Vehicle driving path planning method and device, computer equipment and storage medium

Abstract

The present disclosure relates to the technical field of computer, in particular to a vehicle driving path planning method and device, computer equipment and storage medium, the method comprising: obtaining a target vehicle speed, target vehicle current position information, surrounding perception information within a preset range of the current position information, and a preset space within the preset range and available for the target vehicle to escape; determining a mode state in which the target vehicle is currently located according to the vehicle speed, the current position information, the surrounding perception information, and the preset space; obtaining a target coordinate point at a target position included in the preset space; updating a first random tree generated according to the current position information, the target coordinate point, and any plurality of coordinate points in the preset space to obtain a target curve path; and according to a comparison result of the target curve path and an optimal solution, taking the target curve path as a final planning path or taking a specific curve path composed of a plurality of modes as the final planning path.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computers, in particular to a vehicle driving path planning method and device, a computer device and a storage medium. BACKGROUND

[0002] In the actual driving process of the current autonomous vehicle, when encountering a congestion blocked road section, the vehicle needs to make a decision in advance to perform a detouring behavior in the blocked situation, so as to achieve efficient and more convenient handling of congestion and the like, especially on some unstructured roads. At this time, the vehicle needs to actively perform a detouring behavior to improve the convenience of the autonomous driving experience. The autonomous vehicle actively performs a detouring behavior, which is essential in the autonomous vehicle system.

[0003] In the current vehicle intelligent detouring obstacle avoidance path planning method, a mixed A* method can be used to plan a detouring path according to the actual position information and perception information of the host vehicle. However, in the actual search, the search time may be long due to some relatively complex road conditions, and an optimal solution cannot be obtained. Finally, the host vehicle cannot be provided with a suitable path for execution. Another method for planning a detouring obstacle avoidance path is machine learning: by collecting driver operation data, intelligently identifying the current predicament type through machine learning based on vehicle sensor parameters, and formulating a detouring scheme according to the current type. However, this scheme requires a large amount of data for training, and needs to collect relevant data and methods for successful detouring to generate a scheme. In actual operation, some situations that do not appear in the training set may be encountered, which is not efficient and cannot achieve the expected effect. In addition, human intervention is required, and the method is not intelligent and convenient.

[0004] Therefore, the related technology has the problems of being unable to obtain an optimal path and the generation process not being intelligent and convenient when planning a vehicle intelligent detouring obstacle avoidance path. SUMMARY

[0005] Therefore, the present disclosure provides a vehicle driving path planning method, device, computer device and storage medium to solve the problems of being unable to obtain an optimal path and the generation process not being intelligent and convenient when planning a vehicle intelligent detouring obstacle avoidance path in the related technology.

[0006] In a first aspect, the present disclosure provides a vehicle driving path planning method, which comprises:

[0007] obtaining a vehicle speed of a target vehicle, current position information of the target vehicle, surrounding perception information within a preset range of the current position information, and a preset space within the preset range and available for the target vehicle to detour;

[0008] determine a mode state in which the target vehicle currently is according to the vehicle speed, the current position information, the surrounding perception information and the preset space;

[0009] In a case where the mode state is a target mode state, obtain a target coordinate point at a target position included in the preset space;

[0010] update a generated first random tree according to the current position information, the target coordinate point and any plurality of coordinate points in the preset space, to obtain a target curve path, wherein the first random tree is generated with the current position information as a root node;

[0011] determine the target curve path as a final planning path or a specific curve path composed of a multi-mode combination according to a comparison result of the target curve path and an optimal solution, wherein the multi-mode combination is determined according to the current position information, a current heading angle of the target vehicle and a turning radius.

[0012] In the embodiments of the present disclosure, the mode state in which the target vehicle currently is is determined according to the obtained vehicle speed of the target vehicle, the current position information of the target vehicle, the surrounding perception information within a preset range of the current position information and a preset space included in the preset range and available for the target vehicle to escape, in a case where the mode state is a target mode state, a target coordinate point at a target position included in the preset space is obtained, then a first random tree is updated according to the current position information, the target coordinate point and any plurality of coordinate points in the preset space, to obtain a target curve path, then it is determined whether the target curve path is taken as a final planning path or a specific curve path composed of a multi-mode combination determined according to the current position information, a heading angle and a turning radius of the target vehicle is taken as the final planning path according to a comparison result of the target curve path and an optimal solution. In this way, the solving methods of the two curve paths are combined to determine the final planning path, which is beneficial to the solution of actual problems, and can also consider path planning in complex situations. When a suitable optimal solution path cannot be obtained based on the target curve path, the specific curve path is obtained, which greatly improves the success rate of the escape and detour path planning in complex extreme situations, has better effect and more stable performance, and solves the problems that an optimal path cannot be obtained and the generation process is not intelligent and convenient in related technologies for planning an intelligent escape and obstacle avoidance path of a vehicle.

[0013] In an alternative embodiment, the mode state in which the target vehicle currently is is determined according to the vehicle speed, the current position information, the surrounding perception information and the preset space, comprising:

[0014] In a case that the vehicle speed is a preset value, the number of obstacles determined by the surrounding perception information is less than a first preset threshold, and a preset space exists adjacent to the current position information, it is determined that the mode state in which the target vehicle currently is is a target mode state.

[0015] In the embodiments of the present disclosure, the mode state in which the target vehicle currently is is determined through the determination of the vehicle speed, the surrounding obstacles and the preset space, which lays a good foundation for the path planning of the target vehicle.

[0016] In an optional implementation, the first random tree is updated according to the current position information, the target coordinate point and any plurality of coordinate points in the preset space, and a target curve path is obtained, including:

[0017] A plurality of coordinate points in the preset space are obtained.

[0018] The first random tree is updated according to the inclusion relationship between the plurality of coordinate points and the coverage range of the obstacle existing in the preset space and the positional relationship between the current position information and the plurality of coordinate points.

[0019] A new node to be generated is determined according to the updated first random tree.

[0020] The new node is added to the updated first random tree according to the inclusion relationship between the new node and the coverage range of the obstacle existing in the preset space, until the distance between the new node and the target coordinate point is less than a second preset threshold, a second random tree is generated, and a connection line between all nodes included in the second random tree is taken as a planning path.

[0021] The planning path is smoothed to obtain a target curve path.

[0022] In the embodiments of the present disclosure, the first random tree is updated according to the inclusion relationship between the plurality of coordinate points in the preset space and the coverage range of the obstacle existing in the preset space and the positional relationship between the current position information and the plurality of coordinate points, and a new node is generated according to the updated first random tree to obtain a second random tree, and then the planning path is determined, which improves the timeliness and convenience of the determination of the planning path to a certain extent, considers a plurality of types of nodes, increases the basic solution space and improves the richness of the solution.

[0023] In an optional implementation, the first random tree is updated according to the inclusion relationship between the plurality of coordinate points and the coverage range of the obstacle existing in the preset space and the positional relationship between the current position information and the plurality of coordinate points, including:

[0024] If the plurality of coordinate points are all included in the coverage range of the obstacle, the coordinate points are reselected in the preset space.

[0025] If any of the plurality of coordinate points is not contained in the obstacle coverage range, the reference coordinate point is added to the first random tree to obtain an updated first random tree;

[0026] If none of the plurality of coordinate points is contained in the obstacle coverage range or a preset number of coordinate points are not contained in the obstacle coverage range, a specific coordinate point closest to the current position information is selected from the plurality of coordinate points or the preset number of coordinate points, and the specific coordinate point is added to the first random tree to obtain an updated first random tree.

[0027] In an optional embodiment, the new node is added to the updated first random tree according to the inclusion relationship between the new node and the obstacle coverage range existing in the preset space, including:

[0028] The growth direction and growth distance of the new node are obtained;

[0029] Whether the new node is added to the updated first random tree is determined according to the growth direction, the growth distance, and the inclusion relationship between the new node and the obstacle coverage range existing in the preset space;

[0030] If the growth direction meets a preset direction, the growth distance meets a preset distance, and the new node is not contained in the obstacle coverage range, the new node is added to the updated first random tree.

[0031] In the embodiments of the present disclosure, by obtaining the growth direction and growth distance of the new node and the inclusion relationship between the new node and the obstacle coverage range existing in the preset space, it is determined whether the new node is added to the updated first random tree, so that the next node of the random tree is obtained more regularly, and thus the finally obtained planning path is rule-based and more in line with the driving habits of the target vehicle.

[0032] In an optional embodiment, according to a comparison result of the target curve path and the optimal solution, the target curve path is taken as the final planning path or a specific curve path composed of a plurality of morphologies is taken as the final planning path, including:

[0033] It is determined whether the target curve path is the optimal solution;

[0034] In a case where the target curve path is the optimal solution, the target curve path is taken as the final planning path;

[0035] In a case where the target curve path is not the optimal solution, a current heading angle and a turning radius of the target vehicle are obtained;

[0036] According to the current position information, the current heading angle, and the turning radius, a plurality of morphologies corresponding to the target vehicle and the driving direction and driving distance of each morphology are determined.

[0037] obtaining a specific curve path according to the driving direction and the driving distance;

[0038] taking the specific curve path as the final planning path.

[0039] In the embodiments of the present disclosure, the obtained target curve path is compared with the optimal solution path, if the target curve path is the optimal solution, the target curve path is directly taken as the final planning path, if the target curve path is not the optimal solution, the path planning operation in complex situations is performed through the specific curve path, the combination of the two methods is more conducive to the solution of actual problems and the improvement of the success rate of the path planning in complex and extreme situations.

[0040] In an optional implementation, the multi-configuration combination corresponding to the target vehicle and the driving direction and the driving distance of each configuration are determined according to the current position information, the current heading angle and the turning radius, including:

[0041] the multi-configuration combination and the driving direction of each configuration are determined according to the current position information and the current heading angle;

[0042] the new heading coordinate of the target vehicle is determined according to the driving direction and the current position information and the turning radius;

[0043] the driving distance of each configuration is determined according to the new heading coordinate.

[0044] In the embodiments of the present disclosure, the driving direction of each configuration under the multi-configuration combination is determined through the current position information, and the driving distance of each configuration under the multi-configuration combination is determined based on the new heading coordinate, so that the space for solving is increased in some complex and extreme situations.

[0045] In a second aspect, the present disclosure provides a planning device for a vehicle driving path, the device comprising:

[0046] a first obtaining module, configured to obtain the vehicle speed of a target vehicle, the current position information of the target vehicle, the surrounding perception information within a preset range of the current position information, and a preset space within the preset range and containing a target position available for the target vehicle to escape from a trouble;

[0047] a determining module, configured to determine the mode state in which the target vehicle is currently located according to the vehicle speed, the current position information, the surrounding perception information and the preset space;

[0048] a second obtaining module, configured to obtain the target coordinate point at the target position within the preset space in the case that the mode state is a target mode state;

[0049] The update module is used to update the generated first random tree based on the current location information, the target coordinate point, and any number of coordinate points within the preset space to obtain the target curve path. The first random tree is generated using the current location information as the root node.

[0050] The setting module is used to select the target curve path as the final planned path or a specific curve path composed of multiple shapes as the final planned path based on the comparison results between the target curve path and the optimal solution. The multiple shapes are determined based on the current position information, the target vehicle's current heading angle, and the turning radius.

[0051] Thirdly, this disclosure provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the vehicle driving path planning method of the first aspect or any corresponding embodiment described above.

[0052] Fourthly, this disclosure provides a computer-readable storage medium storing computer instructions for causing a computer to execute the vehicle travel path planning method of the first aspect or any corresponding embodiment described above. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating a method for planning vehicle travel paths according to some embodiments of the present disclosure;

[0055] Figure 2 This is a schematic diagram of the overall process of a vehicle driving path planning method according to some embodiments of the present disclosure;

[0056] Figure 3 This is a structural block diagram of a vehicle travel path planning device according to some embodiments of the present disclosure;

[0057] Figure 4 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present disclosure. Detailed Implementation

[0058] To make the purposes, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0059] In the actual driving process of the current autonomous vehicle, when encountering a congestion blocked road section, the vehicle needs to make a decision in advance to perform a detour behavior in the blocked situation, so as to achieve efficient and more convenient handling of congestion and the like for the autonomous vehicle.

[0060] The existing method of planning a detour path based on the current host vehicle actual position information and perception information based on hybrid A* may be limited by some relatively complex road conditions in the actual search, resulting in long search time and no optimal solution, and ultimately failing to provide the host vehicle with a suitable path for execution. The method of selecting a detour scene by obtaining driver operation data and sensor data combined with machine learning and formulating a scheme for different scenes considers the need for a large amount of driving data and related data collection and training, and in actual operation, the pre-training set may not necessarily appear, so it is not directly efficient and convenient, and may not achieve the expected path and expected effect.

[0061] To solve the above problems, according to the embodiments of the present disclosure, a vehicle driving path planning method is provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0062] In the present embodiment, a vehicle driving path planning method is provided, Figure 1 is a flowchart of the vehicle driving path planning method according to the embodiments of the present disclosure, as Figure 1 shown, the method can be applied to the server side, and the method flow includes the following steps:

[0063] Step S101, obtaining the speed of the target vehicle, the current position information of the target vehicle, the surrounding perception information within a preset range of the current position information, and the preset space within the preset range that can be used for the target vehicle to detour.

[0064] Optionally, in the embodiment of the present disclosure, first, the chassis information of the target vehicle is acquired to obtain the current vehicle speed, then the current position information of the target vehicle is obtained through the vehicle GPS positioning system, and the surrounding sensing information within a certain preset range (such as 3 meters) of the current position information is acquired through the vehicle sensor. It can be understood that the surrounding sensing information can be some obstacle information; the target vehicle can be any car on the road.

[0065] In addition, it is also necessary to acquire whether there is a preset space within the preset range for the target vehicle to escape. It can be understood that the preset space here can be an area space of 5-10 target vehicle bodies, and if the target vehicle currently exists in the preset space, it means that the target vehicle can enter the preset space to escape and detour.

[0066] Step S102, according to the vehicle speed, the current position information, the surrounding sensing information and the preset space, the mode state in which the target vehicle currently is determined.

[0067] Optionally, according to the current vehicle speed of the target vehicle, the current position information of the target vehicle, the surrounding sensing information of the target vehicle and the surrounding preset space of the target vehicle, the mode state in which the target vehicle currently should be determined. It should be noted that the mode state can include a waiting state, an initial preheating state of entering an escape and detour, a formal entering escape and detour state, etc.

[0068] Step S103, in the case that the mode state is the target mode state, the target coordinate point at the target position contained in the preset space is acquired.

[0069] Optionally, in the embodiment of the present disclosure, the formal entering escape and detour state is taken as the target mode state. After determining that the target vehicle enters the target mode state, the current position information of the target vehicle (which is actually a coordinate point) is taken as the starting point, and an appropriate target position in the preset space available for detour is selected, and the target coordinate point thereof is recorded as the ending point.

[0070] It should be explained that the appropriate target position here refers to the coordinate point at the maximum number of vehicle body areas in which the target vehicle can successfully escape and detour, and of course the real existence of the surrounding obstacles also needs to be considered when determining the maximum number. After combining the surrounding obstacles, the target position can be obtained as the coordinate point at the tail of the i-th vehicle body, and i can be 8, 7, etc.

[0071] Step S104, according to the current position information, the target coordinate point and any multiple coordinate points in the preset space, a first random tree generated is updated to obtain a target curve path, wherein the first random tree is generated by taking the current position information as a root node.

[0072] Optionally, the current position information of the target vehicle is taken as a starting point, the current position information is taken as a root node, and the target coordinate point is marked as an end point, and a first random tree is generated from the starting point and the end point, and a method of RRT (Rapidly-Exploring Random Tree) is used in subsequent path planning calculation.

[0073] After the first random tree is obtained, the first random tree can be updated according to the current position information of the target vehicle, the target coordinate point, and any plurality of coordinate points selected from the preset space, and a target curve path is obtained.

[0074] In step S105, the target curve path is taken as a final planning path or a specific curve path composed of a plurality of morphologies is taken as the final planning path according to a comparison result of the target curve path and an optimal solution, wherein the plurality of morphologies are determined according to the current position information, a current heading angle of the target vehicle, and a turning radius.

[0075] Optionally, after the target curve path is obtained according to the RRT algorithm, the target curve path is compared with an optimal solution (i.e., a reasonable path without collision), and it is determined whether the target curve path is the optimal solution. If the target curve path is the optimal solution, the target curve path is directly taken as the final planning path. If the target curve path is not the optimal solution, a specific curve path library is generated by combining specific curves, a specific curve path composed of left turns, right turns, and straight lines is obtained, and a final planning path is obtained.

[0076] It should be understood that the plurality of morphologies are actually left turns, right turns, and straight lines, and the determination of the three morphologies is determined by the current position information of the target vehicle, the current heading angle of the target vehicle, and the turning radius.

[0077] In this embodiment of the disclosure, the target vehicle's current mode state is determined by acquiring the target vehicle's speed, current location information, surrounding perception information within a preset range of the current location information, and a preset space within the preset range that allows the target vehicle to escape from trouble. If the mode state is the target mode state, the target coordinate points at the target location within the preset space are acquired. Then, based on the current location information, the target coordinate points, and any multiple coordinate points within the preset space, the generated first random tree is updated to obtain the target curve path. Then, based on the comparison result between the target curve path and the optimal solution, it is determined whether the target curve path or a specific curve path composed of multiple morphological combinations determined by the target vehicle's current location information, heading angle, and turning radius is used as the final planned path. Combining the two methods of solving curved paths to determine the final planned path is beneficial for solving practical problems. It also takes into account path planning in complex situations. When a suitable optimal solution path cannot be obtained based on the target curved path, the method of obtaining a specific curved path greatly improves the ability to successfully plan escape and detour paths in complex and extreme situations. The effect is better and the performance is more stable. It solves the problem that related technologies cannot obtain the optimal path and the generation process is not intelligent and convenient enough when planning intelligent escape and obstacle avoidance paths for vehicles.

[0078] In some optional implementations, the current mode state of the target vehicle is determined based on vehicle speed, current location information, surrounding perception information, and a preset space, including:

[0079] When the vehicle speed is a preset value, the number of obstacles determined by the surrounding perception information is less than a first preset threshold, and there is a preset space near the current location information, the current mode state of the target vehicle is determined to be the target mode state.

[0080] Optionally, when the vehicle speed is a preset value (i.e., the vehicle speed is 0), it is considered that the target vehicle has entered a blocked environment state and the target vehicle enters the initial warm-up state for getting out of trouble and bypassing. Then, whether to officially enter the state of getting out of trouble and bypassing needs to be further determined whether the number of obstacles around the target vehicle is less than a first preset threshold (e.g., 3). If it is less than the first preset threshold, it is considered that there are relatively few obstacles around. Then, it is further determined whether there is a preset space near the target vehicle that can get out of trouble. If the preset space also exists, the target vehicle is controlled to officially enter the target mode state of getting out of trouble and bypassing.

[0081] Understandably, even if the target vehicle's speed is 0, if the target vehicle senses too many obstacles around it and there is no pre-set space for it to get out of trouble, the target vehicle will continue to wait in its current state.

[0082] In the embodiments of the present disclosure, the mode state in which the target vehicle currently is determined through the determination of the vehicle speed, the surrounding obstacles and the preset space, thereby laying a good foundation for the path planning of the target vehicle.

[0083] In some optional embodiments, the generated first random tree is updated according to the current position information, the target coordinate point and any plurality of coordinate points in the preset space, to obtain a target curve path, including:

[0084] Obtaining a plurality of coordinate points in the preset space;

[0085] Updating the first random tree according to the inclusion relationship between the plurality of coordinate points and the coverage range of the existing obstacles in the preset space and the position relationship between the current position information and the plurality of coordinate points;

[0086] Determining a new node to be generated according to the updated first random tree;

[0087] According to the inclusion relationship between the new node and the coverage range of the existing obstacles in the preset space, the new node is added to the updated first random tree until the distance between the new node and the target coordinate point is less than a second preset threshold, a second random tree is generated, and the connection between all nodes contained in the second random tree is taken as a planned path;

[0088] Smoothing the planned path to obtain a target curve path.

[0089] Optionally, the first random tree is initialized by using the RRT algorithm, and the current position information of the target vehicle is taken as the starting point of the random tree search, at this time, the first random tree contains one node, which is the root node, that is, the current position information is taken as the root node. Then a plurality of coordinate points are randomly sampled from the preset space, and the coordinate points added to the first random tree as new nodes are determined according to the inclusion relationship between the plurality of coordinate points and the coverage range of the existing obstacles in the preset space and the position relationship between the current position information and the plurality of coordinate points, thereby updating the first random tree to obtain the updated first random tree.

[0090] Then, a new node to be generated in the updated first random tree is needed to be obtained, and whether the new node is added to the updated first random tree can be determined according to the inclusion relationship between the new node and the coverage range of the existing obstacle in the preset space. If the new node is not in the coverage range of the obstacle, the new node is considered to be a safe node, and the new node can be added to the updated first random tree. Otherwise, resampling is performed until the distance between the new node and the target coordinate point is less than a second preset threshold (for example, 0.1 meters), and the current new node is considered to be the last path node added to the updated first random tree. After all path nodes are obtained, a random tree generated by the path nodes is referred to as a second random tree, and all nodes in the second random tree are connected to obtain a planned path.

[0091] The planned path is smoothed, for example, the planned path is smoothed by a B-spline curve to obtain a target curve path. The B-spline curve can fit the preposed path points into a curve as the target curve path. The general expression of the B-spline curve is:

[0092]

[0093] where t min ≤t≤t max , 2≤d≤n

[0094] In the above formula, represents a point coordinate vector on the curve, n is the number of control points , B represents the coordinate of the control point (i starts from 0), B i,d(t) represents the polynomial coefficient of the control point coordinate influence weight (where i represents the index of the coordinate, and n represents the highest power of the polynomial), d influences the degree of the B-spline curve, and t is the value when the curve is drawn.

[0095] In the embodiments of the present disclosure, the first random tree is updated according to the inclusion relationship between the plurality of coordinate points in the preset space and the coverage range of the existing obstacle in the preset space and the position relationship between the current position information and the plurality of coordinate points, the new node is generated according to the updated first random tree, the second random tree is obtained, and then the planned path is determined. This generation mode of the tree node improves the timeliness and convenience of the determination of the planned path to a certain extent, and considers various types of nodes, increases the basic solution space, and improves the richness of the solution.

[0096] In some optional embodiments, the first random tree is updated according to the inclusion relationship between the plurality of coordinate points and the coverage range of the existing obstacle in the preset space and the position relationship between the current position information and the plurality of coordinate points, and the first random tree is updated.

[0097] If all the coordinate points are contained in the obstacle coverage range, the coordinate points are reselected in the preset space;

[0098] If any reference coordinate point in the plurality of coordinate points is not contained in the obstacle coverage range, the reference coordinate point is added to the first random tree to obtain an updated first random tree;

[0099] If all the coordinate points are not contained in the obstacle coverage range or a preset number of coordinate points are not contained in the obstacle coverage range, a specific coordinate point closest to the current position information is selected from the plurality of coordinate points or the preset number of coordinate points, and the specific coordinate point is added to the first random tree to obtain an updated first random tree.

[0100] Optionally, when the first random tree is added to the node, the inclusion relationship between the plurality of coordinate points and the obstacle coverage range existing in the preset space is updated: if all the coordinate points are contained in the obstacle coverage range, the coordinate points are reselected in the preset space, and the operation of adding to the first random tree node is not performed; if any reference coordinate point in the plurality of coordinate points is not contained in the obstacle coverage range, the reference coordinate point is added to the first random tree to obtain an updated first random tree; if all the coordinate points are not contained in the obstacle coverage range or a preset number (such as 2 or more than 2) of coordinate points are not contained in the obstacle coverage range, a specific coordinate point closest to the current position information is selected according to the positional relationship between the current position information and the coordinate points, and the specific coordinate point is added to the first random tree to obtain an updated first random tree.

[0101] In an optional embodiment, the new node is added to the updated first random tree according to the inclusion relationship between the new node and the obstacle coverage range existing in the preset space, and the method comprises the following steps:

[0102] The growth direction and the growth distance of the new node are obtained;

[0103] Whether the new node is added to the updated first random tree is determined according to the growth direction, the growth distance, and the inclusion relationship between the new node and the obstacle coverage range existing in the preset space;

[0104] If the growth direction meets a preset direction, the growth distance meets a preset distance, and the new node is not contained in the obstacle coverage range, the new node is added to the updated first random tree.

[0105] Optionally, since the current new node is generated after the updated first random tree, and the updated first random tree at least contains the root node (i.e. the starting point), an added leaf node and a leaf node with an out-degree of 0 (i.e. the end point), the existing nodes in the first random tree are connected, so as to determine the growth direction of the subsequent new node to be generated, and the growth distance of the new node is obtained. In this way, the new node determines whether to add the new node to the updated first random tree according to the growth direction, the growth distance and the inclusion relationship between the new node and the coverage range of the existing obstacle in the preset space.

[0106] Further, the disclosure embodiment can set a preset distance (such as 0.5m) for the growth of the new node. If the new node to be generated satisfies the preset direction corresponding to the connection of the existing nodes in the first random tree, the growth distance of the new node satisfies the preset distance, and the new node is not included in the coverage range of the obstacle, the new node is added to the updated first random tree.

[0107] In the disclosure embodiment, by obtaining the growth direction and growth distance of the new node and the inclusion relationship between the new node and the coverage range of the existing obstacle in the preset space, it is confirmed whether to add the new node to the updated first random tree. The next node of the random tree is obtained more regularly, so that the final planning path is rule-based and more in line with the driving habits of the target vehicle.

[0108] In some optional embodiments, according to the comparison result of the target curve path and the optimal solution, the target curve path is taken as the final planning path or a specific curve path composed of a plurality of morphological combinations is taken as the final planning path, which includes:

[0109] Determine whether the target curve path is the optimal solution;

[0110] In the case that the target curve path is the optimal solution, the target curve path is taken as the final planning path;

[0111] In the case that the target curve path is not the optimal solution, the current heading angle and the turning radius of the target vehicle are obtained;

[0112] According to the current position information, the current heading angle and the turning radius, the plurality of morphological combinations corresponding to the target vehicle and the driving direction and driving distance of each morphological combination are determined;

[0113] According to the driving direction and the driving distance, the specific curve path is obtained;

[0114] The specific curve path is taken as the final planning path.

[0115] Optionally, in a case where the target curve path is determined as the optimal solution, the target curve path is taken as the final planning path; in a case where the target curve path is not the optimal solution, the current heading angle and the turning radius of the target vehicle are obtained.

[0116] According to the current position information, the current heading angle and the turning radius, the combination path of the target vehicle in multiple forms and the driving direction and driving distance of each form can be determined. For example, the current position information of the target vehicle is (x, y), the current heading angle is ( the angle formed by the direction after the vehicle turns and the original forward direction), at this time, the azimuth coordinate is At this time, the azimuth coordinate can be determined based on whether the target vehicle needs to turn left or right or go straight, and the driving direction is obtained. Then, based on the turning radius R, the driving distance of each form is obtained.

[0117] After the driving direction and the driving distance of each form are determined, a specific curve path can be generated, and the specific curve path is taken as the final planning path.

[0118] In the embodiments of the present disclosure, the obtained target curve path is compared with the optimal solution path, if the target curve path is the optimal solution, the target curve path is directly taken as the final planning path, if the target curve path is not the optimal solution, the path planning operation in complex situations is performed by obtaining the specific curve path, the combination of the two methods is more conducive to the solution of actual problems and the improvement of the success rate of the path planning of the escape and detour in complex and extreme situations.

[0119] In an optional implementation, according to the current position information, the current heading angle and the turning radius, the multiple form combinations corresponding to the target vehicle and the driving direction and driving distance of each form are determined, including:

[0120] According to the current position information and the current heading angle, the multiple form combinations and the driving direction of each form are determined.

[0121] According to the driving direction, the current position information and the turning radius, the new heading coordinate of the target vehicle is determined.

[0122] According to the new heading coordinate, the driving distance of each form is determined.

[0123] Optionally, if the coordinate of the current position information of the target vehicle is (x, y), the heading angle is The initial azimuth coordinate is The turning radius is R, assuming that the distance along the straight line when going straight is L, then the new heading coordinate can be calculated by the related geometric relationship formula as:

[0124]

[0125] In the left direction to generate escape from the roundabout path, assuming the vehicle left turn angle is R, the new heading coordinates are:

[0126]

[0127] In the right direction to generate escape from the roundabout path, assuming the vehicle right turn angle is R, the new heading coordinates are:

[0128]

[0129] The above calculation method is normalized, that is, if R is 1, the distance traveled That is, the length of the arc and the straight line can be represented by L at this time, then:

[0130]

[0131]

[0132]

[0133] Where, represent the distance traveled when left turning; represent the distance traveled when right turning; represent the distance traveled when straight.

[0134] For example, after the initial coordinates (0, 0, α) and the end point coordinates (d, 0, β) of the vehicle are known, the path can be generated in the form of arc + straight line, according to the initial coordinates and the heading angle, the driving direction is: the vehicle first left turn t arc and then straight p and then left turn q, combined with the above normalized formula

[0135] L q (S p (L t (0, 0, α)) = (d, 0, β)

[0136] Solve the above formula:

[0137] (-sin(α)+p*cos(α+t)+sin(α+t+q), cos(α)+p*sin(α+t)

[0138] -cos(α+t+q), a+t+q) = (0, 0, d)

[0139] Continue to solve:

[0140]

[0141]

[0142]

[0143] Here, t is the driving distance of the vehicle turning left first; p is the driving distance of the straight driving; and q is the driving distance of the next left turn.

[0144] In the embodiments of the present disclosure, the driving direction of each mode in the multi-mode combination is determined through the current position information, and the driving distance of each mode in the multi-mode combination is determined based on the new heading coordinate, so that the space for solving is increased in some complex and extreme cases.

[0145] In some optional embodiments, as shown in Figure 2 Figure 2 is the overall flowchart of the vehicle driving path planning method according to some embodiments of the present disclosure, and the specific process is as follows:

[0146] Obtain the chassis information and the current vehicle speed information of the vehicle;

[0147] Determine whether it is in a blocked situation;

[0148] If it is in a blocked situation, enter the initial mode of the escape and detour; if it is not in a blocked situation, the vehicle continues to drive;

[0149] After entering the initial mode of the escape and detour, determine whether there is an escape and detour space;

[0150] If there is no escape and detour space, continue to wait; if there is an escape and detour space, select the end position in the escape and detour space and call the RRT algorithm to calculate and obtain the path;

[0151] Determine whether a suitable path is successfully obtained at present;

[0152] If a suitable path is obtained, the B-spline curve is used for optimization processing; then the subsequent path is executed; if a suitable path is not obtained, the method of generating a specific curve path library is executed to obtain the path; then the subsequent path is executed.

[0153] In the embodiments, a vehicle driving path planning device is also provided, which is used to implement the above embodiments and preferred embodiments, and details are not repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware, or a combination of software and hardware is also possible and is contemplated.

[0154] ​The embodiment provides a vehicle driving path planning device, which comprises: Figure 3

[0155] The first acquisition module 301 is configured to acquire a vehicle speed of a target vehicle, current position information of the target vehicle, surrounding perception information within a preset range of the current position information, and a preset space within the preset range and containing a target vehicle for escaping from a trouble;

[0156] The determination module 302 is configured to determine a mode state in which the target vehicle currently stays according to the vehicle speed, the current position information, the surrounding perception information, and the preset space;

[0157] The second acquisition module 303 is configured to acquire a target coordinate point at a target position within the preset space in a case where the mode state is a target mode state.

[0158] The update module 304 is configured to update a generated first random tree to obtain a target curve path according to the current position information, the target coordinate point, and any multiple coordinate points within the preset space, wherein the first random tree is generated by taking the current position information as a root node.

[0159] The setting module 305 is configured to take the target curve path as a final planning path or take a specific curve path composed of a multi-mode combination as the final planning path according to a comparison result of the target curve path and an optimal solution, wherein the multi-mode combination is determined according to the current position information, a current heading angle of the target vehicle, and a turning radius.

[0160] In some optional embodiments, the determination module 302 is specifically configured to determine that the mode state in which the target vehicle currently stays is the target mode state in a case where the vehicle speed is a preset value, a number of obstacles determined according to the surrounding perception information is less than a first preset threshold, and the preset space exists adjacent to the current position information.

[0161] In some optional embodiments, the update module 304 is specifically configured to acquire multiple coordinate points within the preset space; update the first random tree according to a containing relationship between the multiple coordinate points and an obstacle coverage range existing within the preset space and a position relationship between the current position information and the multiple coordinate points; determine a new node to be generated according to the updated first random tree; add the new node into the updated first random tree according to a containing relationship between the new node and the obstacle coverage range existing within the preset space until a distance between the new node and the target coordinate point is less than a second preset threshold, generate a second random tree, and take a connection line between all nodes contained in the second random tree as a planning path; and perform smoothing processing on the planning path to obtain the target curve path.

[0162] ​In some optional embodiments, the updating module 304 is specifically configured to: if the plurality of coordinate points are all contained in the obstacle coverage range, reselect the coordinate points in the preset space; if any reference coordinate point in the plurality of coordinate points is not contained in the obstacle coverage range, add the reference coordinate point to the first random tree to obtain the updated first random tree; or if the plurality of coordinate points are all not contained in the obstacle coverage range or a preset number of coordinate points are not contained in the obstacle coverage range, select a specific coordinate point closest to the current position information from the plurality of coordinate points or the preset number of coordinate points, and add the specific coordinate point to the first random tree to obtain the updated first random tree.

[0163] In some optional embodiments, the updating module 304 is specifically configured to: obtain a growth direction and a growth distance of the new node; and determine whether to add the new node into the updated first random tree according to the growth direction, the growth distance, and a containing relationship between the new node and the obstacle coverage range existing in the preset space; or add the new node into the updated first random tree when the growth direction meets a preset direction, the growth distance meets a preset distance, and the new node is not contained in the obstacle coverage range.

[0164] In some optional embodiments, the setting module 305 is specifically configured to: determine whether the target curve path is an optimal solution; or take the target curve path as the final planning path when the target curve path is the optimal solution; or obtain a current heading angle and a turning radius of the target vehicle when the target curve path is not the optimal solution; or determine a plurality of morphological combinations corresponding to the target vehicle and a driving direction and a driving distance of each morphological combination according to the current position information, the current heading angle, and the turning radius; or obtain a specific curve path according to the driving direction and the driving distance; or take the specific curve path as the final planning path.

[0165] In some optional embodiments, the setting module 305 is specifically configured to: determine the plurality of morphological combinations and the driving direction of each morphological combination according to the current position information and the current heading angle; or determine a new heading coordinate of the target vehicle according to the driving direction and the current position information and the turning radius; or determine the driving distance of each morphological combination according to the new heading coordinate.

[0166] The vehicle driving path planning apparatus in the embodiment is presented in the form of functional units, where the units refer to ASIC circuits, processors and memories executing one or more software or fixed programs, and / or other devices that can provide the above functions.

[0167] Further function descriptions of the above modules and units are the same as those of the above corresponding embodiments, which will not be described here.

[0168] The embodiment of the present disclosure further provides a computer device having the above Figure 3A vehicle travel path planning device.

[0169] Referring to Figure 4 , Figure 4 is a structural schematic diagram of a computer device provided by an optional embodiment of the present disclosure, as Figure 4 shown, the computer device includes one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are communicatively connected to each other by using different buses, and can be installed on a common motherboard or in other manners as needed. The processor can process instructions executed within the computer device, including instructions stored in the memory or graphics information of a GUI stored in the memory for displaying on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory, if necessary. Similarly, multiple computer devices can be connected, each providing part of the necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 4 In the embodiment, the processor 10 is taken as an example.

[0170] The processor 10 can be a central processor, a network processor, or a combination thereof. The processor 10 can further include a hardware chip. The hardware chip can be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device can be a complex programmable logic device, a field programmable logic gate array, a generic array logic, or any combination thereof.

[0171] The memory 20 stores instructions executable by the at least one processor 10, so that the at least one processor 10 executes the method shown in the above embodiments.

[0172] The memory 20 can include a program storage area and a data storage area. The program storage area can store an operating system and application programs required by at least one function; the data storage area can store data created by use of the computer device according to the display of a small program landing page, and the like. In addition, the memory 20 can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some optional embodiments, the memory 20 can optionally include a memory remotely arranged with respect to the processor 10, and these remote memories can be connected to the computer device by a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0173] The memory 20 can include a volatile memory, such as a random access memory, and / or can include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive. The memory 20 can also include a combination of the above-mentioned types of memory.

[0174] The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.

[0175] The embodiments of the present disclosure further provide a computer readable storage medium, and the method according to the embodiments of the present disclosure can be implemented in hardware, firmware, or recorded in a storage medium, or be implemented as computer code originally stored in a remote storage medium or non-transitory machine readable storage medium downloaded through a network and stored in a local storage medium, so that the method described herein can be processed by such software on a storage medium using a general purpose computer, a special purpose processor or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk or a solid state disk, etc. Further, the storage medium can also include a combination of the above-mentioned types of memory. It can be understood that the computer, processor, microprocessor controller or programmable hardware includes a storage component that can store or receive software or computer code, when the software or computer code is accessed and executed by the computer, processor or hardware, the method shown in the above embodiments is implemented.

[0176] Although the embodiments of the present disclosure are described in conjunction with the accompanying drawings, various modifications and changes can be made by those skilled in the art without departing from the spirit and scope of the present disclosure, and such modifications and changes fall within the scope defined by the appended claims.

Claims

1. A method of planning a travel path of a vehicle, characterized by, The method comprises: acquiring a vehicle speed of a target vehicle, current position information of the target vehicle, surrounding perception information within a preset range of the current position information, and a preset space within the preset range and available for the target vehicle to escape; determining a mode state in which the target vehicle currently stays according to the vehicle speed, the current position information, the surrounding perception information, and the preset space; in a case where the mode state is a target mode state, acquiring a target coordinate point at a target position within the preset space; generating a first random tree according to the current position information, the target coordinate point, and any plurality of coordinate points within the preset space, to obtain a target curve path, wherein the first random tree is generated with the current position information as a root node; according to a comparison result of the target curve path and an optimal solution, taking the target curve path as a final planning path or taking a specific curve path composed of a multi-mode combination as the final planning path, wherein the multi-mode combination is determined according to the current position information, a current heading angle of the target vehicle, and a turning radius; wherein, according to the comparison result of the target curve path and the optimal solution, taking the target curve path as the final planning path or taking the specific curve path composed of the multi-mode combination as the final planning path, comprises: determining whether the target curve path is the optimal solution; in a case where the target curve path is the optimal solution, taking the target curve path as the final planning path; in a case where the target curve path is not the optimal solution, acquiring the current heading angle of the target vehicle and the turning radius; determining the multi-mode combination corresponding to the target vehicle and a driving direction and a driving distance of each mode according to the current position information, the current heading angle, and the turning radius; obtaining the specific curve path according to the driving direction and the driving distance; taking the specific curve path as the final planning path.

2. The method of claim 1, wherein, According to the vehicle speed, the current position information, the surrounding perception information, and the preset space, determining the mode state in which the target vehicle currently stays, comprises: in a case where the vehicle speed is a preset value, the number of obstacles determined from the surrounding perception information is less than a first preset threshold, and the preset space exists adjacent to the current position information, determining that the mode state in which the target vehicle currently stays is the target mode state.

3. The method of claim 1, wherein, According to the current position information, the target coordinate point, and any plurality of coordinate points within the preset space, updating the generated first random tree to obtain a target curve path, comprises: acquiring a plurality of the coordinate points within the preset space; updating the first random tree according to a containing relationship between the plurality of the coordinate points and an obstacle coverage range within the preset space and a position relationship between the current position information and the plurality of the coordinate points; determining a new node to be generated according to the updated first random tree; adding the new node into the updated first random tree according to the inclusion relation between the new node and the coverage range of the obstacle existing in the preset space until the distance between the new node and the target coordinate point is less than a second preset threshold, generating a second random tree, and taking the connection between all nodes included in the second random tree as a planning path; performing smoothing processing on the planning path to obtain the target curve path.

4. The method of claim 3, wherein, The updating the first random tree according to the inclusion relation between the plurality of coordinate points and the coverage range of the obstacle existing in the preset space and the positional relation between the current position information and the plurality of coordinate points comprises: if all the plurality of coordinate points are included in the coverage range of the obstacle, selecting coordinate points in the preset space again; if any reference coordinate point in the plurality of coordinate points is not included in the coverage range of the obstacle, adding the reference coordinate point into the first random tree to obtain an updated first random tree; if all the plurality of coordinate points are not included in the coverage range of the obstacle or a preset number of coordinate points are not included in the coverage range of the obstacle, selecting a specific coordinate point closest to the current position information from the plurality of coordinate points or the preset number of coordinate points, and adding the specific coordinate point into the first random tree to obtain an updated first random tree.

5. The method of claim 3, wherein, The adding the new node into the updated first random tree according to the inclusion relation between the new node and the coverage range of the obstacle existing in the preset space comprises: obtaining a growth direction and a growth distance of the new node; determining whether to add the new node into the updated first random tree according to the growth direction, the growth distance and the inclusion relation between the new node and the coverage range of the obstacle existing in the preset space; if the growth direction meets a preset direction, the growth distance meets a preset distance, and the new node is not included in the coverage range of the obstacle, adding the new node into the updated first random tree.

6. The method of claim 1, wherein, The determining the multi-mode combination corresponding to the target vehicle and the driving direction and the driving distance of each mode according to the current position information, the current heading angle and the turning radius comprises: determining the multi-mode combination and the driving direction of each mode according to the current position information and the current heading angle; determining a new heading coordinate of the target vehicle according to the driving direction, the current position information and the turning radius; determining the driving distance of each mode according to the new heading coordinate.

7. A travel path planning device for a vehicle, characterized by comprising: The device comprises: a first obtaining module configured to obtain a vehicle speed of a target vehicle, current position information of the target vehicle, surrounding perception information within a preset range of the current position information, and a preset space included in the preset range and available for the target vehicle to escape from a trouble; a determining module configured to determine a mode state in which the target vehicle currently stays according to the vehicle speed, the current position information, the surrounding perception information and the preset space; The second acquisition module is configured to acquire a target coordinate point at a target position included in the preset space when the mode state is a target mode state. The update module is configured to update a generated first random tree according to the current position information, the target coordinate point, and any plurality of coordinate points in the preset space to obtain a target curve path, wherein the first random tree is generated with the current position information as a root node. The setting module is configured to determine the target curve path as a final planning path or a specific curve path composed of a multi-form combination according to a comparison result of the target curve path and an optimal solution, wherein the multi-form combination is determined according to the current position information, a current heading angle of the target vehicle, and a turning radius. The setting module is further configured to determine whether the target curve path is the optimal solution. When the target curve path is the optimal solution, the target curve path is determined as the final planning path. When the target curve path is not the optimal solution, the current heading angle of the target vehicle and the turning radius are acquired. According to the current position information, the current heading angle, and the turning radius, a multi-form combination corresponding to the target vehicle and a driving direction and a driving distance of each form are determined. According to the driving direction and the driving distance, the specific curve path is obtained. The specific curve path is determined as the final planning path.

8. A computer device, comprising: The memory and the processor are communicatively connected, and the memory stores computer instructions. The processor executes the computer instructions to perform the method for planning a vehicle driving path according to any one of claims 1 to 6. The computer readable storage medium stores computer instructions for causing a computer to perform the method for planning a vehicle driving path according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, ​

Images