Determining method and device, equipment and storage medium

Abstract

The invention discloses a detouring mode determination method, device and equipment and a storage medium, and relates to the technical field of vehicles, and the method comprises the steps: determining a sampling point in a passing area of a vehicle, and carrying out the dynamic planning of the vehicle according to an obstacle in the passing area and the sampling point, and obtaining a plurality of planned coarse trajectories; determining detour labels of sampling points and secondary sampling points forming each planned coarse trajectory according to the obstacles, and dividing the passage area into a plurality of sub-areas according to the detour labels of the sampling points and the secondary sampling points; determining a target planning coarse trajectory according to the loss value of each target coarse trajectory after determining the target coarse trajectory of each sub-region; and determining a bypassing mode of the vehicle to the target obstacle according to the position relationship between the target obstacle and the target planning coarse trajectory. According to the technical scheme, the bypassing mode of the vehicle to the target obstacle provides accurate bypassing suggestions for path planning, the occurrence of repeated bypassing of the obstacle is reduced, and the accuracy and efficiency of path planning are improved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of vehicle technology, and in particular, to a method, device, equipment and storage medium for determining a detour. Background Art

[0002] In recent years, driverless technology has become a hot topic. Autonomous driving technology mainly includes: perception, prediction, planning and decision-making, control, etc. In traditional planning operations, obstacles ahead are mainly avoided by decision-making choices such as longitudinal deceleration or lateral detour.

[0003] In the prior art, in lateral detour avoidance decisions, generally only a decision is made on whether to detour, and the detour direction is less involved.

[0004] Therefore, there is an urgent need for a method for determining a detour method to determine a vehicle's detour method around an obstacle. Summary of the invention

[0005] The present invention provides a method, device, equipment and storage medium for determining a detour method for a vehicle to avoid an obstacle.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining a detour mode, including:

[0007] Determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories;

[0008] Determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points;

[0009] After determining the target rough trajectory of each sub-area, determining the target planning rough trajectory according to the loss value of each target rough trajectory, wherein the loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and the historical trajectory;

[0010] The method for the vehicle to bypass the target obstacle is determined according to the positional relationship between the target obstacle and the target planned rough trajectory.

[0011] The technical solution of an embodiment of the present invention provides a method for determining a detour method, comprising: determining sampling points in a vehicle's passage area, dynamically planning the vehicle according to obstacles in the passage area and the sampling points, and obtaining multiple planned rough trajectories; determining detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and dividing the passage area into multiple sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points; after determining a target rough trajectory for each of the sub-areas, determining a target planned rough trajectory according to a loss value of each of the target rough trajectories, wherein the loss value of the target rough trajectory is determined by the obstacles, the sampling points and secondary sampling points constituting the target rough trajectory, and a historical trajectory; and determining a detour method for the vehicle with respect to the target obstacle according to a positional relationship between the target obstacle and the target planned rough trajectory. The above technical solution can first determine the sampling points in the passage area by sampling the passage area of ​​the vehicle, and dynamically plan the vehicle according to the sampling points and obstacles in the passage area to determine multiple planned rough trajectories, so as to determine the initial path planning of the vehicle. After determining the sampling points and secondary sampling points constituting each planned rough trajectory, the detour labels of the sampling points and secondary sampling points are determined according to the positional relationship between the vehicle rectangular frame of the sampling points and secondary sampling points constituting each planned rough trajectory and the obstacle rectangular frame within the preset range of the sampling points and secondary sampling points, and the passage area is divided into multiple sub-areas according to the detour labels of each sampling point and each secondary sampling point, so as to realize the division of the passage area. Secondly, the target rough trajectory in each sub-area can be determined according to the dynamic planning loss of each planned rough trajectory in each sub-area, and the target planned rough trajectory can be determined according to the loss value of each target rough trajectory, so as to realize the determination of the target planned rough trajectory. Then, the detour method of the vehicle for the target obstacle can be determined according to the positional relationship between the target obstacle and the target planned rough trajectory, so as to provide accurate detour suggestions for the path planning near the target obstacle, reduce the occurrence of repeated detours for obstacles, and improve the accuracy and efficiency of path planning.

[0012] Furthermore, before determining the sampling point in the vehicle's passage area, the method further includes:

[0013] A reference line is generated according to the current position of the vehicle and the global planned path, and the passage area is determined according to the current planned starting point of the vehicle, the reference line and environmental information.

[0014] Further, generating a reference line according to the current position of the vehicle and the global planning path, and determining the passage area according to the current planning starting point of the vehicle, the reference line and environmental information, including:

[0015] Taking the current position as the starting point, extending forward a preset distance along the global planning path to generate the reference line;

[0016] Taking the current planning starting point as the starting point, multiple preview points are determined on the reference line based on a preset step size, and the two side boundaries corresponding to each preview point are determined according to the lane line type on both sides of each preview point determined according to the environmental information, and the passage area is determined according to the two side boundaries corresponding to each preview point.

[0017] Furthermore, the vehicle is dynamically planned according to the obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories, including:

[0018] Determine a track smoothness loss value of each sampling point according to the position information of each sampling point, determine an obstacle loss value of each sampling point according to the position information of each sampling point and each obstacle, and determine a cumulative loss value of each sampling point according to the track smoothness loss value and the obstacle loss value of each sampling point;

[0019] A plurality of planned rough trajectories are constructed according to the sampling points with the smallest cumulative loss value in each column of the sampling points.

[0020] Furthermore, determining detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles includes:

[0021] Performing secondary sampling on each of the planned rough trajectories to obtain the secondary sampling points constituting each of the planned rough trajectories;

[0022] Determine a detour label for each of the secondary sampling points according to the position information of the sampling points and the secondary sampling points constituting each of the planned rough trajectories and the obstacles.

[0023] Further, determining the detour label of each secondary sampling point according to the position information of the sampling points and each secondary sampling point constituting each planned rough trajectory and each obstacle includes:

[0024] When the obstacle is a static obstacle, determining the detour label of the secondary sampling point according to the positional relationship between the vehicle rectangular frame when the vehicle is projected to the sampling point or the secondary sampling point and the obstacle rectangular frame of the obstacle within a preset range of the sampling point or the secondary sampling point;

[0025] When the obstacle is a dynamic obstacle, a vehicle rectangular frame of the vehicle at the sampling point or the secondary sampling point and a projection time are determined by projecting the sampling point or the secondary sampling point onto a predicted trajectory of the vehicle, an obstacle rectangular frame of the obstacle at the projection time is determined in the predicted trajectory of the obstacle, and a detour label of the sampling point or the secondary sampling point is determined according to a positional relationship between the vehicle rectangular frame and the obstacle rectangular frame of the obstacle corresponding to the same projection time.

[0026] Furthermore, the passage area is divided into a plurality of sub-areas according to the detour labels of each sampling point and each secondary sampling point, including:

[0027] The passage area is divided into a plurality of sub-areas according to the detour labels of the sampling points and the secondary sampling points belonging to the same column.

[0028] Further, determining the target rough trajectory of each sub-area includes:

[0029] The dynamic programming loss value of each of the planned rough trajectories in each of the sub-regions is determined, and the planned rough trajectory with the smallest dynamic programming loss value in each of the sub-regions is determined as the target rough trajectory in each of the sub-regions.

[0030] Further, determining the target planning rough trajectory according to the loss value of each target rough trajectory includes:

[0031] Determine the historical trajectory deviation loss value of each target rough trajectory according to the position information of each sampling point constituting each target rough trajectory and the projection position of each sampling point constituting each target rough trajectory on the historical trajectory, determine the obstacle loss value of each target rough trajectory according to the position information of each sampling point constituting each planned rough trajectory and each obstacle, and determine the loss value of each target rough trajectory according to the historical trajectory deviation loss value and the obstacle loss value of each target rough trajectory;

[0032] The target rough trajectory with the smallest loss value is determined as the target planning rough trajectory.

[0033] Furthermore, when the obstacle loss value of each sampling point is determined according to the position information of each sampling point and each obstacle, it also includes:

[0034] If it is determined that the obstacle has an increasing effect on the obstacle loss value of the sampling point, the obstacle is determined to be the target obstacle.

[0035] Furthermore, determining a circumvention method of the vehicle for the target obstacle according to a positional relationship between the target obstacle and the target planned coarse trajectory includes:

[0036] Determining a target point corresponding to the target obstacle in the target planning rough trajectory;

[0037] A way for the vehicle to bypass the target obstacle is determined according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle.

[0038] Further, determining a circumvention method of the vehicle for the target obstacle according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle includes:

[0039] When the target point corresponding to the target obstacle is located on the left side of the target obstacle, determining that the detour method of the vehicle for the target obstacle is to detour to the left;

[0040] When the target point corresponding to the target obstacle is located on the right side of the target obstacle, it is determined that the detour method of the vehicle around the target obstacle is to detour to the right.

[0041] In a second aspect, an embodiment of the present invention further provides a detour method determination device, including:

[0042] A planning module, used to determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories;

[0043] a division module, configured to determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and to divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points;

[0044] A determination module, configured to determine a target planning rough trajectory according to a loss value of each target rough trajectory after determining the target rough trajectory of each sub-area, wherein the loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and a historical trajectory;

[0045] The execution module is used to determine the circumvention method of the vehicle around the target obstacle according to the positional relationship between the target obstacle and the target planned rough trajectory.

[0046] In a third aspect, an embodiment of the present invention further provides an electronic device, including:

[0047] at least one processor; and a memory communicatively coupled to the at least one processor;

[0048] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the detour determination method as described in any one of the first aspects.

[0049] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute a detour determining method as described in any one of the first aspects.

[0050] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes the detour determination method provided in the first aspect.

[0051] It should be noted that the above-mentioned computer instructions may be stored in whole or in part on a computer-readable storage medium. The computer-readable storage medium may be packaged together with the processor of the detour determining device, or may be packaged separately from the processor of the detour determining device, and this application does not limit this.

[0052] The description of the second, third, fourth and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, fourth and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0053] In this application, the name of the above-mentioned detour mode determination device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they belong to the scope of the claims of this application and their equivalent technologies.

[0054] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0056] Figure 1 A flowchart of a method for determining a detour provided by an embodiment of the present invention;

[0057] Figure 2 A flowchart of another method for determining a detour provided by an embodiment of the present invention;

[0058] Figure 3 A schematic diagram of determining a dynamic obstacle rectangular frame in a detour determination method provided by an embodiment of the present invention;

[0059] Figure 4a and 4b A schematic diagram of dividing a traffic area in a method for determining a detour provided in an embodiment of the present invention;

[0060] Figure 5 A schematic diagram of the structure of a detour mode determination device provided by an embodiment of the present invention;

[0061] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0063] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0064] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0065] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0066] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.

[0067] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0068] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0069] Figure 1 A flowchart of a method for determining a detour method provided in an embodiment of the present invention. This embodiment is applicable to a situation where a detour method for a vehicle to an obstacle needs to be determined. The method can be executed by a detour method determination device, such as Figure 1 As shown, the specific steps include:

[0070] Step 110 : determining sampling points in a passage area of ​​the vehicle, and dynamically planning the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories.

[0071] Specifically, when the vehicle is running in an automatic driving mode, trajectory planning can be performed in the passage area, and the passage area is determined by the lane in which the vehicle is currently located. After determining the passage area of ​​the vehicle, sampling can be performed within the passage area based on the preset sampling rules to determine the sampling points. The sl coordinate system is constructed with the starting point of the reference line as the origin, the forward direction of the reference line as the positive direction of s, and the left side of the forward direction as the positive direction of l. Obstacles in the passage area are determined, and the obstacles may include static obstacles and dynamic obstacles. For static obstacles, the obstacle rectangular frame of the static obstacle can be projected to the sl coordinate system to obtain the sl coordinate set of the four corner points of the static obstacle, and the static obstacle array is determined according to each static obstacle and the sl coordinate set of the four corner points of each static obstacle. For dynamic obstacles, the dynamic preset time of the dynamic obstacle can be obtained, and the dynamic preset time can be the minimum value of the trajectory prediction time of the dynamic obstacle and the speed planning trajectory time of the vehicle. According to the preset time step, the dynamic preset time is traversed to obtain the sl coordinate set of the four corner points of the obstacle rectangle of the dynamic obstacle at each time step after being projected to the sl coordinate system, and the dynamic obstacle array is determined according to each dynamic obstacle and the sl coordinate set of the four corner points of each dynamic obstacle at each time step. In addition, if there is no predicted trajectory of the dynamic obstacle at any time step, the position of the dynamic obstacle is obtained by linear interpolation, and the sl coordinate set of the four corner points of the obstacle rectangle of the dynamic obstacle at the time step after being projected to the sl coordinate system is determined according to the position of the dynamic obstacle.

[0072] In practical applications, in order to improve calculation accuracy, the obstacle rectangle can be appropriately enlarged and expanded during the projection to the SL coordinate system. The size of the enlargement and expansion is related to the obstacle type and movement speed. That is, the expansion multiple of a dynamic obstacle is greater than that of a static obstacle, and the expansion multiple of a dynamic obstacle with a high movement speed is greater than that of a dynamic obstacle with a low movement speed.

[0073] The obstacle information can be composed of a static obstacle array and a dynamic obstacle array. The vehicle is dynamically planned according to the sampling points and obstacle information in the passage area. Specifically, the s direction of the sl coordinate system is the column direction, and the l direction is the row direction. Starting from the current planning starting point of the vehicle, the sampling points on each row between two adjacent columns in the passage area are traversed in a loop, and the two points are fitted into a curve based on a fifth-order polynomial. The cumulative loss value between each sampling point on the previous column and each sampling point on the next column is calculated according to the preset s step size. As s increases, the cumulative loss value will gradually increase, and finally the cumulative loss value of all sampling points is obtained. Compare the cumulative loss values ​​of each sampling point, select the points with the smallest cumulative loss value in each column of sampling points in turn to form a point set, and obtain multiple planned rough trajectories.

[0074] It should be noted that the cumulative loss value is determined by the trajectory smoothness loss function and the obstacle loss function. The trajectory smoothness loss function is used to measure the trajectory smoothness of the planned rough trajectory composed of the sampling points, and the obstacle loss function is used to measure the distance between the vehicle and the obstacle when driving on the planned rough trajectory composed of the sampling points.

[0075] In the embodiment of the present invention, dynamic planning of the vehicle is implemented according to the sampling points and obstacles in the passage area to obtain a plurality of planned rough trajectories.

[0076] Step 120: Determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points.

[0077] Specifically, for each planned rough trajectory, secondary sampling can be performed between each sampling point constituting the planned rough trajectory to obtain the secondary sampling points constituting the planned rough trajectory. Then, the detour labels of the sampling points and secondary sampling points constituting the planned rough trajectory can be determined according to the obstacle information. First, the vehicle can be projected to each sampling point and each secondary sampling point to obtain the vehicle rectangular frame corresponding to each sampling point and each secondary sampling point. Secondly, the obstacles within the preset range of each sampling point and each secondary sampling point can be determined. For static obstacles, the detour labels of the sampling points or secondary sampling points can be determined according to the positional relationship between the static obstacle rectangular frame and the vehicle rectangular frame. For dynamic obstacles, the dynamic preset time of the dynamic obstacle can be traversed according to the preset time step to determine the dynamic obstacle rectangular frame corresponding to each time step of the dynamic obstacle. After determining the time when the vehicle arrives at the sampling point or the secondary sampling point, if the time when the vehicle arrives at the sampling point or the secondary sampling point overlaps with the time step of the dynamic obstacle, the detour labels of the sampling point or the secondary sampling point are determined according to the positional relationship between the dynamic obstacle rectangular frame and the vehicle rectangular frame.

[0078] Furthermore, the passage area can be divided into multiple sub-areas according to the detour labels of each sampling point and each secondary sampling point. Specifically, if the detour labels of each sampling point and each secondary sampling point belonging to adjacent columns are consistent, the two columns are divided into one sub-area, otherwise, the two columns are divided into different sub-areas, thereby achieving the division of the passage area into multiple sub-areas.

[0079] In the embodiment of the present invention, detour labels of the sampling points and the secondary sampling points are determined according to the positional relationship between the vehicle rectangular frames of the sampling points and the secondary sampling points constituting each planned coarse trajectory and the obstacle rectangular frames within a preset range of the sampling points and the secondary sampling points, and the passage area is divided into a plurality of sub-areas according to the detour labels of the sampling points and the secondary sampling points, thereby realizing the division of the passage area.

[0080] Step 130: After determining the target rough trajectory of each sub-area, determine the target planning rough trajectory according to the loss value of each target rough trajectory.

[0081] The loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and the historical trajectory.

[0082] Specifically, after dividing the traffic area into multiple sub-areas, the planned rough trajectory of each sub-area can be determined, and the dynamic programming loss of each planned rough trajectory in each sub-area can also be determined, and the planned rough trajectory with the smallest loss in each sub-area can be determined as the target rough trajectory of each sub-area. Furthermore, the loss value of each target rough trajectory can be determined, specifically, the loss value of each target rough trajectory can be determined based on the historical trajectory deviation loss function and the obstacle loss function, and the target rough trajectory with the earliest loss value can be determined as the target planned rough trajectory.

[0083] In an embodiment of the present invention, after determining the target rough trajectory in each sub-area according to the dynamic programming loss of each planned rough trajectory in each sub-area, the loss value of each target rough trajectory is determined, and the target planned rough trajectory is determined according to the loss value of each target rough trajectory, thereby determining the target planned rough trajectory.

[0084] Step 140: Determine a circumvention method for the vehicle around the target obstacle according to a positional relationship between the target obstacle and the target planned coarse trajectory.

[0085] When determining the cumulative loss value of each sampling point according to the trajectory smoothness loss function and the obstacle loss function, if an obstacle has an increasing effect on the cumulative loss value of any sampling point, the obstacle is determined as a target obstacle.

[0086] Specifically, first, the corresponding target point of the target obstacle in the target planning coarse trajectory can be determined, that is, the trajectory point in the target coarse trajectory that is closest to the target obstacle can be determined as the corresponding target point of the target obstacle in the target planning coarse trajectory. Secondly, the positional relationship between the target obstacle and the target planning coarse trajectory can be determined according to the positional relationship between the target obstacle and the corresponding target point of the target obstacle in the target planning coarse trajectory. Then, the vehicle's bypassing method for the target obstacle can be determined according to the positional relationship between the target obstacle and the target planning coarse trajectory. That is, if the target planning coarse trajectory is located on the left side of the target obstacle, then the bypassing method of the target obstacle is determined to be bypassing to the left. If the target planning coarse trajectory is located on the right side of the target obstacle, then the bypassing method of the target obstacle is determined to be bypassing to the right.

[0087] In an embodiment of the present invention, a detour method for a vehicle around a target obstacle is determined based on a positional relationship between the target obstacle and a target planned coarse trajectory, and accurate detour suggestions are provided for the vehicle when it is traveling near the target obstacle, thereby reducing the occurrence of repeated detours around obstacles and improving the accuracy and efficiency of path planning.

[0088] The method for determining a detour method provided by an embodiment of the present invention includes: determining sampling points in a vehicle's passage area, dynamically planning the vehicle according to obstacles in the passage area and the sampling points, and obtaining multiple planned rough trajectories; determining detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and dividing the passage area into multiple sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points; after determining a target rough trajectory of each of the sub-areas, determining a target planned rough trajectory according to a loss value of each of the target rough trajectories, wherein the loss value of the target rough trajectory is determined by the obstacles, the sampling points and the secondary sampling points constituting the target rough trajectory, and a historical trajectory; and determining a detour method of the vehicle for the target obstacle according to a positional relationship between the target obstacle and the target planned rough trajectory. The above technical solution can first determine the sampling points in the passage area by sampling the passage area of ​​the vehicle, and dynamically plan the vehicle according to the sampling points and obstacles in the passage area to determine multiple planned rough trajectories, so as to determine the initial path planning of the vehicle. After determining the sampling points and secondary sampling points constituting each planned rough trajectory, the detour labels of the sampling points and secondary sampling points are determined according to the positional relationship between the vehicle rectangular frame of the sampling points and secondary sampling points constituting each planned rough trajectory and the obstacle rectangular frame within the preset range of the sampling points and secondary sampling points, and the passage area is divided into multiple sub-areas according to the detour labels of each sampling point and each secondary sampling point, so as to realize the division of the passage area. Secondly, the target rough trajectory in each sub-area can be determined according to the dynamic planning loss of each planned rough trajectory in each sub-area, and the target planned rough trajectory can be determined according to the loss value of each target rough trajectory, so as to realize the determination of the target planned rough trajectory. Then, the detour method of the vehicle for the target obstacle can be determined according to the positional relationship between the target obstacle and the target planned rough trajectory, so as to provide accurate detour suggestions for the path planning near the target obstacle, reduce the occurrence of repeated detours for obstacles, and improve the accuracy and efficiency of path planning.

[0089] Figure 2 This is a flow chart of another method for determining a detour provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. Figure 2 As shown, in this embodiment, the method may further include:

[0090] Step 210: Generate a reference line according to the current position of the vehicle and the global planned path, and determine the passage area according to the current planned starting point of the vehicle, the reference line and environmental information.

[0091] In one implementation, step 210 may specifically include:

[0092] Taking the current position as the starting point, extending forward a preset distance along the global planning path to generate the reference line; taking the current planning starting point as the starting point, determining multiple preview points on the reference line based on a preset step size, determining the two side boundaries corresponding to each preview point according to the lane line type on both sides of each preview point determined by the environmental information, and determining the passage area according to the two side boundaries corresponding to each preview point.

[0093] Specifically, the vehicle can obtain the environmental information around it and perform global planning based on the environmental information to obtain the global planning information. After determining the global planning information of the vehicle, the vehicle's current position is used as the starting point to extend the preset distance along the global planning path to generate a reference line. The specific value of the preset distance is related to the accuracy of the radar and image acquisition device installed on the vehicle.

[0094] Then, taking the current planning starting point of the vehicle as the starting point, multiple preview points are determined on the reference line based on the preset step length. For example, 100m is previewed forward at 0.5m on the reference line, and 200 preview points are determined. The lane line type on both sides of each preview point is determined according to the environmental information. Specifically, taking the left side of the preview point as an example, if the lane line on the left side of the preview point is a solid line, the left boundary of the lane where the reference line is located is determined as the left boundary of the pass area; if the lane line on the left side of the preview point is a dotted line, it is determined whether there is a left adjacent lane to the preview point. If there is a left adjacent lane, the left boundary of the left adjacent lane is determined as the left boundary of the pass area. If there is no left adjacent lane, the left boundary of the lane where the reference line is located is determined as the left boundary of the pass area. Based on the same steps, the right boundary of the pass area can be determined, and the rear boundary and the front boundary of the pass area can be determined according to the current planning starting point and the preset distance, and then the pass area can be determined according to the left boundary, the right boundary, the rear boundary and the front boundary.

[0095] In an embodiment of the present invention, after a reference line is generated according to the current position of the vehicle and the global planned path, the passable area is determined according to the current planned starting point of the vehicle, the reference line and environmental information, so as to accurately determine the passable range of the vehicle and facilitate the path planning of the vehicle.

[0096] Step 220: Determine sampling points within the vehicle's passage area.

[0097] Specifically, sampling can be performed within the traffic area based on a preset sampling rule to determine the sampling points, wherein the preset sampling rule can be equal-interval sampling or equal-point number sampling, etc.

[0098] Of course, during sampling, denser sampling can be performed in areas close to the vehicle, and sparser sampling can be performed in areas far from the vehicle.

[0099] In the embodiment of the present invention, the sampling points are determined within the vehicle's passage area.

[0100] Step 230: Dynamically plan the vehicle according to the obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories.

[0101] In one implementation, step 230 may specifically include:

[0102] Determine the trajectory smoothness loss value of each sampling point according to the position information of each sampling point, determine the obstacle loss value of each sampling point according to the position information of each sampling point and each obstacle, determine the cumulative loss value of each sampling point according to the trajectory smoothness loss value and the obstacle loss value of each sampling point; and construct a plurality of planned rough trajectories according to the sampling point with the smallest cumulative loss value in each column of the sampling points.

[0103] Specifically, after determining the coordinates of the sampling point in the sl coordinate system, the trajectory smoothness loss value of the sampling point is determined according to the coordinates of the sampling point in the sl coordinate system. The trajectory smoothness loss function is composed of the loss function in the l direction, the loss function of the derivative dl of l with respect to s, and the loss function of the second-order derivative ddl of l with respect to s, and the loss function in the l direction is characterized by: the larger the l, the larger the loss function value, the loss function of the derivative dl of l with respect to s is characterized by: the larger the dl, the larger the loss function value, and the loss function of the second-order derivative ddl of l with respect to s is characterized by: the larger the ddl, the larger the loss function value. The loss function in the l direction, the loss function of the derivative dl of l with respect to s, and the loss function of the second-order derivative ddl of l with respect to s can be composed of a direct proportional function, an exponential function, or a quadratic function, but are not limited to these function forms.

[0104] For example, the track smoothness loss value of the sampling point may be determined based on Formula 1.

[0105]

[0106] Among them, cost1 represents the trajectory smoothness loss function, cost l_i =k l *l*l, represents the loss value of the i-th sampling point in the l-direction, l represents the coordinate of the i-th sampling point in the l-direction, k l Represents the proportionality coefficient, cost dl_i =k dl *dl*dl, dl represents the derivative of l with respect to s at the i-th sampling point, k dl Represents the proportionality coefficient, cost ddl_i =k ddl *ddl*ddl, ddl represents the second-order derivative of l with respect to s at the i-th sampling point, k ddlrepresents the proportional coefficient, and n represents the number of sampling points in the passage area.

[0107] When the obstacle is a static obstacle, a static obstacle located outside the left and right adjacent lanes of the vehicle in the l direction and a static obstacle that is more than a preset distance away from the vehicle in the s direction will not generate any loss and can be ignored when calculating the obstacle loss value; for static obstacles located in the left and right adjacent lanes of the vehicle in the l direction, the closer the lateral distance to the vehicle is, the greater the obstacle loss value is; if the obstacle rectangle overlaps with the vehicle rectangle projected on the sampling point, there is a collision at the sampling point and the obstacle loss value is infinite.

[0108] When the obstacle is a dynamic obstacle, the current speed planning trajectory of the vehicle is obtained. On the one hand, the speed planning trajectory obtained by the vehicle in the previous cycle can be used as the current speed planning trajectory of the vehicle. On the other hand, taking the current planning starting point as the starting point, only considering the vehicle's cruising speed, lane speed limit, curve speed limit and self-vehicle dynamic characteristics, the current speed planning trajectory of the vehicle is obtained by applying the quadratic programming algorithm; Figure 3 A schematic diagram of determining a dynamic obstacle rectangular frame in a detour determination method provided by an embodiment of the present invention, such as Figure 3 As shown, the dynamic preset time of the dynamic obstacle is traversed with a preset time step, the vehicle's current speed planning trajectory is projected to the corresponding time step position, the dynamic obstacle rectangle corresponding to the time step position is obtained, and the dynamic obstacle rectangle is used as the static obstacle rectangle to calculate the obstacle loss value.

[0109] For example, the obstacle loss value of the sampling point can be determined based on Formula 2.

[0110]

[0111] Among them, cost2 represents the obstacle loss function, dis_thred represents the distance threshold, delta_l j represents the distance from the i-th sampling point to the j-th obstacle in the l direction, k obs is the proportional coefficient, n represents the number of sampling points in the passage area, and m represents the number of obstacles in the passage area.

[0112] Furthermore, the cumulative loss value of the sampling point can be determined by summing the trajectory smoothness loss value and the obstacle loss value of the sampling point, that is, COST1=cost1+cost2 can be determined, where COST1 represents the cumulative loss function of the sampling point. After determining the cumulative loss value of each sampling point, the cumulative loss values ​​of each column of sampling points are compared, and multiple planned rough trajectories are constructed based on the sampling point with the smallest cumulative loss value in each column of sampling points.

[0113] In addition, when the obstacle loss value of each sampling point is determined according to the position information of each sampling point and each obstacle, it also includes:

[0114] If it is determined that the obstacle has an increasing effect on the obstacle loss value of the sampling point, the obstacle is determined to be the target obstacle.

[0115] When determining the obstacle loss value of each sampling point, for a static obstacle, if the obstacle has an increasing effect on the obstacle loss value of any sampling point, it is determined that the obstacle has an impact on the lateral planning and is determined to be a target obstacle. For a dynamic obstacle, if the obstacle projection frame has an increasing effect on the obstacle loss value of any sampling point, the obstacle projection frame is determined as a static obstacle and is determined as a target obstacle, and the position information of the target obstacle is determined by the projection position of the obstacle projection frame.

[0116] In the embodiment of the present invention, dynamic planning of the vehicle is implemented according to the sampling points and obstacles in the passage area to obtain a plurality of planned rough trajectories.

[0117] Step 240: Determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles.

[0118] In one implementation, step 240 may specifically include:

[0119] Each of the planned rough trajectories is subsampled to obtain the subsampling points constituting each of the planned rough trajectories; and a detour label of each of the subsampling points is determined according to the sampling points constituting each of the planned rough trajectories and the position information of each of the subsampling points and each of the obstacles.

[0120] Specifically, for each planned rough trajectory, secondary sampling can be performed between each sampling point constituting the planned rough trajectory to obtain secondary sampling points constituting the planned rough trajectory. The sampling rule can also be equal-interval sampling or equal-point number sampling.

[0121] Further, determining the detour label of each secondary sampling point according to the position information of the sampling points and each secondary sampling point constituting each planned rough trajectory and each obstacle includes:

[0122] When the obstacle is a static obstacle, a detour label of the secondary sampling point is determined according to a positional relationship between a vehicle rectangular frame when the vehicle is projected to the sampling point or the secondary sampling point and an obstacle rectangular frame of the obstacle within a preset range of the sampling point or the secondary sampling point; when the obstacle is a dynamic obstacle, a vehicle rectangular frame and a projection time of the vehicle at the sampling point or the secondary sampling point are determined by projecting the sampling point or the secondary sampling point to a predicted trajectory of the vehicle, an obstacle rectangular frame of the obstacle at the projection time is determined in the predicted trajectory of the obstacle, and a detour label of the sampling point or the secondary sampling point is determined according to a positional relationship between the vehicle rectangular frame and the obstacle rectangular frame of the obstacle corresponding to the same projection time.

[0123] When the obstacle is a static obstacle, determine the positional relationship between the vehicle rectangular box when the vehicle is projected to the sampling point or the secondary sampling point and the obstacle rectangular box of the obstacle within the preset range of the sampling point or the secondary sampling point. When the positional relationship is overlapping, determine the detour label of the point as static crossing. When the positional relationship is that the vehicle rectangular box is located on the left side of the obstacle rectangular box and the detour label of the predecessor point of the point is not unknown, determine the detour label of the point as static crossing. When the positional relationship is that the vehicle rectangular box is located on the left side of the obstacle rectangular box and the detour label of the predecessor point of the point is unknown, determine the detour label of the point as left detour. When the positional relationship is that the vehicle rectangular box is located on the right side of the obstacle rectangular box and the detour label of the predecessor point of the point is not unknown, determine the detour label of the point as static crossing. When the positional relationship is that the vehicle rectangular box is located on the right side of the obstacle rectangular box and the detour label of the predecessor point of the point is unknown, determine the detour label of the point as right detour.

[0124] When the obstacle is a dynamic obstacle, before encountering any obstacle, the detour label of the sampling point or the secondary sampling point is determined to be unknown. If there is no obstacle within the preset range of the sampling point or the secondary sampling point, the detour label of the point is determined according to the detour label of the predecessor point of the point. If it is determined that there is an obstacle within the preset range of the sampling point or the secondary sampling point, the position relationship between the vehicle rectangle and the obstacle rectangle corresponding to the same projection time is determined. If the position relationship is overlapped, the detour label of the point is determined to be dynamic crossing. The position relationship is that the vehicle rectangle is located on the left side of the obstacle rectangle and the predecessor of the point is When the detour label of a point is not unknown, the detour label of the point is determined to be dynamic crossing. When the positional relationship is that the vehicle rectangular box is located on the left side of the obstacle rectangular box and the detour label of the predecessor point of the point is . When the detour label is unknown, the detour label of the point is determined to be left detour. When the positional relationship is that the vehicle rectangular box is located on the right side of the obstacle rectangular box and the detour label of the predecessor point of the point is . When the detour label is not unknown, the detour label of the point is determined to be dynamic crossing. When the positional relationship is that the vehicle rectangular box is located on the right side of the obstacle rectangular box and the detour label of the predecessor point of the point is . When the detour label is unknown, the detour label of the point is determined to be right detour.

[0125] In an embodiment of the present invention, detour labels of sampling points and secondary sampling points are determined according to the positional relationship between the vehicle rectangular frames at the sampling points and secondary sampling points constituting each planned rough trajectory and the obstacle rectangular frames within a preset range of the sampling points and secondary sampling points.

[0126] Step 250: Divide the passage area into a plurality of sub-areas according to the detour labels of the sampling points and the secondary sampling points.

[0127] In one implementation, step 250 may specifically include:

[0128] The passage area is divided into a plurality of sub-areas according to the detour labels of the sampling points and the secondary sampling points belonging to the same column.

[0129] Figure 4a and 4b A schematic diagram of dividing a traffic area in a method for determining a detour provided in an embodiment of the present invention, such as Figure 4a and 4b As shown, the detour labels of the sampling points and the secondary sampling points belonging to the same column are determined. If the detour labels of the sampling points and the secondary sampling points belonging to adjacent columns are consistent, the two columns are divided into one sub-area. Otherwise, the two columns are divided into different sub-areas, so that the pass area is divided into multiple sub-areas.

[0130] In the embodiment of the present invention, the passage area is divided into a plurality of sub-areas according to the detour labels of each sampling point and each secondary sampling point, thereby realizing the division of the passage area.

[0131] Step 260: Determine the target rough trajectory of each sub-area.

[0132] In one implementation, step 260 may specifically include:

[0133] The dynamic programming loss value of each of the planned rough trajectories in each of the sub-regions is determined, and the planned rough trajectory with the smallest dynamic programming loss value in each of the sub-regions is determined as the target rough trajectory in each of the sub-regions.

[0134] Before determining the target rough trajectory of each sub-area, in order to improve efficiency, the planned rough trajectory can be pruned. Specifically, if there is a collision at any point constituting the planned rough trajectory, the point will be pruned, and all the planned rough trajectories including the point do not need to be calculated; if the detour label of any point constituting the planned rough trajectory is a static crossing, the point will be pruned, and all the planned rough trajectories including the point do not need to be calculated; if the trajectory curvature of any two adjacent points constituting the planned rough trajectory is greater than the preset curvature, the planned rough trajectory will be pruned.

[0135] Specifically, the dynamic programming loss value of each planned rough trajectory in each sub-area can be determined according to the position loss, speed loss, obstacle loss and time loss. For each sub-area, the dynamic programming loss values ​​of each planned rough trajectory in the sub-area are sorted, and the planned rough trajectory corresponding to the minimum dynamic programming loss value is determined as the target rough trajectory of the sub-area.

[0136] In the embodiment of the present invention, the target rough trajectory in each sub-area is determined according to the dynamic programming loss of each planned rough trajectory in each sub-area.

[0137] Step 270: Determine a target planning rough trajectory according to the loss value of each target rough trajectory.

[0138] The loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and the historical trajectory.

[0139] In one implementation, step 270 may specifically include:

[0140] The historical trajectory deviation loss value of each target rough trajectory is determined according to the position information of each sampling point constituting each target rough trajectory and the projection position of each sampling point constituting each target rough trajectory on the historical trajectory; the obstacle loss value of each target rough trajectory is determined according to the position information of each sampling point constituting each planned rough trajectory and each obstacle; the loss value of each target rough trajectory is determined according to the historical trajectory deviation loss value and the obstacle loss value of each target rough trajectory; and the target rough trajectory with the smallest loss value is determined as the target planned rough trajectory.

[0141] Specifically, the historical trajectory deviation loss function is characterized in that the greater the distance from the historical trajectory in the l direction, the greater the loss value. The historical trajectory deviation loss function can be composed of a direct proportional function, an exponential function or a quadratic function, but is not limited to these function forms.

[0142] For example, the historical trajectory deviation loss value of the target rough trajectory may be determined based on Formula 3.

[0143]

[0144] Among them, cost his_i represents the trajectory deviation loss function of the i-th sampling point constituting the target rough trajectory, cost his_i =k his *(l curr_i -l his_i )*(l curr_i -l his_i ), l curr_i represents the l coordinate of the i-th point of the target rough trajectory after unifying the target rough trajectory and the historical trajectory into the sl coordinate system, l his_i represents the l coordinate of the projection point of the i-th point of the target rough trajectory on the historical trajectory after unifying the target rough trajectory and the historical trajectory into the sl coordinate system, k his Represents the proportionality factor.

[0145] The obstacle loss value of each sampling point has been determined in the aforementioned step 230. After the sampling points constituting each planned rough trajectory are determined, the obstacle loss value of each target rough trajectory can be determined based on the obstacle loss value of the sampling points constituting each planned rough trajectory. When the obstacle loss value of the sampling points constituting each planned rough trajectory is determined based on Formula 2, delta_l j It represents the distance from the ith sampling point constituting each planned rough trajectory to the jth obstacle in the l direction, n represents the number of sampling points constituting each planned rough trajectory, and m represents the number of obstacles within the preset range of each planned rough trajectory.

[0146] Furthermore, the loss value of each target rough trajectory can be determined by summing the historical trajectory deviation loss value and obstacle loss value of each target rough trajectory, that is, COST2=cost2+cost3 can be determined, where COST2 represents the loss function of the target rough trajectory. After determining the loss value of each target rough trajectory, the loss values ​​of each target rough trajectory are compared, and the target rough trajectory with the smallest loss value is determined as the target planning rough trajectory.

[0147] In the embodiment of the present invention, the target planning rough trajectory is determined according to the loss value of each target rough trajectory.

[0148] Step 280: Determine a way for the vehicle to bypass the target obstacle according to a positional relationship between the target obstacle and the target planned coarse trajectory.

[0149] In one implementation, step 280 may specifically include:

[0150] A target point corresponding to the target obstacle is determined in the target planning rough trajectory; and a circumvention method of the vehicle around the target obstacle is determined according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle.

[0151] Specifically, the corresponding target point of the target obstacle in the target planning rough trajectory may be determined, that is, the trajectory point in the target rough trajectory that is closest to the target obstacle may be determined as the corresponding target point of the target obstacle in the target planning rough trajectory.

[0152] Further, determining a circumvention method of the vehicle for the target obstacle according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle includes:

[0153] When the target point corresponding to the target obstacle is located on the left side of the target obstacle, it is determined that the vehicle's bypassing method for the target obstacle is to bypass to the left; when the target point corresponding to the target obstacle is located on the right side of the target obstacle, it is determined that the vehicle's bypassing method for the target obstacle is to bypass to the right.

[0154] In an embodiment of the present invention, a detour method for a vehicle around a target obstacle is determined based on a positional relationship between the target obstacle and a target planned coarse trajectory, and accurate detour suggestions are provided for the vehicle when it is traveling near the target obstacle, thereby reducing the occurrence of repeated detours around obstacles and improving the accuracy and efficiency of path planning.

[0155] The detour method determination provided by the embodiment of the present invention includes: generating a reference line according to the current position of the vehicle and the global planning path, determining the passage area according to the current planning starting point of the vehicle, the reference line and environmental information; determining sampling points in the passage area of ​​the vehicle; dynamically planning the vehicle according to the obstacles in the passage area and the sampling points to obtain multiple planned rough trajectories; determining the detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles; dividing the passage area into multiple sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points; determining the target rough trajectory of each of the sub-areas; determining the target planned rough trajectory according to the loss value of each of the target rough trajectories; and determining the detour method of the vehicle for the target obstacle according to the positional relationship between the target obstacle and the target planned rough trajectory. The above technical scheme can first generate a reference line according to the current position of the vehicle and the global planned path, determine the pass area according to the current planned starting point of the vehicle, the reference line and the environmental information, and accurately determine the passable range of the vehicle, so as to facilitate the path planning of the vehicle. Secondly, the sampling points in the pass area can be determined by sampling the pass area of ​​the vehicle, and multiple planned rough trajectories can be determined by dynamic planning of the vehicle according to the sampling points and obstacles in the pass area, so as to determine the initial path planning of the vehicle. After determining the sampling points and secondary sampling points constituting each planned rough trajectory, the vehicle rectangular frame of the sampling points and secondary sampling points constituting each planned rough trajectory and the obstacles within the preset range of the sampling points and secondary sampling points can be determined. The positional relationship of the rectangular frame of the object determines the detour labels of the sampling points and the secondary sampling points, and the passage area is divided into multiple sub-areas according to the detour labels of each sampling point and each secondary sampling point, so as to realize the division of the passage area, and then the target coarse trajectory in each sub-area can be determined according to the dynamic planning loss of each planned coarse trajectory in each sub-area, and the target planned coarse trajectory is determined according to the loss value of each target coarse trajectory, so as to realize the determination of the target planned coarse trajectory, and then the detour method of the vehicle for the target obstacle can be determined according to the positional relationship between the target obstacle and the target planned coarse trajectory, so as to provide accurate detour suggestions for the path planning near the target obstacle, reduce the occurrence of repeated detours around obstacles, and improve the accuracy and efficiency of path planning.

[0156] Figure 5 A schematic diagram of a detour determining device provided in an embodiment of the present invention is provided. The device can be applied to situations where it is necessary to determine a detour for a vehicle around an obstacle. The device can be implemented by software and / or hardware and is generally integrated in an electronic device, such as a computer device.

[0157] like Figure 5 As shown, the device comprises:

[0158] A planning module 510 is used to determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories;

[0159] A division module 520, configured to determine detour labels of the sampling points and the secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and to divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and the secondary sampling points;

[0160] A determination module 530 is configured to determine a target planning rough trajectory according to a loss value of each target rough trajectory after determining the target rough trajectory of each sub-area, wherein the loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and the historical trajectory;

[0161] The execution module 540 is used to determine a circumvention method of the vehicle around the target obstacle according to the positional relationship between the target obstacle and the target planned coarse trajectory.

[0162] The detour determining device provided in the embodiment determines sampling points in a vehicle's passage area, dynamically plans the vehicle according to obstacles in the passage area and the sampling points, and obtains a plurality of planned rough trajectories; determines detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and divides the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points; after determining a target rough trajectory for each of the sub-areas, determines a target planned rough trajectory according to a loss value of each of the target rough trajectories, wherein the loss value of the target rough trajectory is determined by the obstacles, the sampling points and secondary sampling points constituting the target rough trajectory, and a historical trajectory; and determines a detour method for the vehicle with respect to the target obstacle according to a positional relationship between the target obstacle and the target planned rough trajectory. The above technical solution can first determine the sampling points in the passage area by sampling the passage area of ​​the vehicle, and dynamically plan the vehicle according to the sampling points and obstacles in the passage area to determine multiple planned rough trajectories, so as to determine the initial path planning of the vehicle. After determining the sampling points and secondary sampling points constituting each planned rough trajectory, the detour labels of the sampling points and secondary sampling points are determined according to the positional relationship between the vehicle rectangular frame of the sampling points and secondary sampling points constituting each planned rough trajectory and the obstacle rectangular frame within the preset range of the sampling points and secondary sampling points, and the passage area is divided into multiple sub-areas according to the detour labels of each sampling point and each secondary sampling point, so as to realize the division of the passage area. Secondly, the target rough trajectory in each sub-area can be determined according to the dynamic planning loss of each planned rough trajectory in each sub-area, and the target planned rough trajectory can be determined according to the loss value of each target rough trajectory, so as to realize the determination of the target planned rough trajectory. Then, the detour method of the vehicle for the target obstacle can be determined according to the positional relationship between the target obstacle and the target planned rough trajectory, so as to provide accurate detour suggestions for the path planning near the target obstacle, reduce the occurrence of repeated detours for obstacles, and improve the accuracy and efficiency of path planning.

[0163] Based on the above embodiment, the device further includes:

[0164] A generation module is used to generate a reference line according to the current position of the vehicle and the global planning path before determining the sampling point in the vehicle's passage area, and determine the passage area according to the current planning starting point of the vehicle, the reference line and environmental information.

[0165] In one embodiment, a reference line is generated based on the current position of the vehicle and the global planning path, and the passage area is determined based on the current planning starting point of the vehicle, the reference line and environmental information, including: starting from the current position, extending forward a preset distance along the global planning path to generate the reference line; starting from the current planning starting point, determining multiple preview points on the reference line based on a preset step size, determining the two side boundaries corresponding to each preview point according to the lane line type on both sides of each preview point determined by the environmental information, and determining the passage area according to the two side boundaries corresponding to each preview point.

[0166] Based on the above embodiment, the planning module 510 is specifically used for:

[0167] Sampling points are determined in a vehicle passage area; a trajectory smoothness loss value of each sampling point is determined according to the position information of each sampling point, an obstacle loss value of each sampling point is determined according to the position information of each sampling point and each obstacle, and a cumulative loss value of each sampling point is determined according to the trajectory smoothness loss value and the obstacle loss value of each sampling point; and a plurality of planned rough trajectories are constructed according to the sampling points with the smallest cumulative loss value in each column of the sampling points.

[0168] Based on the above embodiment, the division module 520 is specifically used for:

[0169] Sub-sampling is performed on each of the planned rough trajectories to obtain the sub-sampling points constituting each of the planned rough trajectories; detour labels of each of the sub-sampling points are determined according to the position information of the sampling points and the sub-sampling points constituting each of the planned rough trajectories and each of the obstacles; and the passage area is divided into a plurality of sub-areas according to the detour labels of each of the sampling points and the sub-sampling points belonging to the same column.

[0170] In one embodiment, the detour label of each secondary sampling point is determined according to the position information of the sampling points and the secondary sampling points constituting each planned rough trajectory and each obstacle, including: when the obstacle is a static obstacle, the detour label of the secondary sampling point is determined according to the positional relationship between the vehicle rectangular frame when the vehicle is projected to the sampling point or the secondary sampling point and the obstacle rectangular frame of the obstacle within a preset range of the sampling point or the secondary sampling point; when the obstacle is a dynamic obstacle, the vehicle rectangular frame of the vehicle at the sampling point or the secondary sampling point and the projection time are determined by projecting the sampling point or the secondary sampling point to the predicted trajectory of the vehicle, the obstacle rectangular frame of the obstacle at the projection time is determined in the predicted trajectory of the obstacle, and the detour label of the sampling point or the secondary sampling point is determined according to the positional relationship between the vehicle rectangular frame and the obstacle rectangular frame of the obstacle corresponding to the same projection time.

[0171] Based on the above embodiment, the determination module 530 is specifically used for:

[0172] Determine the dynamic programming loss value of each of the planned rough trajectories in each of the sub-areas, and determine the planned rough trajectory with the smallest dynamic programming loss value in each of the sub-areas as the target rough trajectory of each of the sub-areas; determine the historical trajectory deviation loss value of each of the target rough trajectories according to the position information of each of the sampling points constituting each of the target rough trajectories and the projection position of each of the sampling points constituting each of the target rough trajectories on the historical trajectory, determine the obstacle loss value of each of the target rough trajectories according to the position information of each of the sampling points constituting each of the planned rough trajectories and each of the obstacles, and determine the loss value of each of the target rough trajectories according to the historical trajectory deviation loss value and the obstacle loss value of each of the target rough trajectories; determine the target rough trajectory with the smallest loss value as the target planned rough trajectory.

[0173] Based on the above embodiment, the planning module 510 is further used for:

[0174] When determining the obstacle loss value of each sampling point according to the position information of each sampling point and each obstacle, if it is determined that the obstacle has an increasing effect on the obstacle loss value of the sampling point, the obstacle is determined to be the target obstacle.

[0175] Based on the above embodiment, the execution module 540 is specifically used to:

[0176] A target point corresponding to the target obstacle is determined in the target planning rough trajectory; and a circumvention method of the vehicle around the target obstacle is determined according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle.

[0177] In one embodiment, a bypassing method of the vehicle for the target obstacle is determined based on a positional relationship between the target obstacle and the target point corresponding to the target obstacle, including: when the target point corresponding to the target obstacle is located on the left side of the target obstacle, determining that the bypassing method of the vehicle for the target obstacle is to bypass to the left; when the target point corresponding to the target obstacle is located on the right side of the target obstacle, determining that the bypassing method of the vehicle for the target obstacle is to bypass to the right.

[0178] The detour way determination device provided in the embodiment of the present invention can execute the detour way determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the detour way determination method.

[0179] It is worth noting that in the embodiment of the above-mentioned detour method determination device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0180] Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 6 A block diagram of an exemplary electronic device 6 suitable for implementing embodiments of the present invention is shown. Figure 6 The electronic device 6 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0181] like Figure 6 As shown, the electronic device 6 is in the form of a general purpose computing electronic device. The components of the electronic device 6 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0182] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0183] The electronic device 6 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 6, including volatile and non-volatile media, removable and non-removable media.

[0184] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 6 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0185] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0186] The electronic device 6 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 6, and / or any device that enables the electronic device 6 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 6 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 6 As shown, the network adapter 20 communicates with other modules of the electronic device 6 via the bus 18. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 6, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0187] The processing unit 16 executes various functional applications and page displays by running the program stored in the system memory 28, for example, implementing the detour mode determination method provided in the embodiment of the present invention, the method comprising:

[0188] Determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories;

[0189] Determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points;

[0190] After determining the target rough trajectory of each sub-area, determining the target planning rough trajectory according to the loss value of each target rough trajectory, wherein the loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and the historical trajectory;

[0191] The method for the vehicle to bypass the target obstacle is determined according to the positional relationship between the target obstacle and the target planned rough trajectory.

[0192] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the detour determination method provided by any embodiment of the present invention.

[0193] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, for example, a method for determining a detour provided by an embodiment of the present invention is implemented. The method includes:

[0194] Determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories;

[0195] Determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points;

[0196] After determining the target rough trajectory of each sub-area, determining the target planning rough trajectory according to the loss value of each target rough trajectory, wherein the loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and the historical trajectory;

[0197] The method for the vehicle to bypass the target obstacle is determined according to the positional relationship between the target obstacle and the target planned rough trajectory.

[0198] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0199] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0200] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0201] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0202] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0203] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0204] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for determining a detour, characterized in that: include: Determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories; Determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points; After determining the target rough trajectory of each sub-area, determining the target planning rough trajectory according to the loss value of each target rough trajectory, wherein the loss value of the target rough trajectory is determined by the sampling points constituting the target rough trajectory, the obstacles and the historical trajectory; The method for the vehicle to bypass the target obstacle is determined according to the positional relationship between the target obstacle and the target planned rough trajectory.

2. The method for determining a detour according to claim 1, characterized in that: Before determining the sampling points within the vehicle's traffic area, it also includes: A reference line is generated according to the current position of the vehicle and the global planned path, and the passage area is determined according to the current planned starting point of the vehicle, the reference line and environmental information.

3. The method for determining a detour according to claim 2, characterized in that: Generating a reference line according to the current position of the vehicle and the global planning path, and determining the passage area according to the current planning starting point of the vehicle, the reference line and environmental information, including: Taking the current position as the starting point, extending forward a preset distance along the global planning path to generate the reference line; Taking the current planning starting point as the starting point, multiple preview points are determined on the reference line based on a preset step size, and the two side boundaries corresponding to each preview point are determined according to the lane line type on both sides of each preview point determined according to the environmental information, and the passage area is determined according to the two side boundaries corresponding to each preview point.

4. The method for determining a detour according to claim 1, characterized in that: The vehicle is dynamically planned according to the obstacles in the passage area and the sampling points to obtain multiple planned rough trajectories, including: Determine a track smoothness loss value of each sampling point according to the position information of each sampling point, determine an obstacle loss value of each sampling point according to the position information of each sampling point and each obstacle, and determine a cumulative loss value of each sampling point according to the track smoothness loss value and the obstacle loss value of each sampling point; A plurality of planned rough trajectories are constructed according to the sampling points with the smallest cumulative loss value in each column of the sampling points.

5. The method for determining a detour according to claim 1, characterized in that: Determining detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles includes: Performing secondary sampling on each of the planned rough trajectories to obtain the secondary sampling points constituting each of the planned rough trajectories; Determine a detour label for each of the secondary sampling points according to the position information of the sampling points and the secondary sampling points constituting each of the planned rough trajectories and the obstacles.

6. The method for determining a detour according to claim 5, characterized in that: Determining the detour labels of the secondary sampling points according to the sampling points and the position information of the secondary sampling points constituting the planned rough trajectories and the obstacles comprises: When the obstacle is a static obstacle, determining the detour label of the secondary sampling point according to the positional relationship between the vehicle rectangular frame when the vehicle is projected to the sampling point or the secondary sampling point and the obstacle rectangular frame of the obstacle within a preset range of the sampling point or the secondary sampling point; When the obstacle is a dynamic obstacle, a vehicle rectangular frame of the vehicle at the sampling point or the secondary sampling point and a projection time are determined by projecting the sampling point or the secondary sampling point onto a predicted trajectory of the vehicle, an obstacle rectangular frame of the obstacle at the projection time is determined in the predicted trajectory of the obstacle, and a detour label of the sampling point or the secondary sampling point is determined according to a positional relationship between the vehicle rectangular frame and the obstacle rectangular frame of the obstacle corresponding to the same projection time.

7. The method for determining a detour according to claim 5, characterized in that: Dividing the passage area into a plurality of sub-areas according to the detour labels of each sampling point and each secondary sampling point includes: The passage area is divided into a plurality of sub-areas according to the detour labels of the sampling points and the secondary sampling points belonging to the same column.

8. The method for determining a detour according to claim 1, characterized in that: Determining a rough target trajectory of each sub-area includes: The dynamic programming loss value of each of the planned rough trajectories in each of the sub-regions is determined, and the planned rough trajectory with the smallest dynamic programming loss value in each of the sub-regions is determined as the target rough trajectory in each of the sub-regions.

9. The method for determining a detour according to claim 1, characterized in that: Determining a target planning rough trajectory according to the loss value of each target rough trajectory includes: Determine the historical trajectory deviation loss value of each target rough trajectory according to the position information of each sampling point constituting each target rough trajectory and the projection position of each sampling point constituting each target rough trajectory on the historical trajectory, determine the obstacle loss value of each target rough trajectory according to the position information of each sampling point constituting each planned rough trajectory and each obstacle, and determine the loss value of each target rough trajectory according to the historical trajectory deviation loss value and the obstacle loss value of each target rough trajectory; The target rough trajectory with the smallest loss value is determined as the target planning rough trajectory.

10. The method for determining a detour according to claim 4, characterized in that: When the obstacle loss value of each sampling point is determined according to the position information of each sampling point and each obstacle, the method further includes: If it is determined that the obstacle has an increasing effect on the obstacle loss value of the sampling point, the obstacle is determined to be the target obstacle.

11. The method for determining a detour according to claim 10, characterized in that: Determining a way for the vehicle to bypass the target obstacle according to a positional relationship between the target obstacle and the target planned rough trajectory includes: Determining a target point corresponding to the target obstacle in the target planning rough trajectory; A way for the vehicle to bypass the target obstacle is determined according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle.

12. The method for determining a detour according to claim 11, characterized in that: Determining a circumvention method of the vehicle around the target obstacle according to a positional relationship between the target obstacle and the target point corresponding to the target obstacle includes: When the target point corresponding to the target obstacle is located on the left side of the target obstacle, determining that the detour method of the vehicle for the target obstacle is to detour to the left; When the target point corresponding to the target obstacle is located on the right side of the target obstacle, it is determined that the detour method of the vehicle around the target obstacle is to detour to the right.

13. A detour method determination device, characterized in that: include: A planning module, used to determine sampling points in a vehicle's passage area, and dynamically plan the vehicle according to obstacles in the passage area and the sampling points to obtain a plurality of planned rough trajectories; a division module, configured to determine detour labels of the sampling points and secondary sampling points constituting each of the planned rough trajectories according to the obstacles, and to divide the passage area into a plurality of sub-areas according to the detour labels of each of the sampling points and each of the secondary sampling points; A determination module, configured to determine a target planning rough trajectory according to a loss value of each target rough trajectory after determining the target rough trajectory of each sub-area, wherein the loss value of the target rough trajectory is determined by the obstacle, the sampling points and the secondary sampling points constituting the target rough trajectory, and a historical trajectory; The execution module is used to determine the circumvention method of the vehicle around the target obstacle according to the positional relationship between the target obstacle and the target planned rough trajectory.

14. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the detour determining method as described in any one of claims 1-12.

15. A storage medium containing computer executable instructions, characterized in that: When the computer executable instructions are executed by a computer processor, they are used to perform the detour mode determination method as described in any one of claims 1-12.

Images