920 is used to obtain the obstacle distribution on the lane boundary;

[0078] A judgment module 930, configured to judge whether the lane boundary expansion condition is met according to the distribution of the obstacles and the lane minimum width requirement value, wherein the lane minimum width requirement value is obtained according to vehicle parameters and road parameters;

[0079] The expansion module 940 is used to expand the lane boundary when the expansion condition of the lane boundary is met, wherein the expanded lane boundary is located within the obstacle boundary.

[0080] According to the path decision post-processing system of the vehicle in the embodiment of the present application, after obtaining the lane boundary, obstacle boundary and the obstacle distribution on the lane boundary, it is determined whether the lane boundary expansion condition is met according to the obstacle distribution and the lane minimum width requirement value. When the expansion condition is met, the lane boundary is expanded. Therefore, for vehicles, especially for vehicles with larger body sizes such as driving, the path planning constraints are divided into two types of soft and hard constraints, which are used to constrain the wheels and the body respectively during path optimization, expanding the optimized solution space, and by expanding the soft and hard boundaries to a certain extent, the drivable space boundary is made more neat, thereby making the optimized path smoother. The two boundaries are used to generate the drivable space boundary of the truck, which expands the drivable space of the truck and improves the flexibility of the truck on roads with large curvature. On the other hand, by post-processing the boundaries, the left and right boundaries are made more consistent, providing a more reasonable solution space for subsequent path optimization, ensuring that the generated path is smoother and reducing unnecessary left and right detours. The size of the vehicle is taken into consideration, so it is more reasonable and reliable when judging the sampling point block.

[0081] For the specific definition of the vehicle's path decision post-processing system, please refer to the definition of the vehicle's path decision post-processing method above, which will not be repeated here. The various modules of the above-mentioned vehicle's path decision post-processing system can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0082] In one embodiment, a vehicle is provided, comprising: a path decision post-processing system for a vehicle according to the above embodiment. After the vehicle obtains the lane boundary, the obstacle boundary and the obstacle distribution on the lane boundary, it determines whether the lane boundary expansion condition is met according to the obstacle distribution and the lane minimum width requirement value, and when the expansion condition is met, the lane boundary is expanded. Therefore, for vehicles, especially for vehicles with larger body sizes such as driving, the path planning constraints are divided into two types of soft and hard constraints, which are used to constrain wheels and body respectively during path optimization, thereby expanding the optimized solution space, and by expanding the soft and hard boundaries to a certain extent, the drivable space boundary is made more neat, thereby making the optimized path smoother. The two boundaries are used to generate the drivable space boundary of the truck, which expands the drivable space of the truck and improves the flexibility of the truck on roads with large curvature. On the other hand, by post-processing the boundaries, the left and right boundaries are made more consistent, providing a more reasonable solution space for subsequent path optimization, ensuring that the generated path is smoother and reducing unnecessary left and right detours. The size of the vehicle is taken into consideration, so it is more reasonable and reliable when judging the sampling point block.

[0083] In addition, other structures and functions of the vehicle according to the embodiment of the present application are known to ordinary technicians in the field and will not be elaborated here.

[0084] In one embodiment, a computer device is provided. Fig.10 This is a block diagram of the computer device provided in the embodiment of the present application, refer to Fig.10 The computer device includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the embodiment of the path decision post-processing method of the vehicle is implemented. For example, the following steps are performed: obtaining a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary;

[0085] Obtain the obstacle distribution on the lane boundary;

[0086] Determining whether the lane boundary expansion condition is met according to the distribution of the obstacles and the required minimum lane width, wherein the required minimum lane width is obtained according to vehicle parameters and road parameters;

[0087] If yes, the lane boundary is extended, wherein the extended lane boundary is located within the obstacle boundary.

[0088] The embodiment of the present application also provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the processor executes the computer program to implement the above-mentioned vehicle path decision post-processing method embodiment. For example, the following steps are performed: obtaining a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheel, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary;

[0089] Obtain the obstacle distribution on the lane boundary;

[0090] Determining whether the lane boundary expansion condition is met according to the distribution of the obstacles and the required minimum lane width, wherein the required minimum lane width is obtained according to vehicle parameters and road parameters;

[0091] If yes, the lane boundary is extended, wherein the extended lane boundary is located within the obstacle boundary.

[0092] The present application embodiment provides a computer program product, which includes instructions. When the instructions are executed, the method described in the embodiment of the present application is executed. For example, it can be executed Figure 1The various steps of the vehicle path decision post-processing method shown, for example, are performed: obtaining a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary;

[0093] Obtain the obstacle distribution on the lane boundary;

[0094] Determining whether the lane boundary expansion condition is met according to the distribution of the obstacles and the required minimum lane width, wherein the required minimum lane width is obtained according to vehicle parameters and road parameters;

[0095] If yes, the lane boundary is extended, wherein the extended lane boundary is located within the obstacle boundary.

[0096] Those of ordinary skill in the art can understand that all or part of the processes in the methods for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0097] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0098] The above embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A vehicle path decision post-processing method, characterized in that: include: Obtaining a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary; Obtain the obstacle distribution on the lane boundary; Determining whether the lane boundary expansion condition is met according to the distribution of the obstacles and the required minimum lane width, wherein the required minimum lane width is obtained according to vehicle parameters and road parameters; If yes, the lane boundary is extended, wherein the extended lane boundary is located within the obstacle boundary.

2. The vehicle path decision post-processing method according to claim 1, characterized in that: The vehicle parameters include vehicle length, wheelbase and vehicle width, the road parameters include road curvature, and the method further includes: Obtaining a turning radius according to the road curvature; The minimum lane width requirement value is obtained according to the vehicle length, wheelbase, vehicle width and turning radius.

3. The vehicle path decision post-processing method according to claim 1, characterized in that: The determining, based on the distribution of the obstacles and the required value of the minimum lane width, whether the lane boundary expansion condition is met includes: If there is an obstacle on one side of the lane boundary, further determining whether the width of the lane boundary after expansion is less than or equal to the required minimum lane width; If yes, it is determined that the extension condition of the lane boundary is satisfied.

4. The vehicle path decision post-processing method according to claim 3, characterized in that: If there are obstacles on both sides of the lane boundary, the obstacles on both sides are longitudinally extended according to their leftmost and rightmost positions in the longitudinal direction; After longitudinally extending the obstacles on both sides, determining whether the width of the lane boundary after expansion is less than or equal to the required minimum lane width; If yes, further determine whether the longitudinal distance between the obstacles on both sides after expansion and the adjacent obstacles in the lateral direction is greater than a threshold; If yes, it is determined that the extension condition of the lane boundary is satisfied.

5. The vehicle path decision post-processing method according to claim 4, characterized in that: The threshold is related to the longitudinal distance between the obstacles on both sides.

6. The vehicle path decision post-processing method according to claim 1, characterized in that: Also includes: When it is determined that the lane boundary extension condition is not met, the path planning is performed again.

7. A vehicle path decision post-processing system, characterized in that: include: An acquisition module, used to obtain a lane boundary and an obstacle boundary, wherein the lane boundary is used to constrain the wheels, the obstacle boundary is used to constrain the vehicle body, and the obstacle boundary is obtained by expanding the lane boundary; Obstacle detection module, used to obtain the distribution of obstacles on the lane boundary; A judgment module, used to judge whether the lane boundary expansion condition is met according to the distribution of the obstacles and the lane minimum width requirement value, wherein the lane minimum width requirement value is obtained according to vehicle parameters and road parameters; An expansion module is used to expand the lane boundary when the expansion condition of the lane boundary is met, wherein the expanded lane boundary is located within the obstacle boundary.

8. A vehicle, characterized in that: include: The vehicle path decision post-processing system according to claim 7.

9. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the path decision post-processing method for the vehicle according to any one of claims 1-6 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the path decision post-processing method for a vehicle according to any one of claims 1 to 6 is implemented.

Images