Path processing method and electronic device

Abstract

The application provides a path processing method and an electronic device. The method comprises the following steps: the electronic device samples a road where any first path is located by acquiring obstacle information and a pose of a vehicle at a starting position point and a terminal position point; after the pose of a sampling position point is acquired each time, a parent node corresponding to the sampling position point is determined from a RRT tree according to the pose of the sampling position point and node information of each node in the RRT tree; a target child node corresponding to the parent node is added in the RRT tree according to the node information of the parent node and the obstacle information; and when the node information of the target child node meets a preset condition, a target path is determined according to the target child node and a root node, so that the quality of the target path is effectively improved. The technical scheme can meet the special obstacle avoidance and straightening requirements of a tractor semi-trailer, and the smoothness and quality of the target path are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of navigation technology, and in particular to a path processing method and an electronic device. BACKGROUND

[0002] With the progress of vehicle technology, automatic driving technology emerges as the times require, which greatly promotes the development of the transportation industry. Among them, since the tractor semi-trailer can be applied to more scenes, such as airports, ports and freight stations, etc., its automation degree has attracted widespread attention from researchers. Generally speaking, the tractor semi-trailer has a smaller turning radius than the single rigid body vehicle, and the tractor semi-trailer system has highly nonlinear and nonholonomic complex dynamics characteristics, which brings great challenges to the development of motion planning and control algorithm of the tractor semi-trailer.

[0003] At present, the motion planning of the tractor semi-trailer is mainly realized by the Rapidly exploring Random Tree (RRT) algorithm in the random sampling method. RRT is suitable for solving the motion planning problem with differential equation constraint limit, and its core idea is to incrementally sample and construct a random path from the starting configuration until a branch of the path system successfully connects the terminal configuration.

[0004] However, the existing random sampling method cannot accurately process complex constraint conditions, and the quality of the obtained path is poor, which cannot meet the special obstacle avoidance and straightening requirements of the tractor semi-trailer. SUMMARY

[0005] The present application provides a path processing method and an electronic device to solve the problem that the existing random sampling method cannot accurately process complex constraint conditions, and the quality of the obtained path is poor, which cannot meet the special obstacle avoidance and straightening requirements of the tractor semi-trailer.

[0006] In a first aspect, an embodiment of the present application provides a path processing method, comprising:

[0007] Obtaining obstacle information and the pose of the vehicle at a starting position point and a terminal position point, the obstacle information being used to represent the obstacles on both sides of a plurality of first paths from the starting position point to the terminal position point;

[0008] Sampling from the road where any first path is located, and after obtaining the pose of a sampling position point each time, determining the parent node corresponding to the sampling position point from an RRT tree according to the pose of the sampling position point and the node information of each node in the RRT tree, the RRT tree comprising a root node and a plurality of nodes under the root node for representing positions, the node information of each node being used to represent the running state of the vehicle at the corresponding position, and the node information of the root node being related to the pose of the starting position point.

[0009] adding a target child node corresponding to the parent node in the RRT tree according to the node information of the parent node and the obstacle information;

[0010] if the node information of the target child node meets a preset condition, determining a target path from the start position point to the end position point according to the target child node and the root node, the preset condition being related to the pose of the end position point.

[0011] In a possible design of the first aspect, the sampling is performed from the road in which any first path is located, and after obtaining the pose of the sampling position point each time, a parent node corresponding to the sampling position point is determined from the RRT tree according to the pose of the sampling position point and the node information of each node in the RRT tree, including:

[0012] sampling is performed from the road in which any first path is located, and the pose of the sampling position point is obtained;

[0013] after obtaining the pose of the sampling position point each time, for each node in the RRT tree, a first possibility degree of the vehicle traveling from a position point corresponding to the node to the sampling position point is calculated according to the pose of the sampling position point and the node information of all nodes in a second path from the node to the root node.

[0014] the node with the largest first possibility degree is determined as the parent node corresponding to the sampling position point.

[0015] Optionally, the vehicle is a tractor semi-trailer, and the node information includes coordinates, a tractor attitude angle, a trailer attitude angle, a steering angle of a front wheel of the tractor, and a steering angle change rate.

[0016] Correspondingly, the method further includes:

[0017] after obtaining the pose of the sampling position point each time, for each node in the RRT tree, a third path length and a third path smoothness degree between the sampling position point and a position point corresponding to the node are determined according to the pose of the sampling position point and the coordinates, the tractor attitude angle, and the trailer attitude angle of the node.

[0018] For each node in the RRT tree, according to the steering angle and the steering angle rate of the front wheel of the tractor of all nodes in the second path, the steering angle absolute value accumulation sum and the steering angle rate absolute value accumulation sum of the front wheel of the tractor of all nodes in the second path are calculated;

[0019] For each node in the RRT tree, the number of used steering angle rates in the discrete steering angle rate set of the node is determined, the used discrete steering angle rate has been used to determine whether the node can add the next level child node corresponding to the used discrete steering angle rate;

[0020] For each node in the RRT tree, according to the third path length, the third path non-smooth degree, the number of used steering angle rates, the steering angle absolute value accumulation sum and the steering angle rate absolute value accumulation sum of the front wheel of the tractor, the first possibility degree is determined.

[0021] Optionally, the adding the target child node corresponding to the parent node in the RRT tree according to the node information of the parent node and the obstacle information comprises:

[0022] According to the node information of the parent node, the tractor dynamics correction coefficient and the trailer dynamics coefficient, the addable child node of the parent node in the RRT tree is determined;

[0023] For each addable child node, according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information, the second possibility degree of the vehicle from the position point corresponding to the parent node to the position point corresponding to the addable child node is calculated;

[0024] The addable child node with the largest second possibility degree is determined as the target child node corresponding to the parent node;

[0025] The target child node corresponding to the parent node is added in the RRT tree.

[0026] Optionally, the calculating the second possibility degree of the vehicle from the position point corresponding to the parent node to the position point corresponding to the addable child node for each addable child node according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information comprises:

[0027] For each addable child node, according to the coordinates of the addable child node, the front wheel steering angle and the steering angle rate of the tractor, and the coordinates of the parent node, the front wheel steering angle and the steering angle rate of the tractor, the fourth path length and the fourth path non-smooth degree between the position point corresponding to the addable child node and the position point corresponding to the parent node are determined;

[0028] For each addable child node, according to the allowed maximum turning angle of the front wheel of the towing vehicle and the obstacle information, determine a collision condition of a position point corresponding to the addable child node and a road boundary;

[0029] For each addable child node, determine a turning angle change direction between the addable child node and the parent node, and a consistency with a turning angle change direction of the parent node and a parent node of a previous level of the parent node;

[0030] For each addable child node, according to the fourth path length, the fourth path non-smoothness, the collision condition, and the consistency, calculate the second possibility degree.

[0031] Optionally, if the node information of the target child node meets a preset condition, determine a target path according to the target child node and the root node, the target path being a path from the starting position point to the terminal position point, comprising:

[0032] According to the node information of the target child node and the pose of the terminal position point, calculate an error of the target child node relative to the terminal position point;

[0033] If the error is less than a preset error, determine a fifth path from the target child node to the root node as the target path;

[0034] According to the error of each fifth path and an absolute value sum of a turning angle change rate of the front wheel of the towing vehicle of all nodes in the fifth path, determine the target path from all fifth paths;

[0035] The preset condition is that the error of the target child node relative to the terminal position point is less than a preset error.

[0036] Optionally, the method further comprises:

[0037] Generate a segmented polynomial of the target path through cubic spline interpolation;

[0038] Perform quadratic programming on the segmented polynomial to obtain an optimized node of the target path;

[0039] According to the allowed maximum turning angle of the front wheel of the towing vehicle and the obstacle information, determine whether a collision occurs between a position point corresponding to each optimized node and a road boundary;

[0040] If not, update the target path according to the optimized node to generate an updated target path;

[0041] If yes, a node needing re-optimization is determined from all the optimized nodes through a coordinate of a collision position point where a path composed of the optimized nodes collides with the road boundary;

[0042] The curvature weight and the curvature change rate weight of the node needing re-optimization are reduced.

[0043] Optionally, the pose of the sampling position point is obtained by sampling from a road where any first path is located, comprising:

[0044] A probability value of determining the termination position point as the sampling position point is obtained by random normal sampling from a preset probability range;

[0045] If the probability value is greater than a preset probability value, the termination position point is determined as the sampling position point, and the preset probability value is in the preset probability range;

[0046] Otherwise, an initial sampling position point is obtained by sampling from a road center line of a road where any first path is located;

[0047] A sampling range is determined according to the initial sampling position point and a preset distance;

[0048] The sampling position point is obtained by sampling from the sampling range, and a tractor pose angle and a trailer pose angle of the sampling position point are the same as those of the initial sampling position point.

[0049] Optionally, the error of the target sub-node relative to the termination position point is calculated according to the node information of the target sub-node and the pose of the termination position point, comprising:

[0050] The error of the target sub-node relative to the termination position point is calculated according to the node information of the target sub-node and the pose of the termination position point, wherein a horizontal coordinate difference value between the target sub-node and the termination position point is less than a first preset distance, a vertical coordinate difference value between the target sub-node and the termination position point is less than a second preset distance, a tractor pose angle difference value between the target sub-node and the termination position point is less than a first pose angle difference value, and a trailer pose angle difference value between the target sub-node and the termination position point is less than a second pose angle difference value.

[0051] The error comprises the horizontal coordinate difference value, the vertical coordinate difference value, the tractor pose angle difference value and the trailer pose angle difference value.

[0052] In a second aspect, an embodiment of the present application provides a path processing device, comprising:

[0053] obstacle information and poses of the vehicle at a start position point and an end position point, the obstacle information being used to represent obstacles on both sides of a plurality of first paths from the start position point to the end position point;

[0054] a determining module configured to sample from a road in which any first path is located, and determine a parent node corresponding to a sampling position point from the RRT tree according to the pose of the sampling position point and node information of each node in the RRT tree after obtaining the pose of the sampling position point each time, the RRT tree comprising a root node and a plurality of nodes at different levels under the root node and used to represent positions, and the node information of each node being used to represent a running state of the vehicle at a corresponding position, and the node information of the root node being related to the pose of the start position point;

[0055] an adding module configured to add a target child node corresponding to the parent node in the RRT tree according to the node information of the parent node and the obstacle information;

[0056] The determining module is further configured to determine a target path according to the target child node and the root node if the node information of the target child node meets a preset condition, the target path being a path from the start position point to the end position point, and the preset condition being related to the pose of the end position point.

[0057] In a possible design of the second aspect, the determining module is specifically configured to:

[0058] sample from a road in which any first path is located, and obtain the pose of the sampling position point;

[0059] after obtaining the pose of the sampling position point each time, calculate a first possibility degree of the vehicle traveling from a position point corresponding to each node in the RRT tree to the sampling position point according to the pose of the sampling position point and node information of all nodes in the RRT tree that are in a second path from the node to the root node;

[0060] determine the node with the largest first possibility degree as the parent node corresponding to the sampling position point.

[0061] Optionally, the vehicle is a tractor semi-trailer, and the node information comprises coordinates, a tractor attitude angle, a trailer attitude angle, a steering angle of a front wheel of the tractor, and a steering angle change rate of the front wheel of the tractor.

[0062] Correspondingly, the determining module is specifically configured to:

[0063] After obtaining the pose of the sampling position point each time, for each node in the RRT tree, determine the length of the third path between the sampling position point and the position point corresponding to the node and the degree of third path roughness according to the pose of the sampling position point and the coordinates of the node, the tractor attitude angle, and the trailer attitude angle;

[0064] For each node in the RRT tree, calculating the cumulative sum of the absolute values ​​of the steering angles of the tractor front wheels and the cumulative sum of the absolute values ​​of the steering angle change rates of all nodes in the second path based on the steering angles and steering angle change rates of the tractor front wheels in all nodes in the second path;

[0065] For each node in the RRT tree, determining the number of used steering angle change rates in the discrete steering angle change rate set of the node, the used discrete steering angle change rates being used to determine whether a next-level child node corresponding to the used discrete steering angle change rates can be added to the node;

[0066] For each node in the RRT tree, the first degree of possibility is determined based on the third path length, the third path non-smoothness, the number of used steering angle change rates, the cumulative sum of the absolute values ​​of the steering angles of the tractor front wheels, and the cumulative sum of the absolute values ​​of the steering angle change rates.

[0067] Optionally, the adding module is specifically used to:

[0068] Determining an addable child node of the parent node in the RRT tree according to the node information of the parent node, the tractor dynamics correction coefficient, and the trailer dynamics coefficient;

[0069] For each addable child node, calculating a second likelihood of the vehicle traveling from the position point corresponding to the parent node to the position point corresponding to the addable child node based on the maximum allowable steering angle of the front wheels of the tractor and the obstacle information;

[0070] Determine the addable child node with the second greatest probability as the target child node corresponding to the parent node;

[0071] Add the target child node corresponding to the parent node in the RRT tree.

[0072] Optionally, the adding module is specifically used to:

[0073] For each addable child node, determining a fourth path length and a fourth path roughness between a position point corresponding to the addable child node and a position point corresponding to the parent node based on the coordinates of the addable child node, the front wheel steering angle and the steering angle change rate of the tractor, and the coordinates of the parent node, the front wheel steering angle and the steering angle change rate of the tractor;

[0074] For each addable child node, determine a collision condition of a position point corresponding to the addable child node and a road boundary according to the allowed maximum turning angle of the tractor front wheel and the obstacle information;

[0075] For each addable child node, determine a consistency of a turning angle change direction between the addable child node and the parent node with a turning angle change direction between the parent node and a parent node of a previous level of the parent node;

[0076] For each addable child node, calculate the second degree of possibility according to the fourth path length, the fourth path non-smoothness, the collision condition, and the consistency.

[0077] Optionally, the determining module is specifically configured to:

[0078] According to the node information of the target child node and the pose of the terminal position point, calculate an error of the target child node relative to the terminal position point;

[0079] If the error is less than a preset error, determine a fifth path from the target child node to a root node as the target path;

[0080] According to the error of each fifth path and an absolute value cumulative sum of a turning angle change rate of the tractor front wheel of all nodes in the fifth path, determine the target path from all fifth paths;

[0081] The preset condition is that the error of the target child node relative to the terminal position point is less than a preset error.

[0082] Optionally, the device further includes:

[0083] The generating module is configured to generate a segmented polynomial of the target path through cubic spline interpolation;

[0084] The obtaining module is further configured to perform quadratic programming on the segmented polynomial to obtain an optimized node of the target path.

[0085] The judging module is configured to judge whether a position point corresponding to each optimized node collides with a road boundary according to the allowed maximum turning angle of the tractor front wheel and the obstacle information.

[0086] The generating module is further configured to, if not, update the target path according to the optimized node to generate an updated target path.

[0087] The determining module is further configured to, if yes, determine the node that needs to be optimized again from all the optimized nodes according to a collision position point at which the path composed of the optimized nodes collides with the road boundary.

[0088] The decreasing module is configured to decrease the curvature weight and the curvature change rate weight of the node that needs to be optimized again.

[0089] Optionally, the determining module is specifically configured to:

[0090] randomly perform normal sampling in a preset probability range to obtain a probability value of determining the termination position point as the sampling position point;

[0091] if the probability value is greater than a preset probability value, the termination position point is determined as the sampling position point, and the preset probability value is in the preset probability range;

[0092] otherwise, an initial sampling position point is obtained by sampling on a road center line of a road where any first path is located;

[0093] a sampling range is determined according to the initial sampling position point and a preset distance;

[0094] the sampling position point is obtained by sampling in the sampling range, and a tractor attitude angle and a trailer attitude angle of the sampling position point are the same as those of the initial sampling position point.

[0095] Optionally, the determining module is specifically configured to:

[0096] the target sub-node and the termination position point are calculated according to node information of the target sub-node and a pose of the termination position point, and the target sub-node and the termination position point have a horizontal coordinate difference value less than a first preset distance, a vertical coordinate difference value less than a second preset distance, a tractor attitude angle difference value less than a first attitude angle difference value, and a trailer attitude angle difference value less than a second attitude angle difference value.

[0097] The error includes the horizontal coordinate difference value, the vertical coordinate difference value, the tractor attitude angle difference value, and the trailer attitude angle difference value.

[0098] In a third aspect, an electronic device is provided, which includes a processor, a memory, and computer program instructions stored in the memory and executable on the processor, and the processor is configured to implement the method provided in the first aspect and the possible designs.

[0099] In a fourth aspect, the embodiments of the present application can provide a computer readable storage medium, which stores computer execution instructions. When the computer execution instructions are executed by a processor, the computer execution instructions are used to implement the method provided in the first aspect and the possible designs.

[0100] In a fifth aspect, the embodiments of the present application provide a computer program product, which includes a computer program. When the computer program is executed by a processor, the computer program is used to implement the method provided in the first aspect and the possible designs.

[0101] The path processing method and the electronic device provided by the embodiments of the present application are as follows. In the method, the electronic device samples from a road where any first path is located by obtaining obstacle information and poses of a vehicle at a starting position point and a terminal position point. After the pose of each sampling position point is obtained, a parent node corresponding to the sampling position point is determined from an RRT tree according to the pose of the sampling position point and node information of each node in the RRT tree. A target child node corresponding to the parent node is added in the RRT tree according to the node information of the parent node and the obstacle information. When the node information of the target child node meets a preset condition, a target path is determined according to the target child node and a root node. The quality of the target path is effectively improved. In the technical solution, the poses of the tractor and the semitrailer are iteratively calculated in the search process. The RRT tree is expanded in combination with the positions of the nodes and the running states of the vehicle at the positions. The special obstacle avoidance and straightening requirements of the tractor and the semitrailer are met. The target path determined according to the expanded RRT tree meets the kinematic constraints of the tractor and the semitrailer. The smoothness of the target path is improved. The vehicle has a good tracking effect. The tractor and the semitrailer are prevented from colliding with known static obstacles. BRIEF DESCRIPTION OF DRAWINGS

[0102] The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments consistent with the present application and, together with the description, further serve to explain the principles of the application.

[0103] Figure 1 A flowchart of the path processing method provided by Embodiment One of the embodiments of the present application is shown in FIG. 1.

[0104] Figure 2 A flowchart of the path processing method provided by Embodiment Two of the embodiments of the present application is shown in FIG. 2.

[0105] Figure 3 Four circular arc diagrams provided by the embodiments of the present application are shown in FIG. 3.

[0106] Figure 4 A flowchart of the path processing method provided by Embodiment Three of the embodiments of the present application is shown in FIG. 4.

[0107] Figure 5A flowchart of the path processing method embodiment four provided by the embodiments of the present application is shown in the following figure;

[0108] Figure 6 A flowchart of the path processing method embodiment five provided by the embodiments of the present application is shown in the following figure;

[0109] Figure 7 A path comparison diagram provided by the embodiments of the present application is shown in the following figure;

[0110] Figure 8 A curvature comparison diagram provided by the embodiments of the present application is shown in the following figure;

[0111] Figure 9 A curvature change rate comparison diagram provided by the embodiments of the present application is shown in the following figure;

[0112] Figure 10 A structure diagram of the path processing device provided by the embodiments of the present application is shown in the following figure;

[0113] Figure 11 A structure diagram of the electronic device provided by the embodiments of the present application is shown in the following figure.

[0114] The specific embodiments of the present application have been shown in the above figures, and will be described in more detail hereinafter. These figures and textual descriptions are not intended to limit the scope of the concept of the present application by any means, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0115] In order to make the objects, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions of the embodiments of the present application will be described clearly and completely below in combination with the figures in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative work fall within the scope of protection of the present application.

[0116] Before introducing the embodiments of the present application, the application background of the embodiments of the present application is explained first:

[0117] Automatic driving technology can improve work efficiency and safety, greatly changing the work mode of the transportation industry, among which the automation of tractor-semitrailer widely used in airports, ports and freight stations has attracted the attention of researchers. Tractor-semitrailer has two large-size bodies, namely tractor and semitrailer. The tractor is a kind of vehicle similar to a car, with a traction engine, while the semitrailer is a kind of articulated vehicle used for transporting goods. Generally speaking, the tractor-semitrailer has a smaller turning radius than the single rigid body vehicle, and the tractor-semitrailer system has highly nonlinear and nonholonomic complex dynamics, which brings great challenges to the development of motion planning and control algorithm of tractor-semitrailer.

[0118] Currently, the commonly used motion planning methods include graph search method, random sampling method and optimization-based method. Among them, the random sampling method is suitable for solving motion planning problems in high-dimensional configuration space and has probabilistic completeness: as long as the solution of the motion planning problem exists, the probability of the random sampling method finding it in a sufficiently long time is 100%, so it has been widely used in motion planning work in various industries. Popular random sampling methods include Probailistic Roadmap Method (PRM) and RRT. RRT is suitable for solving motion planning problems with differential equation constraint restrictions, and its core idea is to incrementally sample from the initial configuration to build a random path until a branch of the path system successfully connects the terminal configuration.

[0119] However, although the random sampling method has probabilistic completeness, it cannot accurately handle complex constraint conditions. In particular, the process of generating motion states by random sampling method is blind and cannot find solutions that precisely satisfy the constraint conditions. The inherent random mechanism makes it impossible for the random sampling method to directly handle motion planning tasks with complex constraints, and the rough path obtained by sampling is discontinuous in curvature, which does not meet the requirements of the control link. The path quality obtained by the random sampling method is poor, and the path has corners and is not smooth enough to meet the special obstacle avoidance and straightening needs of tractor-semitrailer.

[0120] Based on the above technical problems, the technical concept of the present application is that in the prior art, the nodes of the RRT tree are mainly updated by determining the node closest to the sampling position point in the RRT tree, taking the node as the parent node, and adding the sampling position point as the child node of the parent node. That is, the prior art only considers the distance between nodes when updating nodes, without considering the fluency between multiple nodes, resulting in the determined target path having problems such as containing corners and not being smooth enough, which cannot meet the special obstacle avoidance and straightening requirements of the tractor-semitrailer. The path processing method proposed in the present application redefines the RRT tree and the process of updating the nodes of the RRT tree, adds node information for representing the running state of the tractor-semitrailer at the corresponding position to the nodes in the RRT tree, and in the process of updating the nodes of the RRT tree, determines the parent node corresponding to the sampling position point from the RRT tree in combination with the pose of the tractor-semitrailer at the sampling position point and the node information of each node in the RRT tree, and determines the target child node from the multiple addable child nodes corresponding to the parent node according to the node information of the parent node and the obstacle information, and adds it to the corresponding position in the RRT tree. In this way, when the node information of the target child node meets the preset condition related to the pose of the termination position point, the path from the target child node to the root node is determined as the target path, which can effectively improve the quality of the determined target path, thereby meeting the special obstacle avoidance and straightening requirements of the tractor-semitrailer.

[0121] In the following, the technical solutions of the present application will be described in detail through specific embodiments.

[0122] It should be noted that the following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0123] Figure 1 The flowchart of the path processing method embodiment one provided by the present application is shown in FIG. 1. As shown in the figure, the path processing method is applied to an electronic device, which can be a server, and can also be a vehicle itself. The path processing method can include the following steps: Figure 1

[0124] S101, obtain obstacle information and the pose of the vehicle at the starting position point and the termination position point.

[0125] In this step, since path planning needs to plan a path that can avoid obstacles according to the starting position point (that is, the departure place), the termination position point (that is, the destination) and the obstacle situation on both sides of the road, so as to control the vehicle to travel on the path. Therefore, it is necessary to obtain the obstacle information and the coordinates of the starting position point and the coordinates of the termination position point.

[0126] ​Further, since the driving direction of the vehicle needs to be consistent with the road direction. Therefore, after obtaining the start position point and the end position point, the vehicle direction also needs to be determined, so as to ensure that the subsequent planned path meets the traffic rules. Wherein, the pose of the position point includes the coordinates of the position point and the driving direction of the vehicle at the position point.

[0127] Wherein, the obstacle information is used to represent the obstacles on both sides of the plurality of first paths from the start position point to the end position point.

[0128] On the one hand, the coordinates of the start position point and the end position point input by the user through the touch display screen of the vehicle can be obtained, the road direction closest to the position point is determined according to the high-definition map, so as to determine the driving direction of the vehicle at the position point, and the pose of the start position point and the end position point is obtained. Taking the electronic device as an example, the vehicle can display a graphical user interface to the user through the touch display screen, and the graphical user interface is used to display the high-definition map. The user can input the start position point and the end position point according to his own needs, and the vehicle obtains the coordinates of the start position point and the end position point input by the user in response to the user's operation. Further, the vehicle determines the driving direction of the vehicle at the position point according to the road direction closest to the position point. That is, the pose of the position point includes the coordinates of the position point and the driving direction of the vehicle at the position point.

[0129] On the other hand, for the obstacle information, all first paths from the start position point to the end position point can be obtained through the high-definition map. For each first path, the obstacle contour within a preset range along the first path is extracted according to the high-definition map, so as to obtain the obstacle information. For example, the combination of roads and intersections to be passed through by each first path can be determined, the obstacle contour of each road and intersection combination is extracted, and the obstacle information is generated.

[0130] Optionally, all first paths from the start position point to the end position point in the high-definition map can be calculated by Dijkstra algorithm. It should be understood that all first paths in the high-definition map can also be calculated by other existing algorithms. The specific algorithm used for calculation can be determined according to actual conditions, and the embodiments of the present application do not make specific limitations.

[0131] Optionally, when the vehicle is a tractor semi-trailer, the pose of the position point includes the coordinates, and the tractor attitude angle and the trailer attitude angle of the vehicle at the position point.

[0132] S102, sampling is performed from the road where any first path is located, and after obtaining the pose of each sampling position point, the parent node corresponding to the sampling position point is determined from the RRT tree according to the pose of the sampling position point and the node information of each node in the RRT tree.

[0133] In this step, after the poses of the start position point and the end position point are acquired, it is necessary to construct and expand the RRT tree according to the poses of the start position point and the end position point, so as to acquire a smooth target path suitable for vehicle driving through the expanded RRT tree. In the process of expanding the RRT tree, it is necessary to sample from the road where any first path is located, and the sampled position point is used to add a new node in the RRT tree. If the target path cannot be acquired through the RRT tree with the added new node, and the sampling times do not reach the preset times, the sampling from the road where any first path is located is continued, and the above expansion process is repeated, otherwise, the sampling is stopped, and the target path is determined through the RRT tree with the added new node or it is prompted that the path planning for the start position point and the end position point cannot be performed. Wherein, the first path of each sampling can be the same or different.

[0134] The expansion of the RRT tree mainly includes two processes: process 1, determining the parent node corresponding to the sampled position point from the RRT tree according to the pose of the sampled position point. Process 2, determining the target child node corresponding to the parent node which can be added to the RRT tree, S102 corresponds to the above process 1.

[0135] Wherein, the RRT tree includes a root node and multiple levels of nodes under the root node for representing positions, and the node information of each node is used to represent the running state of the vehicle at the corresponding position, and the node information of the root node is related to the pose of the start position point.

[0136] In a possible implementation, for each node in the RRT tree, the first possibility degree of the vehicle driving from the position point corresponding to the node to the sampled position point can be calculated according to the pose of the sampled position point and the node information of all nodes in the second path from the node to the root node, so as to determine the node with the largest first possibility degree as the parent node corresponding to the sampled position point.

[0137] It should be understood that the specific implementation and principles of this step can refer to the embodiments shown in Figure 2 and will not be described here.

[0138] S103, adding the target child node corresponding to the parent node in the RRT tree according to the node information of the parent node and the obstacle information.

[0139] In this step, after the parent node corresponding to the sampled position point is determined, the target child node corresponding to the parent node which can be added to the RRT tree can be determined according to the parent node, so as to complete the process of expanding the RRT tree.

[0140] In a possible implementation, when the vehicle is a tractor semi-trailer, the number of the child nodes of the parent node in the RRT tree can be recursively obtained according to the node information of the parent node, the dynamic correction coefficient of the tractor, and the dynamic coefficient of the trailer.

[0141] In S104, if the node information of the target child node meets the preset condition, a target path is determined according to the target child node and the root node, and the target path is a path from the start position point to the end position point.

[0142] In this step, after the RRT tree is expanded each time, it is necessary to determine whether the target path can be determined from the expanded RRT tree according to the preset condition. If yes, the expansion is stopped, and the target path is obtained from the expanded RRT tree. If no, the expansion is continued or stopped.

[0143] The preset condition is related to the pose of the end position point.

[0144] In a possible implementation, S104 can be implemented through steps (1) to (3):

[0145] In step (1), an error of the target child node relative to the end position point is calculated according to the node information of the target child node and the pose of the end position point.

[0146] Optionally, when the vehicle is a tractor semi-trailer, the horizontal coordinate difference between the target child node and the end position point is less than a first preset distance, the vertical coordinate difference between the target child node and the end position point is less than a second preset distance, the tractor attitude angle difference between the target child node and the end position point is less than a first attitude angle difference, and the trailer attitude angle difference between the target child node and the end position point is less than a second attitude angle difference.

[0147] That is, the error includes the horizontal coordinate difference, the vertical coordinate difference, the tractor attitude angle difference, and the trailer attitude angle difference.

[0148] In step (1), when the vehicle is a tractor semi-trailer, the pose of the end position point is compared with the pose in the node information of the target child node, the proximity of the position corresponding to the target child node to the end position point and the proximity of the direction of the vehicle when the vehicle is at the position corresponding to the target child node to the end position point are determined by calculating the error between the two, which can more accurately determine whether the RRT tree needs to be expanded again.

[0149] In step (2), if the error is less than a preset error, the path from the target child node to the root node is determined as the fifth path.

[0150] Step (3), determining a target path from all fifth paths according to the error of each fifth path and the absolute value summation of the steering angle rate of change of the tractor front wheels of all nodes in the fifth path.

[0151] It should be understood that step (3) can be executed when the number of fifth paths reaches a preset path number, or when the number of samplings in the process of expanding the RRT tree exceeds a preset number.

[0152] For example, a corresponding weight can be assigned to the error and the absolute value summation of the steering angle rate of change in advance, and for each fifth path, the error and the absolute value summation of the steering angle rate of change of the fifth path are weighted and summed to obtain a processed value, and the fifth path corresponding to the smallest processed value is determined as the target path.

[0153] Since the processed value can reflect the error of the target child node relative to the termination position point and the smoothness of the fifth path, the smaller the processed value, the smaller the error of the target child node relative to the termination position point, and the smoother the fifth path, therefore, determining the fifth path corresponding to the smallest processed value as the target path can ensure the accuracy and smoothness of the target path.

[0154] In another possible implementation, the error of the target child node relative to the termination position point can be calculated according to the node information of the target child node and the pose of the termination position point. If the error is less than a preset error, the path from the target child node to the root node is determined as the target path.

[0155] Optionally, in the above two possible implementations, after the target path is determined, a termination node corresponding to the termination position point can be added and connected with the target child node in the target path to generate a processed target path.

[0156] Optionally, when the node information of the target child node does not satisfy the preset condition, it is judged whether the number of samplings in the process of expanding the RRT tree exceeds a preset number. If yes, the expansion is stopped, otherwise, the expansion is continued, that is, steps S102 to S104 are repeatedly executed until the target path is determined or the number of samplings exceeds the preset number.

[0157] In the path processing method provided by the embodiment of the present application, the electronic device obtains obstacle information and the posture of the vehicle at the starting and ending positions, and samples from the road where any first path is located. After each time the posture of the sampling position point is obtained, the parent node corresponding to the sampling position point is determined from the RRT tree based on the posture of the sampling position point and the node information of each node in the RRT tree. Based on the node information of the parent node and the obstacle information, the target child node corresponding to the parent node is added to the RRT tree. When the node information of the target child node meets the preset conditions, the target path is determined based on the target child node and the root node, effectively improving the quality of the target path. In this technical solution, the posture of the tractor and semi-trailer is iteratively calculated during the search process, and the RRT tree is expanded based on the position of each node and the operating status of the vehicle at that position. This can meet the special obstacle avoidance and straightening requirements of the tractor and semi-trailer. The target path determined according to the expanded RRT tree meets the kinematic constraints of the tractor and semi-trailer, improves the smoothness of the target path, ensures good vehicle tracking effect, and avoids collisions between the tractor and semi-trailer and known static obstacles.

[0158] based on Figure 1 In the embodiment shown, S102 is explained in detail below. Figure 2 This is a flow chart of the second embodiment of the path processing method provided in the embodiment of this application. Figure 2 As shown, S102 can be implemented by the following steps:

[0159] S201: Sampling is performed from a road on any first path to obtain a position and posture of a sampling location point.

[0160] In this step, when expanding the RRT tree, sampling locations are required to add new nodes to the RRT tree based on the sampling locations. Since the first path between the starting and ending locations is determined, the target path subsequently determined is the same road as one of the first paths. This means that the location corresponding to the node newly added to the RRT tree must be on a road located on any of the first paths. Therefore, sampling can be performed directly from the road located on any of the first paths to obtain the sampling locations used to add the new node to the RRT tree.

[0161] In a possible implementation, S201 may be implemented through the following steps (4) to (8):

[0162] Step (4) performs random normal sampling within a preset probability range to obtain a probability value for determining the end position point as the sampling position point.

[0163] For example, the preset probability range can be (0, 1). It should be understood that in actual applications, the preset probability range can also be other preset probability ranges, such as (0, 0.5), (0.5, 1), (0.25, 0.75), and the like, and the embodiments of the present application do not specifically limit this.

[0164] For example, the preset probability range is (0, 1). The above probability value can be obtained by random normal sampling k = random (0, 1). Wherein, k is the probability value of determining the termination position point as the sampling position point.

[0165] Step (5), if the probability value is greater than the preset probability value, the termination position point is determined as the sampling position point.

[0166] Optionally, the preset probability value is in the preset probability range, and the specific value can be preset according to actual conditions, and the embodiments of the present application do not specifically limit this.

[0167] After step (5) is executed, subsequent steps (6) to (8) are stopped.

[0168] Step (6), otherwise, the initial sampling position point is obtained by sampling from the road center line of any first path.

[0169] Optionally, the above sampling method can be random normal sampling.

[0170] Step (7), determining the sampling range according to the initial sampling position point and the preset distance.

[0171] Optionally, a square sampling range can be determined with the initial sampling position point as the center and the preset distance as the side length.

[0172] Step (8), sampling from the sampling range to obtain a sampling position point.

[0173] Wherein, the tractor attitude angle and the trailer attitude angle of the sampling position point are the same as those of the initial sampling position point.

[0174] Optionally, a position point can be randomly normally sampled in the above sampling range, the position point is determined as the sampling position point, and the direction of the initial sampling position point is assigned to the sampling position point, so as to obtain the pose of the sampling position point.

[0175] In the above implementation manner, by means of random normal sampling from the preset probability range, there is a certain probability to directly determine the termination position point as the sampling position point, so as to ensure that the RRT tree grows in the direction of the termination position point while expanding around. Meanwhile, due to different operation requirements and vehicle structures of different vehicles, some vehicles cannot always travel along the road center line, so sampling can also be performed within a certain range from the initial sampling position point, and the direction of the initial sampling position point is assigned to the sampling position point obtained by sampling, and the states of the two are combined as the pose of the sampling position point, which is closer to the actual vehicle travel condition.

[0176] S202, after obtaining the pose of the sampling position point each time, for each node in the RRT tree, the first possibility degree of the vehicle traveling from the position point corresponding to the node to the sampling position point is calculated according to the pose of the sampling position point and the node information of all nodes in the second path from the node to the root node.

[0177] In this step, after the pose of the sampling position point is determined, the parent node corresponding to the sampling position point needs to be determined from the RRT tree, so as to expand the RRT tree according to the parent node and add the target child node corresponding to the parent node.

[0178] In a possible implementation manner, the vehicle is a tractor semi-trailer, and the node information includes coordinates, a tractor attitude angle, a trailer attitude angle, a steering angle of a front wheel of the tractor and a steering angle change rate.

[0179] Correspondingly, in the possible implementation manner, S202 can be implemented through the following steps (9) to (12):

[0180] Step (9), after obtaining the pose of the sampling position point each time, for each node in the RRT tree, the third path length and the third path non-smooth degree between the sampling position point and the position point corresponding to the node are determined according to the pose of the sampling position point and the coordinates, the tractor attitude angle and the trailer attitude angle of the node.

[0181] Optionally, the four circular arcs between the coordinates of the node and the left side of the sampling position point can be determined according to the pose of the sampling position point and the coordinates, the tractor attitude angle and the trailer attitude angle of the node, and the third path length and the third path non-smooth degree between the sampling position point and the position point corresponding to the node are determined according to the determined four circular arcs.

[0182] Figure 3 The four circular arcs provided by the embodiments of the present application are shown in the following figure. Figure 3As shown, the radii of the four arcs are R1, R2, R2, and R1, respectively. The gray arc-shaped line segments between the nodes and the sampling location points are the third path lengths between the two, and the third path non-smoothness degree is positively correlated with dy.

[0183] The third path length and the third path non-smoothness degree can also represent the reachability of the vehicle from the corresponding position point of the node to the sampling location point.

[0184] In step (9), when calculating the path length between the sampling location point and the corresponding position point of the node, not only the straight-line distance between the two is calculated according to the coordinates, but also the actual path length when the vehicle travels between the two is calculated in combination with the vehicle direction, so that the calculated value is more accurate. At the same time, since the smoother the path is, the worse the driving fluency is, the non-smoothness degree factor is added to participate in the subsequent determination of whether the node is the parent node corresponding to the sampling location point, and the quality of the target path determined subsequently is further improved.

[0185] Step (10), for each node in the RRT tree, according to the steering angle and the steering angle rate of change of the front wheels of the tractor in all nodes in the second path, the steering angle absolute value sum and the steering angle rate of change absolute value sum of the front wheels of the tractor in all nodes in the second path are calculated.

[0186] Step (11), for each node in the RRT tree, the number of steering angle rates of change used in the discrete steering angle rate of change set of the node is determined.

[0187] Among them, the discrete steering angle rate of change used has been used to determine whether the node can add the next level child node corresponding to the discrete steering angle rate of change used.

[0188] In practical applications, the discrete steering angle rate of change set can be represented by enum_dsteer, which contains a plurality of discrete steering angle rates of change, such as dsteer1, dsteer2, …, dsteer i The index of the discrete steering angle rate of change used in enum_dsteer can be recorded, so as to determine the number of steering angle rates of change used in the discrete steering angle rate of change set of the node.

[0189] Step (12), for each node in the RRT tree, according to the third path length, the third path non-smoothness degree, the number of steering angle rates of change used, the steering angle absolute value sum and the steering angle rate of change absolute value sum of the front wheels of the tractor, the first possibility degree is determined.

[0190] Optionally, the third path length, the third path non-smoothness, the number of used steering angle change rates, the absolute value sum of the steering angle of the front wheel of the towing vehicle and the absolute value sum of the steering angle change rate of the front wheel of the towing vehicle are weighted and summed to determine the first possibility degree.

[0191] Optionally, the first possibility degree can be determined by the following formula:

[0192] Cost1 = Dist + Valid.size + StrreCost + dSteerCost

[0193] wherein, Cost1 is the first possibility degree, Dist is the third path length and the third path non-smoothness, Valid.size is the number of used steering angle change rates, StrreCost is the absolute value sum of the steering angle of the front wheel of the towing vehicle, and dSteerCost is the absolute value sum of the steering angle change rate of the front wheel of the towing vehicle.

[0194] S203, determining the node with the largest first possibility degree as the parent node corresponding to the sampling position point.

[0195] In this step, after the first possibility degree of the vehicle driving from the position point corresponding to each node to the sampling position point is calculated, the node with the largest first possibility degree can be determined as the parent node corresponding to the sampling position point, so as to determine the target node corresponding to the parent node which can be added to the RRT tree in the subsequent step, and achieve the purpose of expanding the RRT tree in the random position.

[0196] The method provided by the above embodiment considers the influence of the vehicle direction, the steering angle of each node of the path and the steering angle change rate on the actual running path of the vehicle when determining the parent node corresponding to the sampling position point in the RRT tree, so that the node with the largest first possibility degree is determined as the parent node corresponding to the sampling position point, and the accuracy of the determination is improved, which lays a foundation for subsequent accurate acquisition of the target path.

[0197] Based on Figure 2 The embodiment shown in FIG. 10 will be explained in detail. Figure 4 The flowchart of the path processing method provided by the third embodiment of the present application is shown in FIG. 10. Figure 4 As shown in FIG. 10, S103 can be implemented by the following steps:

[0198] S401, determining the addable nodes of the parent node in the RRT tree according to the node information of the parent node, the towing vehicle dynamics correction coefficient and the trailer dynamics coefficient.

[0199] In this step, after determining the parent node, the addable child nodes of the parent node also need to be determined, so that the target child node is determined from the addable child nodes and added to the RRT tree.

[0200] Optionally, when the vehicle is a tractor semi-trailer, the addable child nodes of the parent node in the RRT tree can be recursively obtained according to the node information of the parent node, the tractor dynamics correction coefficient, and the trailer dynamics coefficient.

[0201] For example, the node information includes coordinates, tractor attitude angle, trailer attitude angle, steering angle of the tractor front wheel, and steering angle change rate. The recursive process can be implemented according to the following formula:

[0202] Where the left side is the parent node, the right side is the addable child node of the parent node, x and y are the coordinates of the vehicle rear axle as the center point in the reference line coordinate system, yaw1 is the tractor attitude angle in the reference line coordinate system, yaw2 is the trailer attitude angle in the reference line coordinate system, steer is the steering angle of the tractor front wheel, dsteer is the steering angle change rate of the tractor front wheel, c yaw1 is the tractor dynamics correction coefficient, and c yaw2 is the trailer dynamics coefficient.

[0203] S402, for each addable child node, according to the allowed maximum steering angle of the tractor front wheel and the obstacle information, calculate the second possibility degree of the vehicle driving from the position point corresponding to the parent node to the position point corresponding to the addable child node.

[0204] In this step, after determining the plurality of addable child nodes in 401, the target child node to be added to the RRT tree also needs to be determined from the addable child nodes. Wherein, the second possibility degree of the vehicle driving from the position point corresponding to the parent node to the position point corresponding to the addable child node can be calculated, and the target child node is determined according to the second possibility degree.

[0205] In one possible implementation, S402 can be implemented by steps (13) to (16):

[0206] Step (13), for each addable child node, according to the coordinates of the addable child node, the steering angle and the steering angle change rate of the tractor front wheel, and the coordinates of the parent node, the steering angle and the steering angle change rate of the tractor front wheel, determine the fourth path length and the fourth path unsmooth degree between the position point corresponding to the addable child node and the position point corresponding to the parent node.

[0207] It should be understood that the specific implementation and principles of step (13) can refer to the related contents in step (9), which will not be repeated here.

[0208] Step (14), for each addable child node, determining the collision condition between the position point corresponding to the addable child node and the road boundary according to the allowed maximum turning angle of the tractor front wheel and the obstacle information.

[0209] Optionally, for each addable child node, it can be determined whether the turning angle of the tractor front wheel exceeds the allowed maximum turning angle of the tractor front wheel and whether there is an obstacle according to the addable child node and the parent node. When it is determined that the allowed maximum turning angle of the tractor front wheel is exceeded and / or there is an obstacle, it is determined that there is a collision, and a preset maximum value is assigned thereto.

[0210] Step (15), for each addable child node, determining the consistency of the turning angle change direction between the addable child node and the parent node with the turning angle change direction of the parent node and the parent node's previous node.

[0211] Optionally, when it is inconsistent, it means that the turning angle change direction of the vehicle when driving from the position point corresponding to the parent node to the position point corresponding to the addable child node is inconsistent with the previous step, and a preset penalty amount (i.e., a preset value) is assigned thereto, so that the target node determined subsequently can enable the vehicle to continuously turn when driving along the target path.

[0212] Step (16), for each addable child node, calculating the second possibility degree according to the fourth path length, the fourth path roughness, the collision condition, and the consistency.

[0213] Optionally, the fourth path length, the fourth path roughness, the collision condition, and the consistency can be weighted and summed, and the summed value is the second possibility degree.

[0214] Exemplarily, the second possibility degree can be determined by the following formula:

[0215] Cost2 = Dist + CollisionCost + SmoothCost

[0216] Wherein, Cost2 is the second possibility degree, CostCollision is the collision condition, and SmoothCost is the consistency.

[0217] Optionally, after calculating the second possibility of each addable child node, the turning angle change rate of the addable child node relative to the parent node can be marked as used in the discrete turning angle change rate set.

[0218] S403, determining the addable child node with the largest second possibility degree as the target node corresponding to the parent node.

[0219] In this step, after calculating the second possibility degree of the vehicle driving from the position point corresponding to the parent node to the position point corresponding to the addable child node, the node with the largest second possibility degree can be determined as the target child node.

[0220] S404, adding the target child node corresponding to the parent node in the RRT tree.

[0221] The method provided by the above embodiment considers the path length and path smoothness between two nodes, and also considers the collision and smoothness of the addable child node, so that the path where the determined target child node is located will not exceed the allowed maximum steering angle of the front wheel of the tractor and will not collide with the obstacle, and the continuity of vehicle steering is improved.

[0222] Based on any of the above embodiments, after the target path is determined, further smoothing processing can be performed on the target path. Figure 5 The flowchart of the path processing method provided by Embodiment Four of the application is shown in FIG. 6. Figure 5 As shown in FIG. 6, after the target path is determined, the path processing method can further include the following steps:

[0223] S501, generating a segmented polynomial of the target path through cubic spline interpolation.

[0224] In this step, after the target path is determined, the target path can be smoothed through cubic spline interpolation, further improving the path quality.

[0225] Optionally, the target path can be obtained through cubic spline interpolation to obtain x(s), y(s) segmented polynomials (s is the path length).

[0226] S502, performing quadratic programming on the segmented polynomial to obtain the optimized node of the target path.

[0227] In this step, a quadratic programming problem for path smoothing needs to be constructed to optimize the nodes in the target path and obtain the optimized node of the target path.

[0228] In actual application, the transverse deviation of the node of the target path at the cubic spline s i is the optimization variable: d0, d1,..., d n-1 , the first derivative is d'0, d'1,..., d' n-1 , and the second derivative is d''0, d''1,..., d'' n-1 .

[0229] The quadratic programming problem can be represented by the following formula:

[0230]

[0231]

[0232] d0= 0,

[0233]

[0234] d"0= 0

[0235] d n-1 = 0,

[0236]

[0237]

[0238] d' i+1 = d' i + d" i (s i+1 - s i ) + d'" i-＞i+1 (s i+1 - s i ) 2 / 2

[0239] d i+1 = d i + d' i (s i+1 - s i ) + d" i (s i+1 - s i ) 2 / 2 + d'" i-＞i+1 (s i+1 - s i ) 3 / 6

[0240]

[0241] d' min < d' i < d' max

[0242] d" min < d" i < d" max

[0243]

[0244] wherein J is a cost function, which can be expressed by the following formula:

[0245] J = J d + J k + Jdk +J end

[0246] Further, in the cost function:

[0247]

[0248]

[0249]

[0250]

[0251]

[0252] yaw world = yaw ref +d'

[0253] where w d represents the optimization weight of the optimization variable d, w k represents the optimization weight of the curvature in the Cartesian coordinate system, w dk represents the optimization weight of the rate of change of the curvature in the Cartesian coordinate system, represents the optimization weight of the orientation angle of the end position point, represents the optimization weight of the rate of change of the curvature of the end position point. k ref , yaw ref respectively refer to the Cartesian curvature and the Cartesian slope of the cubic spline interpolated by the target path at the corresponding s i .

[0254] where the quadratic programming problem also needs to satisfy the following constraints:

[0255] (1) The initial state boundary value constraint requires that the position and curvature of the smoothed path at the initial state be consistent with the smoothing before, and the path yaw be consistent with the towing vehicle initial attitude angle yaw init .

[0256] (2) The final state boundary value constraint requires that the position of the smoothed path at the final state be consistent with the smoothing before, and the error between the path yaw and the towing vehicle final attitude angle yaw end be within The final state curvature radius is within the range of (-R converg , R converg ).

[0257] (3) The d' continuity constraint

[0258] (4) The d" continuity constraint

[0259] (5) The d, d", d"' range constraint, the cubic spline s iThe normal at the point and the left and right intersection points of the constraint polygon, and s i The point-to-intersection distance as a constraint range of the lateral deviation d of the mounting point

[0260] S503, according to the allowed maximum steering angle of the front wheels of the towing vehicle and the obstacle information, determine whether the position point corresponding to each optimized node collides with the road boundary.

[0261] In this step, it is also necessary to verify whether the optimized node is available. If the position point corresponding to the optimized node collides with the road boundary, it means that the optimized node is not available and needs to be optimized again. If the position point corresponding to the optimized node does not collide with the road boundary, it means that the optimized node is available.

[0262] Optionally, the obtained d0, d1,..., d n-1 , d'0, d'1,..., d' n-1 , d"0, d"1,..., d" n-1 Turn to the world coordinate system, according to the allowed maximum steering angle of the front wheels of the towing vehicle and the obstacle information, determine the collision situation of the position point corresponding to the added sub-node and the road boundary. The specific determination method can refer to step (14) and will not be repeated here.

[0263] S5041, if not, update the target path according to the optimized node to generate an updated target path.

[0264] In this step, when the position point corresponding to the optimized node does not collide with the road boundary, it means that the path formed by the optimized node can meet the driving requirements, and then the optimized node can be output in the Cartesian coordinate system, and the updated target path can be generated according to the optimized node.

[0265] S5042, if yes, according to the collision position point of the path formed by the optimized node and the road boundary, determine the node that needs to be optimized again from all the optimized nodes through the coordinates of the collision position point.

[0266] In this step, when the position point corresponding to the optimized node collides with the road boundary, it means that the path formed by the optimized node at this time does not meet the driving requirements and needs to be optimized again.

[0267] Optionally, the collision coordinates can be determined according to the path coordinates formed by the optimized node and the coordinates of the road boundary. The collision coordinates are converted to the frenet coordinate system with the cubic spline as the s axis to obtain the projection point s, and the bisection method is used to find the optimization variable corresponding to this s. The optimization variable is the node that needs to be optimized again and the lateral deviation at the cubic spline si.

[0268] S5052、decrease the curvature weight and the curvature change rate weight of the node that needs to be optimized again.

[0269] In this step, when the node that needs to be optimized again is found, the curvature weight and the curvature change rate weight need to be decreased to reduce the possibility of collision with the road boundary.

[0270] Optionally, the curvature weight and the curvature change rate weight of the node that needs to be optimized again can be reduced to 1 / 2.

[0271] Optionally, it can be judged whether the number of smoothing processing reaches the preset number of smoothing processing, if yes, stop, if not, repeat S501 to S5052.

[0272] In the above embodiment, after the target path is generated, it can be further smoothed according to the cubic spline interpolation, which improves the quality of the updated target path and the automatic driving performance of the vehicle.

[0273] Based on the path processing method provided in any of the above embodiments, the following will be explained and described through a specific example.

[0274] Figure 6 The flowchart of the path processing method provided in Embodiment Five of the present application is shown in FIG. 5. Figure 6 As shown in the figure, the path processing method includes three parts of constructing a two-dimensional motion planning problem, improving RRT search and post-processing optimization.

[0275] Constructing a two-dimensional motion planning problem

[0276] It should be understood that the path processing method can be implemented through a vehicle model, and constructing a two-dimensional motion planning problem is to construct a vehicle model for determining a target path from a starting position point to a terminal position point.

[0277] First, the pose of the vehicle at the starting position point and the terminal position point input by the user is obtained, and then the vehicle model parameters, the vehicle running state, and the recursive relationship of the vehicle running state in adjacent frames (i to i+1) are defined.

[0278] Vehicle model parameters:

[0279] The model recursive single-step time is dt, the model recursive single-step path length is ds, c yaw1 is a correction coefficient for the tractor dynamics, c yaw2 is a trailer dynamics coefficient, the distance from the front axle of the tractor to the hitch point is l1, the distance from the rear axle of the trailer to the hitch point is l2, the maximum steering angle of the front wheels of the tractor is steer_constraint, and the set of discrete steering angle change rates is enum_dsteer.

[0280] Vehicle running state:

[0281] x, y are coordinates of the center point of the rear axle of the vehicle in the reference line coordinate system, yaw1 is the attitude angle of the tractor in the reference line coordinate system, yaw2 is the attitude angle of the trailer in the reference line coordinate system, steer is the steering angle of the front wheels of the tractor, and dsteer is the change rate of the steering angle of the front wheels of the tractor.

[0282] Recursive relationship:

[0283]

[0284] Further, a plurality of first paths from a starting position point to a terminal position point are obtained from the high-precision map, so as to obtain obstacle information.

[0285] Finally, the parameters of the RRT planning problem and the post-processing optimization problem are input, so as to complete the construction process.

[0286] Improved RRT search

[0287] After the planning starts, the iteration number is incremented by 1, and it is determined whether the iteration number is less than the first preset iteration number. If not, the planning is directly ended. If yes, a random sampling is performed to obtain the pose of the sampling position point, the parent node corresponding to the sampling position point is determined from the RRT tree, the target child node that can be added is determined, the target child node is updated to the RRT tree, and it is determined whether the target child node satisfies the preset condition (that is, it is determined whether the position point corresponding to the target child node reaches the terminal position point). If not, the iteration number is incremented by 1, and the above steps are repeatedly executed until the planning is ended. If yes, the path from the target child node to the root node is determined as the fifth path and is recorded, and it is determined whether the number of fifth paths exceeds the preset path number. If yes, the planning is ended. If not, the iteration number is incremented by 1, and the above steps are repeatedly executed until the planning is ended.

[0288] Post-processing optimization

[0289] A target path is determined from the fifth path, an optimization problem is constructed for the target path, the optimization weight iteration number is incremented by 1, and it is determined whether the current optimization weight iteration number is less than the second preset iteration number. If not, the optimization is ended. If yes, the optimization problem is solved, and it is determined whether the map constraint is satisfied. If yes, the optimization is ended. If not, the constraint position smoothing weight is halved, the optimization weight iteration number is incremented by 1, and the above process is repeatedly executed until the optimization is ended.

[0290] In a specific example, taking a semitrailer as an example, the maximum steering angle is 800 degrees, corresponding to the maximum front wheel steering angle 0.6 rad, the maximum steering angle speed is 400 degrees / s, corresponding to the maximum front wheel steering angle change rate 0.3 rad / s. Now assume that the vehicle is at a minimum cornering speed of 1.5 m / s, which can be processed by the following process:

[0291] 1. Obtain the local high-precision map that needs to search for a feasible path.

[0292] 2. According to the pose of the vehicle at the starting position point and the ending position point, the parameters for constructing the planning problem are given.

[0293] 3. Use the RRT tree considering the kinematic constraints of the tractor-semitrailer to plan multiple paths that the vehicle can reach the ending position point.

[0294] 4. Smooth the target path that the vehicle can reach the ending position point, and check whether all constraints are met. The updated target path is obtained after smoothing.

[0295] Through the above example, it can be seen that the path processing method has the following beneficial effects:

[0296] 1. The sampling method based on the road center line effectively speeds up the result convergence.

[0297] 2. It can generate a path that is beneficial for the automatic driving vehicle to execute and meet the kinematic constraints of the tractor-semitrailer.

[0298] 3. It can avoid collision between the tractor and the semitrailer and static obstacles.

[0299] 4. It ensures the smoothness of the path.

[0300] In order to verify the effect of the technical solution, the prior art and the technical solution are simulated respectively, and the simulation results are as follows.

[0301] Figure 7 The path comparison schematic diagram provided for the embodiments of the present application. As shown in Figure 7 , the original reference line is the target path determined by the prior art, and the search result is the target path determined by the technical solution. By Figure 7 It can be found that the target path determined by the technical solution is smoother than the prior art.

[0302] Figure 8 The curvature comparison schematic diagram provided for the embodiments of the present application. As shown in Figure 8As shown, the curvature of the target path generated by the prior art is greater than that of the present technical solution as a whole, and even exceeds the maximum execution curvature of the vehicle at some positions, which cannot meet the actual operation requirements of the vehicle. The curvature of the target path generated by the present technical solution changes little and is less than the maximum execution curvature of the vehicle, which can meet the special obstacle avoidance and straightening requirements of the tractor-semitrailer.

[0303] Figure 9 A curvature change rate comparison diagram is provided for the embodiments of the present application. As shown in Figure 9 The curvature change rate of the target path generated by the prior art fluctuates much more than that of the present technical solution, that is, the smoothness of the target trajectory of the present technical solution is much greater than that of the prior art.

[0304] The following is an apparatus embodiment of the present application, which can be used to execute the method embodiments of the present application. For details not disclosed in the apparatus embodiments of the present application, please refer to the method embodiments of the present application.

[0305] Figure 10 A structure diagram of a path processing device is provided for the embodiments of the present application. As shown in Figure 10 The path processing device 1000 includes:

[0306] The acquisition module 1001 is configured to acquire obstacle information and poses of a vehicle at a starting position point and a terminal position point, wherein the obstacle information is used to indicate obstacles on both sides of a plurality of first paths from the starting position point to the terminal position point.

[0307] The determination module 1002 is configured to sample from a road where any first path is located, and after acquiring a pose of a sampling position point each time, determine a parent node corresponding to the sampling position point from an RRT tree according to the pose of the sampling position point and node information of each node in the RRT tree, wherein the RRT tree includes a root node and a plurality of nodes under the root node for indicating positions, the node information of each node is used to indicate an operating state of the vehicle at a corresponding position, and the node information of the root node is related to the pose of the starting position point.

[0308] The addition module 1003 is configured to add a target child node corresponding to the parent node in the RRT tree according to the node information of the parent node and the obstacle information.

[0309] The determination module 1002 is further configured to determine a target path according to the target child node and the root node if the node information of the target child node meets a preset condition, wherein the target path is a path from the starting position point to the terminal position point, and the preset condition is related to the pose of the terminal position point.

[0310] In a possible design of the embodiments of the present application, the determining module 1002 is specifically configured to:

[0311] sampling from a road where the first path is located to obtain a pose of the sampling position point;

[0312] after obtaining the pose of the sampling position point each time, for each node in the RRT tree, calculating a first possibility degree of the vehicle traveling from a position point corresponding to the node to the sampling position point according to the pose of the sampling position point and node information of all nodes in the second path from the node to the root node;

[0313] determining the node with the largest first possibility degree as a parent node corresponding to the sampling position point.

[0314] Optionally, the vehicle is a tractor semi-trailer, and the node information includes a coordinate, a tractor attitude angle, a trailer attitude angle, a steering angle of a front wheel of the tractor, and a steering angle change rate.

[0315] Correspondingly, the determining module 1002 is specifically configured to:

[0316] after obtaining the pose of the sampling position point each time, for each node in the RRT tree, determining a third path length and a third path non-smoothness degree between the sampling position point and a position point corresponding to the node according to the pose of the sampling position point and the coordinate, the tractor attitude angle, and the trailer attitude angle of the node;

[0317] for each node in the RRT tree, calculating a steering angle absolute value sum and a steering angle change rate absolute value sum of the front wheel of the tractor of all nodes in the second path according to the steering angle of the front wheel of the tractor and the steering angle change rate of the front wheel of the tractor of all nodes in the second path;

[0318] for each node in the RRT tree, determining a number of used steering angle change rates in a discrete steering angle change rate set of the node, the used steering angle change rate having been used to determine whether the node can add a next level child node corresponding to the used steering angle change rate;

[0319] for each node in the RRT tree, determining the first possibility degree according to the third path length, the third path non-smoothness degree, the number of used steering angle change rates, the steering angle absolute value sum, and the steering angle change rate absolute value sum.

[0320] Optionally, the adding module 1003 is specifically configured to:

[0321] determine, according to the node information of the parent node, the trailer dynamics coefficient and the trailer dynamics coefficient, an addable child node of the parent node in the RRT tree;

[0322] For each addable child node, calculate a second possibility degree of the vehicle from a position point corresponding to the parent node to a position point corresponding to the addable child node according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information;

[0323] determine the addable child node with the largest second possibility degree as a target child node corresponding to the parent node;

[0324] add the target child node corresponding to the parent node in the RRT tree.

[0325] Optionally, the adding module 1003 is specifically configured to:

[0326] For each addable child node, determine a fourth path length and a fourth path unsmooth degree between a position point corresponding to the addable child node and a position point corresponding to the parent node according to the coordinates of the addable child node, the steering angle of the front wheel of the tractor and the steering angle change rate, and the coordinates of the parent node, the steering angle of the front wheel of the tractor and the steering angle change rate.

[0327] For each addable child node, determine a collision condition between the position point corresponding to the addable child node and the road boundary according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information.

[0328] For each addable child node, determine the consistency between the steering angle change direction between the addable child node and the parent node and the steering angle change direction between the parent node and a parent node of the parent node.

[0329] For each addable child node, calculate the second possibility degree according to the fourth path length, the fourth path unsmooth degree, the collision condition and the consistency.

[0330] Optionally, the determining module 1002 is specifically configured to:

[0331] calculate an error of the target child node relative to the terminal position point according to the node information of the target child node and the pose of the terminal position point;

[0332] if the error is less than a preset error, determine a path from the target child node to a root node as a fifth path;

[0333] determine the target path from all fifth paths according to errors of each fifth path and an absolute value cumulative sum of the rate of change of the steering angle of the front wheel of the tractor of all nodes in the fifth path;

[0334] wherein the preset condition is that an error between the target sub-node and the termination position point is less than a preset error.

[0335] Optionally, the path processing apparatus 1000 further comprises:

[0336] a generating module configured to generate a segmented polynomial of the target path through cubic spline interpolation;

[0337] The acquisition module 1001 is further configured to perform quadratic programming on the segmented polynomial to acquire an optimized node of the target path.

[0338] a judging module configured to judge whether a position point corresponding to each optimized node collides with a road boundary according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information.

[0339] The generating module is further configured to, if no, update the target path according to the optimized node to generate an updated target path.

[0340] The determining module 1002 is further configured to, if yes, determine a node that needs to be optimized again from all optimized nodes through a coordinate of a collision position point at which a path composed of the optimized nodes collides with the road boundary.

[0341] a reducing module configured to reduce a curvature weight and a curvature rate weight of the node that needs to be optimized again.

[0342] Optionally, the determining module 1002 is specifically configured to:

[0343] perform random normal sampling in a preset probability range to obtain a probability value of determining the termination position point as the sampling position point;

[0344] if the probability value is greater than a preset probability value, the termination position point is determined as the sampling position point, and the preset probability value is in the preset probability range;

[0345] otherwise, an initial sampling position point is acquired by sampling from a road center line of a road on which any first path is located;

[0346] a determining module configured to determine a sampling range according to the initial sampling position point and a preset distance.

[0347] Sampling is performed within the sampling range to obtain the sampling position point, wherein the tractor attitude angle and the trailer attitude angle at the sampling position point are the same as those at the initial sampling position point.

[0348] Optionally, the determining module 1002 is specifically configured to:

[0349] According to the node information of the target subnode and the position of the terminal position point, it is calculated that the difference between the horizontal coordinates of the target subnode and the terminal position point is less than a first preset distance, the difference between the vertical coordinates of the target subnode and the terminal position point is less than a second preset distance, the difference between the tractor attitude angles of the target subnode and the terminal position point is less than a first attitude angle difference, and the difference between the trailer attitude angles of the target subnode and the terminal position point is less than a second attitude angle difference;

[0350] The error includes the horizontal coordinate difference, the vertical coordinate difference, the tractor attitude angle difference and the trailer attitude angle difference.

[0351] The path processing device provided in the embodiment of the present application can be used to execute the path processing method in any of the above embodiments. Its implementation principles and technical effects are similar and will not be repeated here.

[0352] It should be noted that it should be understood that the division of the various modules of the above device is merely a division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated. Moreover, these modules can all be implemented in the form of software called by processing elements; they can also all be implemented in the form of hardware; some modules can also be implemented in the form of software called by processing elements, and some modules can be implemented in the form of hardware. In addition, these modules can be fully or partially integrated together or implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or by instructions in the form of software.

[0353] Figure 11 This is a schematic diagram of the structure of the electronic device provided in the embodiment of the present application. Figure 11 As shown, the electronic device 1100 may include: a processor 1101, a memory 1102, and computer program instructions stored in the memory 1102 and executable on the processor 1101. When the processor 1101 executes the computer program instructions, the path processing method provided in any of the aforementioned embodiments is implemented.

[0354] Optionally, the above-mentioned components of the electronic device 1100 can be connected via a system bus.

[0355] The memory 1102 can be a separate storage unit or a storage unit integrated in the processor. The number of processors is one or more.

[0356] Optionally, the electronic device 1100 can further include an interface for interacting with other devices.

[0357] It should be understood that the processor 1101 can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor and the like. The steps of the method disclosed in the present application can be directly embodied as hardware processor execution, or executed by a combination of hardware and software modules in the processor.

[0358] The system bus can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The system bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus. The memory can include a random access memory (RAM) and can also include a non-volatile memory (NVM), such as at least one disk memory.

[0359] All or part of the steps of the above-mentioned method embodiments can be completed by program instruction related hardware. The foregoing program can be stored in a readable memory. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the foregoing memory (storage medium) includes a read-only memory (ROM), a RAM, a flash memory, a hard disk, a solid state disk, a magnetic tape, a floppy disk, an optical disc and any combination thereof.

[0360] The electronic device provided by the embodiments of the present application can be used to execute the path processing method provided by any one of the above-mentioned method embodiments, and the implementation principle and technical effects are similar, which will not be described here.

[0361] The embodiment of the present application provides a computer readable storage medium, and the computer readable storage medium stores computer execution instructions. When the computer execution instructions run on a computer, the computer is caused to execute the path processing method.

[0362] The computer readable storage medium described above can be realized by any type of volatile or nonvolatile storage devices or a combination thereof, such as static random access memory, electrically erasable programmable read-only memory, erasable programmable read-only memory, programmable read-only memory, read-only memory, magnetic memory, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0363] Optionally, the readable storage medium is coupled to the processor, so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist as discrete components in the device.

[0364] The embodiment of the present application also provides a computer program product, which includes a computer program stored in a computer readable storage medium, and at least one processor can read the computer program from the computer readable storage medium, and the at least one processor executes the computer program to realize the path processing method.

[0365] It should be understood that the present application is not limited to the precise construction that has been described above and illustrated in the accompanying drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present application is limited only by the claims that follow.

Claims

1. A path processing method, characterized by, The method comprises the following steps: obtaining obstacle information and poses of a vehicle at a starting position point and a terminal position point, the obstacle information being used to represent obstacles on both sides of a plurality of first paths from the starting position point to the terminal position point, and the vehicle being a tractor-semitrailer; sampling from a road in which any first path is located to obtain a pose of a sampling position point; after obtaining the pose of the sampling position point each time, determining, for each node in an RRT tree, a third path length and a third path non-smoothness degree between the sampling position point and a position point corresponding to the node according to the pose of the sampling position point and coordinates of the node, a tractor attitude angle and a trailer attitude angle, calculating, for each node in the RRT tree, a steering angle absolute value sum and a steering rate absolute value sum of a tractor front wheel of all nodes in a second path according to steering angles of the tractor front wheel of the nodes in the second path and steering rate changes of the nodes in the second path, determining, for each node in the RRT tree, a number of used steering rate changes in a discrete steering rate change set of the node, the used steering rate changes having been used to determine whether the node can add a next level child node corresponding to the used steering rate changes, and determining, for each node in the RRT tree, a first possibility degree according to the third path length, the third path non-smoothness degree, the number of the used steering rate changes, the steering angle absolute value sum and the steering rate absolute value sum of the tractor front wheel; determining a node with the largest first possibility degree as a parent node corresponding to the sampling position point; the RRT tree comprises a root node and a plurality of nodes under the root node for representing positions, node information of each node is used to represent a running state of the vehicle at a corresponding position, and node information of the root node is related to a pose of the starting position point; the node information comprises coordinates, a tractor attitude angle, a trailer attitude angle, a steering angle and a steering rate change of a tractor front wheel; adding a target child node corresponding to the parent node in the RRT tree according to the node information of the parent node and the obstacle information; if node information of the target child node meets a preset condition, determining a target path from the starting position point to the terminal position point according to the target child node and the root node, and the preset condition being related to a pose of the terminal position point.

2. The method of claim 1, wherein, The method further comprises the following steps: determining, according to the node information of the parent node, a tractor dynamics correction coefficient and a trailer dynamics coefficient, addable child nodes of the parent node in the RRT tree; for each addable child node, calculating a second possibility degree of the vehicle from a position point corresponding to the parent node to a position point corresponding to the addable child node according to an allowed maximum steering angle of the tractor front wheel and the obstacle information; and determining, for each addable child node, a steering rate change corresponding to the addable child node according to the node information of the parent node, the tractor dynamics correction coefficient and the trailer dynamics coefficient. determining the second possibility degree of the vehicle from the position point corresponding to the parent node to the position point corresponding to the addable child node according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information; adding the target child node corresponding to the parent node in the RRT tree.

3. The method of claim 2, wherein, The method further comprises: determining the second possibility degree of the vehicle from the position point corresponding to the parent node to the position point corresponding to the addable child node according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information, comprising: For each addable child node, determining the fourth path length and the fourth path unsmooth degree between the position point corresponding to the addable child node and the position point corresponding to the parent node according to the coordinates of the addable child node, the steering angle and the steering angle change rate of the front wheel of the tractor, and the coordinates of the parent node, the steering angle and the steering angle change rate of the front wheel of the tractor; For each addable child node, determining the collision between the position point corresponding to the addable child node and the road boundary according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information; For each addable child node, determining the consistency of the steering angle change direction between the addable child node and the parent node and the steering angle change direction between the parent node and the parent node of the previous node of the parent node; For each addable child node, calculating the second possibility degree according to the fourth path length, the fourth path unsmooth degree, the collision, and the consistency.

4. The method according to claim 2 or 3, characterized in that, If the node information of the target child node meets the preset condition, determining a target path according to the target child node and the root node, the target path being a path from the starting position point to the terminal position point, comprising: calculating the error of the target child node relative to the terminal position point according to the node information of the target child node and the pose of the terminal position point; if the error is less than a preset error, determining the path from the target child node to the root node as a fifth path; determining the target path from all fifth paths according to the error of each fifth path and the absolute value sum of the steering angle change rate of the front wheel of the tractor of all nodes in the fifth path; wherein the preset condition is that the error of the target child node relative to the terminal position point is less than a preset error.

5. The method according to claim 2 or 3, characterized in that, The method further comprises: generating a segmented polynomial of the target path through cubic spline interpolation; performing quadratic programming on the segmented polynomial to obtain optimized nodes of the target path; determining whether a collision occurs between the position point corresponding to each optimized node and the road boundary according to the allowed maximum steering angle of the front wheel of the tractor and the obstacle information; if not, updating the target path according to the optimized nodes to generate an updated target path; if yes, determining the node that needs to be optimized again from all optimized nodes through the coordinates of the collision position point where the path formed by the optimized nodes collides with the road boundary; reducing the curvature weight and the curvature change rate weight of the node that needs to be optimized again.

6. The method according to claim 2 or 3, characterized in that, The method further comprises: sampling from the road where any first path is located to obtain the pose of the sampling position point, comprising: randomly sampling in a preset probability range to obtain a probability value of determining the termination position point as the sampling position point; if the probability value is greater than a preset probability value, determining the termination position point as the sampling position point, the preset probability value being in the preset probability range; otherwise, sampling an initial sampling position point from a road center line of a road where any first path is located; determining a sampling range according to the initial sampling position point and a preset distance; sampling the sampling position point from the sampling range, the towing vehicle attitude angle and the trailer attitude angle of the sampling position point being the same as those of the initial sampling position point.

7. The method of claim 4, wherein, the error of the target sub-node relative to the termination position point is calculated according to the node information of the target sub-node and the pose of the termination position point, and the error comprises: the horizontal coordinate difference value, the longitudinal coordinate difference value, the towing vehicle attitude angle difference value and the trailer attitude angle difference value. a processor, a memory and computer program instructions stored on the memory and executable on the processor, and when the processor executes the computer program instructions, the processor is configured to implement the path processing method according to any one of claims 1 to 7.

8. An electronic device comprising: a processor, a memory and computer program instructions stored on the memory and executable on the processor, and when the processor executes the computer program instructions, the processor is configured to implement the path processing method according to any one of claims 1 to 7.

Images