Route planning method, device and equipment for articulated vehicle and storage medium

Abstract

The invention provides a path planning method and device for an articulated vehicle, equipment and a storage medium, and relates to the technical field of path planning. The method comprises the steps of obtaining an obstacle map of a driving scene where a target vehicle is located; wherein the target vehicle comprises a front vehicle body and a rear vehicle body which are connected in a hinged mode; based on the starting point and the terminal point, respectively performing path search on the obstacle map to obtain a first path search tree starting from the starting point and a second path search tree starting from the terminal point; and according to the first path search tree and the second path search tree, generating a target path from the starting point to the ending point for the target vehicle. The target path of the target vehicle can be generated by adopting the path search tree without sampling the action of the target vehicle, so that the efficiency of performing path planning on the target vehicle is improved.

Description

Technical Field

[0001] The present application relates to the technical field of path planning, and in particular to a path planning method, apparatus, device and storage medium for an articulated vehicle. Background Art

[0002] A loader is a type of engineering machinery that is widely used in the construction of various fields such as roads, mines, and railways. Automated loaders can complete operations independently without human intervention, thereby improving the operating efficiency of the loader.

[0003] The driving of automated loaders depends on path planning. Currently, a trained model is usually used to plan the loader's path, but the model needs to sample the loader's movements, which is time-consuming and highly complex. Summary of the Invention

[0004] In response to the above-mentioned deficiencies in the prior art, the present application provides a path planning method, device, equipment and storage medium for an articulated vehicle, so as to solve the problems existing in the prior art.

[0005] The technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, an embodiment of the present application provides a path planning method for an articulated vehicle, comprising:

[0007] Obtaining an obstacle map of a driving scene in which a target vehicle is located; wherein the target vehicle includes a front body and a rear body that are articulated;

[0008] Based on the starting point and the end point, path search is performed on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point;

[0009] A target path from the starting point to the end point for the target vehicle is generated based on the first path search tree and the second path search tree.

[0010] In a second aspect, an embodiment of the present application provides a path planning device for an articulated vehicle, comprising:

[0011] An acquisition module, configured to acquire an obstacle map of a driving scene in which a target vehicle is located; wherein the target vehicle includes a front body and a rear body that are articulated;

[0012] A search module is configured to perform path searches on the obstacle map based on a starting point and an end point, respectively, to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point;

[0013] A generating module is configured to generate a target path from the starting point to the end point for the target vehicle according to the first path search tree and the second path search tree.

[0014] In a third aspect, an embodiment of the present application provides a computer device comprising: a processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor. When the computer device is running, the processor and the storage medium communicate via the bus, and the processor executes the program instructions to implement the path planning method for an articulated vehicle described in any of the above embodiments.

[0015] In a fourth aspect, an embodiment of the present application provides a readable storage medium having program instructions stored thereon, and when the program instructions are executed by a processor, the path planning method for an articulated vehicle described in any of the above embodiments is implemented.

[0016] The beneficial effects of the present application are as follows: the present application provides a path planning method for an articulated vehicle, comprising obtaining an obstacle map of a driving scene in which a target vehicle is located; wherein the target vehicle comprises an articulated front body and a rear body; based on a starting point and an end point, a path search is performed on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point; based on the first path search tree and the second path search tree, a target path from the starting point to the end point is generated for the target vehicle.

[0017] Among them, the target path of the target vehicle can be generated by using the first path search tree and the second path search tree, without sampling the target vehicle's movements, thereby improving the efficiency of path planning for the target vehicle. In addition, the first path search tree and the second path search tree are generated from the starting point and the end point respectively, which improves the path search success rate in narrow driving scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without creative work.

[0019] Figure 1 This is a flow chart of a method for path planning for an articulated vehicle provided in one embodiment of the present application;

[0020] Figure 2 This is a second flow chart of a path planning method for an articulated vehicle provided in one embodiment of the present application;

[0021] Figure 3 A schematic diagram of the target path provided for this application;

[0022] Figure 4 This is a third flow chart of a path planning method for an articulated vehicle provided in one embodiment of the present application;

[0023] Figure 5 A fourth flowchart of a path planning method for an articulated vehicle provided in an embodiment of the present application;

[0024] Figure 6 This is a fifth flow chart of a path planning method for an articulated vehicle provided in one embodiment of the present application;

[0025] Figure 7 Flowchart 6 of the path planning method for an articulated vehicle provided in one embodiment of the present application;

[0026] Figure 8 FIG7 is a flowchart of a path planning method for an articulated vehicle provided in an embodiment of the present application;

[0027] Figure 9 One of the schematic diagrams of the connection path provided for this application;

[0028] Figure 10 FIG8 is a flow chart of a method for path planning of an articulated vehicle according to an embodiment of the present application;

[0029] Figure 11 The second schematic diagram of the connection path provided for this application;

[0030] Figure 12 A comparison diagram of the target path before and after optimization provided in this application;

[0031] Figure 13 9 is a flowchart of a path planning method for an articulated vehicle provided in one embodiment of the present application;

[0032] Figure 14 A schematic structural diagram of a path planning device for an articulated vehicle provided in one embodiment of the present application;

[0033] Figure 15 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments.

[0035] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for protection, but merely represents selected embodiments of the present application. All other embodiments obtained by persons of ordinary skill in the art based on the embodiments in the present application without creative work are within the scope of protection of the present application.

[0036] In the description of this application, it should be noted that if the terms "upper", "lower", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the accompanying drawings, or is the orientation or position relationship in which the product of the application is usually placed when in use. It is only for the convenience of describing this application and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on this application.

[0037] In addition, the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] It should be noted that, in the absence of conflict, the features in the embodiments of this application can be combined with each other.

[0039] An embodiment of the present application provides a path planning method for an articulated vehicle. The method can be generated by any computer device with computing and processing capabilities. The computer device can be, for example, a terminal-oriented computer device or a back-end server.

[0040] The path planning method for an articulated vehicle provided in this application is specifically described below through multiple examples in conjunction with the accompanying drawings.

[0041] Figure 1 This is a flow chart of a path planning method for an articulated vehicle provided in one embodiment of the present application, as shown in FIG. Figure 1 As shown, the method includes:

[0042] S101: Obtain an obstacle map of a driving scene where a target vehicle is located.

[0043] First, an obstacle map is created for the target vehicle's driving scenario. This map contains information about obstacles in the driving scenario and can be used for collision detection. Collision detection involves checking the obstacle map for obstacles along the path. The target vehicle consists of an articulated front and rear body, such as an articulated loader, excavator, bus, or other type of articulated vehicle.

[0044] S102 : Based on the starting point and the end point, perform path search on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point.

[0045] The obstacle map is pre-set with start and end points represented by icons (such as solid dots or other graphical symbols) based on the target vehicle's driving mission. For example, if the target vehicle is a loader and the loader's loading and unloading mission has a starting point at the shoveling point and an end point at the unloading point, the obstacle map generated based on the loader's driving scenario will include the starting point corresponding to the shoveling point and the end point corresponding to the unloading point.

[0046] Based on the starting point and the end point, the RRT* algorithm (Rapid-exploration RandomTree) is used to perform path search on the obstacle map, respectively, to obtain the first path search tree starting from the starting point and the second path search tree starting from the end point.

[0047] It should be noted that in addition to pre-setting the start and end points, the start and end points can also be determined after the target vehicle begins traveling, based on the target vehicle's current trajectory. For example, if the target vehicle begins moving from point A, and based on the target vehicle's current trajectory trend, it is calculated that the target vehicle's current driving goal is to travel from point A to point B, then the start point is determined to be point A and the end point is determined to be point B.

[0048] S103 : Generate a target path from the starting point to the end point for the target vehicle according to the first path search tree and the second path search tree.

[0049] After obtaining the first path search tree and the second path search tree, a target path from the starting point to the end point for the target vehicle can be generated according to the first path search tree and the second path search tree, thereby completing the path planning for the target vehicle.

[0050] Compared to only generating a search tree from the starting point to the end point, this embodiment generates a first path search tree and a second path search tree from the starting point and the end point respectively, which can improve the path search success rate, especially the path search success rate in narrow driving scenarios.

[0051] In summary, this embodiment provides a path planning method for an articulated vehicle, which uses a first path search tree and a second path search tree to generate a target path for a target vehicle without sampling the movements of the target vehicle, thereby improving the efficiency of path planning for the target vehicle. In addition, the first path search tree and the second path search tree are generated from the starting point and the end point respectively, thereby improving the path search success rate in narrow driving scenarios.

[0052] An embodiment of the present application provides a possible implementation method for generating a path search tree, such as Figure 2 As shown, S102 performs path search on the obstacle map based on the starting point and the end point, respectively, to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point, which may include:

[0053] S201 : Based on a starting point and an end point, search an obstacle map for a plurality of first extension paths from the starting point to a sampling point, and a plurality of second extension paths from the end point to the sampling point.

[0054] In this embodiment, a point is randomly sampled in the obstacle map, denoted as point P(x, y, θ), where x and y are the coordinates of point P in the obstacle map, and θ is the steering angle between the front and rear bodies of the target vehicle at point P.

[0055] like Figure 3 As shown, based on the starting point A and the end point B, multiple first extension paths from the starting point A to the sampling point P and multiple second extension paths from the end point B to the sampling point P are searched in the obstacle map.

[0056] S202 : Generate a first path search tree and a second path search tree based on the plurality of first extension paths and the plurality of second extension paths, respectively.

[0057] After obtaining multiple first extension paths and multiple second extension paths, a first path search tree can be formed based on the multiple first extension paths, and a second path search tree can be formed based on the multiple second extension paths. It can be understood that starting point A is the root of the first path search tree, and end point B is the root of the second path search tree.

[0058] In this embodiment, a sampling point P is randomly obtained in the obstacle map. Then, based on the position of point P, multiple first extension paths are searched from the starting point A to point P, and multiple second extension paths are searched from the end point B to point P. Then, based on the multiple first extension paths and the multiple second extension paths, a first path search tree and a second path search tree are generated, respectively.

[0059] In one embodiment, if Figure 4As shown, S201 searches for multiple first extension paths from the starting point to the sampling point and multiple second extension paths from the end point to the sampling point from the obstacle map based on the starting point and the end point, which may include:

[0060] S301 : Based on a starting point and an end point, a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point are respectively screened from an obstacle map.

[0061] When generating the first and second path search trees, unlike the RRT algorithm, which selects the node closest to the root in the obstacle map, the RRT* algorithm in this embodiment uses the characteristics of a double clothoid curve to filter the nodes in the obstacle map to obtain multiple first candidate nodes closest to the starting point and multiple second candidate nodes closest to the end point. This filtering removes invalid nodes (such as obstacle nodes or nodes that exceed the RRT* algorithm's extension step), thereby improving the efficiency and success rate of generating the first and second path search trees.

[0062] S302 : Based on the starting point and the end point, extend from the plurality of first candidate nodes and the plurality of second candidate nodes respectively to obtain a plurality of first extended paths and a plurality of second extended paths.

[0063] Specifically, a double clothoid curve is used to extend the starting point A to multiple first candidate nodes multiple times to obtain multiple first extension paths, and to extend the end point B to multiple second candidate nodes multiple times to obtain multiple second extension paths.

[0064] In actual operation, the extension can be performed alternately, that is, based on the starting point A, the extension is performed to a first candidate node to obtain a first extension path, and then based on the end point B, the extension is performed to a second candidate node to obtain a second extension path, and this is repeated multiple times to obtain multiple first extension paths and multiple second extension paths; or it can be performed based on the starting point A to multiple first candidate nodes multiple times to obtain multiple first extension paths, and then based on the end point B, the extension is performed to multiple second candidate nodes multiple times to obtain multiple second extension paths.

[0065] Among them, a double clothoid curve is a curve with zero curvature at both the starting point and the end point. The double clothoid curve is used for path extension, and then the target path is generated based on the first path search tree and the second path search tree obtained by extension. The curvature of the target path at both the starting point and the end point is zero. When tracking the target path, the target vehicle can return to the center position at the starting point and the end point, that is, the steering angle of the front and rear bodies is zero.

[0066] The double clothoid curve also ensures that the curvature of the generated target path increases linearly. This curvature corresponds to the target vehicle's turning angle when tracking the target path. This linear curvature reduces the need for large steering wheel adjustments and can meet the maximum turning radius constraints of articulated vehicles. The maximum turning radius of an articulated vehicle is limited by factors such as the maximum steering angle between the front and rear bodies and the wheelbase of the front and / or rear bodies.

[0067] In one embodiment, if Figure 5 As shown, S301 screens multiple first candidate nodes closest to the starting point and multiple second candidate nodes closest to the end point from the obstacle map based on the starting point and the end point, which may include:

[0068] S401: Construct a first coordinate system and a second coordinate system based on a starting point and an end point, respectively.

[0069] The first coordinate system is constructed with the starting point as the coordinate origin, which is recorded as coordinate system A, and the second coordinate system is constructed with the end point as the coordinate origin, which is recorded as coordinate system B.

[0070] S402 : Convert the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes.

[0071] Based on the vehicle steering angle corresponding to each node, the coordinates of all nodes in the obstacle map are converted from the map coordinate system W to the first coordinate system A, and the first coordinates of all nodes are obtained, which are recorded as (x1, y1, θ1); the coordinates of all nodes in the obstacle map are converted from the map coordinate system W to the second coordinate system B, and the second coordinates are obtained, which are recorded as (x2, y2, θ2).

[0072] S403 : Filter multiple first candidate nodes from the obstacle map based on the starting point and the first coordinates of all nodes.

[0073] According to the first coordinates of all nodes, multiple first candidate nodes closest to the starting point A are screened from the obstacle map.

[0074] S404: Filter multiple second candidate nodes from the obstacle map based on the end point and the second coordinates of all nodes.

[0075] According to the second coordinates of all nodes, multiple second candidate nodes closest to the end point B are screened from the obstacle map.

[0076] Then, S202 extends from the plurality of first candidate nodes and the plurality of second candidate nodes based on the starting point and the end point, respectively, to obtain a plurality of first extended paths and a plurality of second extended paths, which may include:

[0077] S405 : In the first coordinate system, extend from the starting point to the plurality of first candidate nodes to obtain a plurality of first extension paths.

[0078] After screening and obtaining multiple first candidate nodes closest to the starting point, the paths can be extended from the starting point to the multiple first candidate nodes in the first coordinate system A, and finally multiple first extension paths from the starting point to the sampling point are obtained, thereby obtaining a first path search tree composed of multiple first extension paths.

[0079] S406 : Extend from the end point to multiple second candidate nodes in the second coordinate system to obtain multiple second extended paths.

[0080] Similarly, after screening and obtaining multiple second candidate nodes closest to the end point, the path can be extended from the end point to the multiple second candidate nodes in the second coordinate system B, and finally multiple second extension paths from the end point to the sampling point are obtained, thereby obtaining a second path search tree composed of multiple second extension paths.

[0081] In this embodiment, based on the screened multiple first candidate nodes and multiple second candidate nodes, multiple first extended paths and multiple second extended paths are respectively extended from the starting point and the end point, thereby improving the efficiency and success rate of generating the first path search tree and the second path search tree.

[0082] It should be noted that before extending from the starting point to the multiple first candidate nodes, the coordinates of the sampling point P need to be converted to the first coordinate system. Similarly, before extending from the end point to the multiple second candidate nodes, the coordinates of the sampling point P need to be converted to the second coordinate system.

[0083] The following describes a possible implementation method for screening multiple first candidate nodes and multiple second candidate nodes with reference to specific examples:

[0084] S403 screening a plurality of first candidate nodes from the obstacle map based on the starting point and the first coordinates of all nodes may include:

[0085] According to the following first relationship, multiple first candidate nodes are screened from the obstacle map based on the starting point and the first coordinates of all nodes:

[0086]

[0087] Among them, x1 and y1 are used to represent the position of the node in the first coordinate system, and θ1 is used to represent the vehicle steering angle of the node of the target vehicle in the first coordinate system.

[0088] S404 screening multiple second candidate nodes from the obstacle map based on the end point and the second coordinates of all nodes may include:

[0089] According to the following second relationship, multiple second candidate nodes are screened from the obstacle map based on the end point and the second coordinates of all nodes:

[0090]

[0091] Among them, x2 and y2 are used to represent the position of the node in the second coordinate system, and θ2 is used to represent the vehicle steering angle of the node of the target vehicle in the second coordinate system.

[0092] In addition to obtaining multiple first candidate nodes after screening according to the above-mentioned first relationship formula and multiple second candidate nodes after screening according to the second relationship formula, it is also possible to directly obtain the node coordinates of the obstacle according to the obstacle map, and then delete the node coordinates of the obstacle in the obstacle map, and obtain multiple first candidate nodes and multiple second candidate nodes according to the coordinates of the remaining nodes.

[0093] In one embodiment, if Figure 6 As shown, after obtaining the first path search tree and the second path search tree, a method for generating a target path from a starting point to an end point for a target vehicle according to the first path search tree and the second path search tree may include:

[0094] S501: Determine multiple connected paths from a starting point to an end point according to a first path search tree and a second path search tree.

[0095] like Figure 3 As shown, since the intersection of the first path search tree and the second path search tree is the sampling point P, multiple connected paths from the start point to the end point can be generated among the multiple first extension paths constituting the first path search tree and the multiple second extension paths constituting the second path search tree.

[0096] S502 : According to the trajectory lengths of the multiple connected paths, determine a path with the shortest trajectory length from the multiple connected paths as a target path.

[0097] After obtaining multiple connected paths, in order to ensure that the target vehicle can complete the driving task at the fastest speed when tracking the target path, the path with the shortest trajectory length can be determined from the multiple connected paths as the target path.

[0098] In one embodiment, in order to ensure that the target path is collision-free (no obstacles on the path), as Figure 7 As shown, before determining the path with the shortest trajectory length from the multiple connected paths as the target path in S502 according to the trajectory lengths of the multiple connected paths, collision detection may be performed on the multiple connected paths:

[0099] S601: Perform collision detection on nodes on multiple connected paths to obtain multiple candidate connected paths without collision.

[0100] Each connected path consists of multiple nodes in the obstacle map. In the obstacle map, each node on each connected path is checked for obstacles. If there is an obstacle on at least one node in a connected path, the connected path is considered to have a collision. Collision detection is performed on the nodes on each connected path to obtain multiple collision-free connected paths as candidate connected paths.

[0101] Then, the method of determining the path with the shortest trajectory length from the multiple connected paths as the target path according to the trajectory lengths of the multiple connected paths in S502 may be:

[0102] S602 : Based on the trajectory lengths of the plurality of candidate connected paths, determine a path with the shortest trajectory length from the plurality of candidate connected paths as a target path.

[0103] The multiple candidate connected paths are all collision-free connected paths. The multiple candidate connected paths are sorted according to the trajectory length, and the path with the shortest trajectory length is determined as the target path from the multiple candidate connected paths.

[0104] In this embodiment, after collision detection is performed on multiple connected paths, multiple candidate connected paths without collision are sorted to obtain a target path. This ensures that before the target path is obtained based on the multiple candidate connected paths, there is no collision among the multiple candidate connected paths. This avoids the need to regenerate the target path due to collision after the target path has been generated, thereby ensuring the success rate of obtaining the target path.

[0105] Alternatively, multiple connected paths can be sorted by path length to determine the shortest path. This path is then checked for collisions. If no collisions are found, the shortest path is selected as the target path. If no collisions are found, collision checking is performed on the second shortest connected path in the sorted order, and so on until a collision-free and shortest connected path is determined among the multiple connected paths. This approach, by prioritizing sorting and then performing collision checking, can reduce the time spent on collision checking for unnecessary nodes in actual operation and speed up the acquisition of the target path.

[0106] When an articulated vehicle performs a driving task, its working route can usually be abstracted into a V-shaped path, that is, first retreating to the reversal point and then heading to the end point. Therefore, a reversal needs to be included in a path tracking. This application provides two possible implementation methods for generating a connected path under reversal conditions. The following is combined with Figures 8 to 11 Provide explanation.

[0107] like Figure 8 As shown, in one embodiment, S501 determines multiple connected paths from the start point to the end point based on the first path search tree and the second path search tree, which may include:

[0108] S701: If there is no path intersection between a first path in the first path search tree and a second path in the second path search tree, calculate a vehicle steering angle at any path endpoint based on the curvature of any path endpoint on the first path and the second path.

[0109] In some cases, such as Figure 9 As shown, the first path in the first path search tree and the second path on the second path search tree may not have a path intersection. In this case, the first path or the second path needs to be adjusted (for example, the adjustment can be as follows Figure 9 ), so that the first path and the second path intersect to obtain a connected path.

[0110] During this process, since the target vehicle is an articulated vehicle comprising a front body and a rear body, the directions of the front body and the rear body may be inconsistent during driving. In order to ensure that the connected path obtained after the intersection of the first path and the second path can make the directions of the front body and the rear body of the target vehicle consistent when changing direction, this embodiment calculates the vehicle steering angle at the path endpoint of the first path based on the curvature of the path endpoint of the first path, so that the steering angle of the target vehicle at the path endpoint is 0.

[0111] S702: Adjust the path where the path endpoint is located according to the vehicle steering angle so that the adjusted path intersects with another path to obtain a first connected path.

[0112] According to the vehicle steering angle, the path where the path endpoint is located is adjusted so that the adjusted path intersects with another path to obtain a first connected path. The target vehicle is controlled to track the trajectory according to the first connected path, which can ensure that the front and rear bodies of the target vehicle are in the same direction.

[0113] S703: If the third path in the first path search tree and the third path in the second path search tree intersect, directly connect the third path and the fourth path to generate a second connected path.

[0114] If the third path in the first path search tree and the third path in the second path search tree intersect, the third path and the fourth path are directly connected according to the intersection, and redundant paths are deleted to generate a second connected path.

[0115] The above embodiment can ensure that after switching forwards and backwards, the front body and the rear body of the target vehicle keep in the same direction as much as possible, and the extended straight line is shorter, which is suitable for the case where the driving scene of the target vehicle is smaller.

[0116] like Figure 10As shown, in one embodiment, before determining the path with the shortest trajectory length from the multiple connected paths as the target path based on the trajectory lengths of the multiple connected paths, the method of the present application may further include:

[0117] S801: Perform a reversal detection on the connection point on each connected path.

[0118] After obtaining multiple connected paths, a direction change detection is performed on a connection point on each connected path to determine whether the target vehicle needs to change direction when tracking the connected path. The connection point on each connected path may be a sampling point P.

[0119] S802: If it is detected that there is a vehicle turning demand at the connection point, extend a line of a preset length from the connection point.

[0120] like Figure 11 If a vehicle turning requirement is detected at the connection point, a line of a preset length is extended from the connection point ( Figure 11 ), so that the target vehicle can change direction by extending the lines.

[0121] S803 : Calculate the trajectory length of each connected path based on the trajectory length of each connected path and line.

[0122] Since the connected path is extended beyond the preset length of the line, the track length of the connected path is actually the sum of the track lengths of the connected path and the extended line.

[0123] This embodiment can ensure that the front and rear bodies of the target vehicle maintain the same direction as much as possible after switching forwards and backwards, and the extended straight line will occupy a certain space, which is suitable for situations where the driving scene of the target vehicle is large.

[0124] Since the RRT* algorithm is an asymptotically optimal algorithm, the target path obtained may be somewhat tortuous when computing resources are limited. Therefore, this application can optimize the target path based on the starting point and the end point, specifically including:

[0125] Based on the starting point and the end point, the target path is optimized respectively using a double clothoid curve. Specifically, after obtaining the target path according to the first path search tree and the second path search tree, the path starting point and the path end point are tried to be connected using a double clothoid curve. If the connection fails or an obstacle is detected in the target path after the connection, the point i that can be connected to the end point is traversed from the starting point to the end point. After the connection is successful, the point i is set as the end point, and attempts to connect the point i and the starting point are continued, and this process is repeated recursively until the connection is successful or all points fail to be connected.

[0126] like Figure 12As shown in the figure, the curvature changes frequently in path 1 before optimization, while the curvature changes smoothly in path 2 after optimization, which is more conducive to controlling the target vehicle to track the target path.

[0127] like Figure 13 As shown, in one embodiment, S101 obtains an obstacle map of the driving scene where the target vehicle is located, which may include:

[0128] S901: Acquire three-dimensional point cloud data of a driving scene.

[0129] The three-dimensional point cloud data of the driving scene can be obtained by sampling the driving scene through a point cloud acquisition device (such as radar, laser, etc.).

[0130] S902: Construct an obstacle map based on the three-dimensional point cloud data.

[0131] The three-dimensional point cloud data includes environmental point cloud data and obstacle point cloud data. A grid map is constructed based on the environmental point cloud data and the obstacle point cloud data. Then, the obstacle point cloud data is expanded in the grid map to obtain an obstacle map.

[0132] In summary, the embodiments of the present application provide a path planning method for an articulated vehicle, which has the following advantages:

[0133] 1. The target path of the target vehicle can be generated by using the first path search tree and the second path search tree, without sampling the target vehicle's movements, thereby improving the efficiency of path planning for the target vehicle.

[0134] 2. Extending from the starting and ending sampling points respectively, the first path search tree and the second path search tree are obtained, which can not only improve the path search success rate in narrow scenes, but also support the target vehicle to change direction once.

[0135] 3. The use of double clothoid curves for extension can ensure that the curvature increases linearly, ensuring that the direction angle is small when tracking the trajectory according to the target path, and the amplitude of controlling the steering wheel of the target vehicle does not need to be too large.

[0136] 4. Use double clothoid curves for extension to ensure that the curvature of the target path is 0 at the starting point and the end point, so that the target vehicle can return to the straight position at the beginning and end of the trajectory tracking.

[0137] 5. After obtaining the target path, optimizing the target path can avoid the tortuosity of the target path caused by insufficient search time, making the optimized target path more conducive to trajectory tracking of the target vehicle.

[0138] The following continues to explain the apparatus, device and storage medium for executing the path planning method for an articulated vehicle provided in any of the above embodiments of the present application. The specific implementation process and the technical effects produced are the same as those of the corresponding method embodiments mentioned above. For the sake of brief description, for the parts not mentioned in the following embodiments, please refer to the corresponding content in the method embodiments.

[0139] Figure 14 This is a schematic diagram of the structure of a path planning device for an articulated vehicle provided in one embodiment of the present application, as shown in FIG. Figure 14 As shown, an embodiment of the present application provides a path planning device for an articulated vehicle, comprising:

[0140] The acquisition module 10 is used to acquire an obstacle map of a driving scene in which a target vehicle is located; wherein the target vehicle includes a front body and a rear body that are articulated.

[0141] The search module 20 is configured to perform path searches on the obstacle map based on the starting point and the end point, respectively, to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point.

[0142] The generating module 30 is configured to generate a target path from a starting point to an end point for a target vehicle according to the first path search tree and the second path search tree.

[0143] Optionally, the search module 20 is used to search for multiple first extension paths from the starting point to the sampling point and multiple second extension paths from the end point to the sampling point in the obstacle map based on the starting point and the end point; and generate a first path search tree and a second path search tree based on the multiple first extension paths and the multiple second extension paths, respectively.

[0144] Optionally, the search module 20 is used to screen, based on the starting point and the end point, multiple first candidate nodes closest to the starting point and multiple second candidate nodes closest to the end point in the obstacle map; based on the starting point and the end point, extend from the multiple first candidate nodes and the multiple second candidate nodes respectively to obtain multiple first extended paths and multiple second extended paths.

[0145] Optionally, the search module 20 is used to construct a first coordinate system and a second coordinate system based on the starting point and the end point, respectively; convert the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes; based on the starting point and the first coordinates of all nodes, screen multiple first candidate nodes from the obstacle map; based on the end point and the second coordinates of all nodes, screen multiple second candidate nodes from the obstacle map; in the first coordinate system, extend from the starting point to the multiple first candidate nodes to obtain multiple first extension paths; in the second coordinate system, extend from the end point to the multiple second candidate nodes to obtain multiple second extension paths.

[0146] Optionally, the search module 20 is used to convert the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system respectively based on the vehicle steering angle corresponding to each node, so as to obtain the first coordinates and the second coordinates of all nodes; wherein the vehicle steering angle is the angle between the front body and the rear body of the target vehicle.

[0147] Optionally, the search module 20 is configured to screen a plurality of first candidate nodes from the obstacle map based on the starting point and the first coordinates of all nodes according to the following first relationship:

[0148]

[0149] Among them, x1 and y1 are used to represent the position of the node in the first coordinate system, and θ1 is used to represent the vehicle steering angle of the node of the target vehicle in the first coordinate system.

[0150] Optionally, the search module 20 is configured to screen a plurality of second candidate nodes from the obstacle map based on the second coordinates of the end point and all nodes according to the following second relationship:

[0151]

[0152] Among them, x2 and y2 are used to represent the position of the node in the second coordinate system, and θ2 is used to represent the vehicle steering angle of the node of the target vehicle in the second coordinate system.

[0153] Optionally, the search module 20 is configured to extend the path to the plurality of first candidate nodes and the plurality of second candidate nodes respectively using a double clothoid curve based on the starting point and the end point, so as to obtain a plurality of first extension paths and a plurality of second extension paths.

[0154] Optionally, the generation module 30 is configured to determine multiple connected paths from the start point to the end point based on the first path search tree and the second path search tree; and determine, based on the trajectory lengths of the multiple connected paths, a path with the shortest trajectory length as the target path from the multiple connected paths.

[0155] Optionally, the generation module 30 is configured to perform collision detection on nodes on multiple connected paths to obtain multiple collision-free candidate connected paths; and based on the trajectory lengths of the multiple candidate connected paths, determine the path with the shortest trajectory length from the multiple candidate connected paths as the target path.

[0156] Optionally, the generation module 30 is configured to calculate a vehicle steering angle at a path endpoint based on the curvature of any path endpoint on the first path and the second path if there is no path intersection between the first path in the first path search tree and the second path on the second path search tree; adjust the path at the path endpoint according to the vehicle steering angle so that the adjusted path intersects with the other path to obtain a first connected path; and directly connect the third path and the fourth path to generate a second connected path if there is a path intersection between the third path in the first path search tree and the third path on the second path search tree.

[0157] Optionally, the generation module 30 is used to perform reversal detection on the connection point on each connected path; if a vehicle reversal requirement is detected at the connection point, a line of a preset length is extended from the connection point; and based on the trajectory length of each connected path and the line, the trajectory length of each connected path is calculated.

[0158] Optionally, the path planning device for the articulated vehicle may further include an optimization module for optimizing the target path based on the starting point and the end point.

[0159] Optionally, the optimization module is used to optimize the target path using double clothoid curves based on the starting point and the end point.

[0160] Optionally, the acquisition module 10 is configured to acquire three-dimensional point cloud data of the driving scene; and construct an obstacle map based on the three-dimensional point cloud data.

[0161] Optionally, the three-dimensional point cloud data includes: environmental point cloud data and obstacle point cloud data; the acquisition module 10 is used to construct a grid map based on the environmental point cloud data and the obstacle point cloud data; in the grid map, the obstacle point cloud data is expanded to obtain an obstacle map.

[0162] The above-mentioned device is used to execute the method provided in the above-mentioned embodiment. Its implementation principle and technical effect are similar and will not be repeated here.

[0163] The above modules can be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), one or more microprocessors, or one or more field programmable gate arrays (FPGAs). For another example, when a module is implemented by scheduling program code through a processing element, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call program code. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0164] Figure 15 A schematic diagram of the structure of a computer device provided in one embodiment of the present application is shown in FIG. Figure 15 As shown, an embodiment of the present application provides a computer device, including: a processor 100, a storage medium 200 and a bus 300, and the processor and the storage medium communicate through the bus.

[0165] The storage medium stores program instructions executable by the processor. When the computer device is running, the processor executes the program instructions. The implementation method includes:

[0166] Obtaining an obstacle map of a driving scene in which a target vehicle is located; wherein the target vehicle includes an articulated front body and a rear body;

[0167] Based on the starting point and the end point, a path search is performed on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point;

[0168] A target path from a starting point to an end point for the target vehicle is generated according to the first path search tree and the second path search tree.

[0169] Optionally, based on the starting point and the end point, a path search is performed on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point, including:

[0170] Based on the starting point and the end point, searching the obstacle map for a plurality of first extension paths from the starting point to the sampling point, and a plurality of second extension paths from the end point to the sampling point;

[0171] Based on the plurality of first extension paths and the plurality of second extension paths, a first path search tree and a second path search tree are generated respectively.

[0172] Optionally, based on the starting point and the end point, searching the obstacle map for a plurality of first extension paths from the starting point to the sampling point, and a plurality of second extension paths from the end point to the sampling point, includes:

[0173] Based on the starting point and the end point, a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point are respectively screened in the obstacle map;

[0174] Based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths.

[0175] Optionally, based on the starting point and the end point, a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point are screened in the obstacle map, including:

[0176] Based on the starting point and the end point, a first coordinate system and a second coordinate system are constructed respectively;

[0177] Convert the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes;

[0178] Based on the starting point and the first coordinates of all nodes, screening multiple first candidate nodes from the obstacle map;

[0179] Based on the end point and the second coordinates of all nodes, screening multiple second candidate nodes from the obstacle map;

[0180] Based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths, including:

[0181] In the first coordinate system, extending from the starting point to the plurality of first candidate nodes to obtain a plurality of first extension paths;

[0182] In the second coordinate system, multiple second extended paths are obtained by extending from the end point to the multiple second candidate nodes.

[0183] Optionally, the coordinates of all nodes in the obstacle map are converted from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes, including:

[0184] Based on the vehicle steering angle corresponding to each node, the coordinates of all nodes in the obstacle map are converted from the map coordinate system to the first coordinate system and the second coordinate system, respectively, to obtain the first coordinates and the second coordinates of all nodes; where the vehicle steering angle is the angle between the front and rear bodies of the target vehicle.

[0185] Optionally, based on the starting point and the first coordinates of all nodes, a plurality of first candidate nodes are screened from the obstacle map, including:

[0186] According to the following first relationship, multiple first candidate nodes are screened from the obstacle map based on the starting point and the first coordinates of all nodes:

[0187]

[0188] Among them, x1 and y1 are used to represent the position of the node in the first coordinate system, and θ1 is used to represent the vehicle steering angle of the node of the target vehicle in the first coordinate system.

[0189] Optionally, based on the end point and the second coordinates of all nodes, multiple second candidate nodes are screened from the obstacle map, including:

[0190] According to the following second relationship, multiple second candidate nodes are screened from the obstacle map based on the end point and the second coordinates of all nodes:

[0191]

[0192] Among them, x2 and y2 are used to represent the position of the node in the second coordinate system, and θ2 is used to represent the vehicle steering angle of the node of the target vehicle in the second coordinate system.

[0193] Optionally, based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths, including:

[0194] Based on the starting point and the end point, a double clothoid curve is used to extend to the multiple first candidate nodes and the multiple second candidate nodes respectively, to obtain multiple first extension paths and multiple second extension paths.

[0195] Optionally, generating a target path from a starting point to an end point for a target vehicle according to the first path search tree and the second path search tree includes:

[0196] Determine multiple connected paths from a starting point to an end point according to the first path search tree and the second path search tree;

[0197] According to the trajectory lengths of the multiple connected paths, a path with the shortest trajectory length is determined from the multiple connected paths as the target path.

[0198] Optionally, before determining the path with the shortest trajectory length from the multiple connected paths as the target path based on the trajectory lengths of the multiple connected paths, the method further includes:

[0199] Perform collision detection on nodes on multiple connected paths to obtain multiple candidate connected paths without collision;

[0200] According to the trajectory lengths of multiple connected paths, the path with the shortest trajectory length is determined as the target path from the multiple connected paths, including:

[0201] Based on the trajectory lengths of the multiple candidate connected paths, a path with the shortest trajectory length is determined from the multiple candidate connected paths as the target path.

[0202] Optionally, determining multiple connected paths from the start point to the end point according to the first path search tree and the second path search tree includes:

[0203] If there is no path intersection between the first path in the first path search tree and the second path on the second path search tree, calculating a vehicle steering angle at a path endpoint based on a curvature of any path endpoint on the first path and the second path;

[0204] Adjusting the path where the path endpoint is located according to the vehicle steering angle so that the adjusted path intersects with another path to obtain a first connected path;

[0205] If the third path in the first path search tree and the third path in the second path search tree intersect, the third path and the fourth path are directly connected to generate a second connected path.

[0206] Optionally, before determining the path with the shortest trajectory length from the multiple connected paths as the target path based on the trajectory lengths of the multiple connected paths, the method further includes:

[0207] Perform reversal detection on the connection points on each connected path;

[0208] If a vehicle turning requirement is detected at the connection point, a line of a preset length is extended from the connection point;

[0209] Based on the trajectory lengths of each connected path and line, the trajectory length of each connected path is calculated.

[0210] Optionally, the method further comprises:

[0211] Optimize the target path based on the starting point and the end point.

[0212] Optionally, the target path is optimized based on the starting point and the end point, including:

[0213] Based on the starting point and the end point, double clothoid curves are used to optimize the target path.

[0214] Optionally, obtaining an obstacle map of the driving scene where the target vehicle is located includes:

[0215] Obtain three-dimensional point cloud data of the driving scene;

[0216] Build obstacle maps based on 3D point cloud data.

[0217] Optionally, the three-dimensional point cloud data includes: environmental point cloud data and obstacle point cloud data;

[0218] Based on 3D point cloud data, an obstacle map is constructed, including:

[0219] Construct a raster map based on the environment point cloud data and obstacle point cloud data.

[0220] In the grid map, the obstacle point cloud data is expanded to obtain the obstacle map.

[0221] An embodiment of the present application further provides a readable storage medium, wherein the readable storage medium stores program instructions. When the program instructions are executed by a processor, a method implemented includes:

[0222] Obtaining an obstacle map of a driving scene in which a target vehicle is located; wherein the target vehicle includes an articulated front body and a rear body;

[0223] Based on the starting point and the end point, a path search is performed on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point;

[0224] A target path from a starting point to an end point for the target vehicle is generated according to the first path search tree and the second path search tree.

[0225] Optionally, based on the starting point and the end point, a path search is performed on the obstacle map respectively to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point, including:

[0226] Based on the starting point and the end point, searching the obstacle map for a plurality of first extension paths from the starting point to the sampling point, and a plurality of second extension paths from the end point to the sampling point;

[0227] Based on the plurality of first extension paths and the plurality of second extension paths, a first path search tree and a second path search tree are generated respectively.

[0228] Optionally, based on the starting point and the end point, searching the obstacle map for a plurality of first extension paths from the starting point to the sampling point, and a plurality of second extension paths from the end point to the sampling point, includes:

[0229] Based on the starting point and the end point, a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point are respectively screened in the obstacle map;

[0230] Based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths.

[0231] Optionally, based on the starting point and the end point, a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point are screened in the obstacle map, including:

[0232] Based on the starting point and the end point, a first coordinate system and a second coordinate system are constructed respectively;

[0233] Convert the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes;

[0234] Based on the starting point and the first coordinates of all nodes, screening multiple first candidate nodes from the obstacle map;

[0235] Based on the end point and the second coordinates of all nodes, screening multiple second candidate nodes from the obstacle map;

[0236] Based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths, including:

[0237] In the first coordinate system, extending from the starting point to the plurality of first candidate nodes to obtain a plurality of first extension paths;

[0238] In the second coordinate system, multiple second extended paths are obtained by extending from the end point to the multiple second candidate nodes.

[0239] Optionally, the coordinates of all nodes in the obstacle map are converted from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes, including:

[0240] Based on the vehicle steering angle corresponding to each node, the coordinates of all nodes in the obstacle map are converted from the map coordinate system to the first coordinate system and the second coordinate system, respectively, to obtain the first coordinates and the second coordinates of all nodes; where the vehicle steering angle is the angle between the front and rear bodies of the target vehicle.

[0241] Optionally, based on the starting point and the first coordinates of all nodes, a plurality of first candidate nodes are screened from the obstacle map, including:

[0242] According to the following first relationship, multiple first candidate nodes are screened from the obstacle map based on the starting point and the first coordinates of all nodes:

[0243]

[0244] Among them, x1 and y1 are used to represent the position of the node in the first coordinate system, and θ1 is used to represent the vehicle steering angle of the node of the target vehicle in the first coordinate system.

[0245] Optionally, based on the end point and the second coordinates of all nodes, multiple second candidate nodes are screened from the obstacle map, including:

[0246] According to the following second relationship, multiple second candidate nodes are screened from the obstacle map based on the end point and the second coordinates of all nodes:

[0247]

[0248] Among them, x2 and y2 are used to represent the position of the node in the second coordinate system, and θ2 is used to represent the vehicle steering angle of the node of the target vehicle in the second coordinate system.

[0249] Optionally, based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths, including:

[0250] Based on the starting point and the end point, a double clothoid curve is used to extend to the multiple first candidate nodes and the multiple second candidate nodes respectively, to obtain multiple first extension paths and multiple second extension paths.

[0251] Optionally, generating a target path from a starting point to an end point for a target vehicle according to the first path search tree and the second path search tree includes:

[0252] Determine multiple connected paths from a starting point to an end point according to the first path search tree and the second path search tree;

[0253] According to the trajectory lengths of the multiple connected paths, a path with the shortest trajectory length is determined from the multiple connected paths as the target path.

[0254] Optionally, before determining the path with the shortest trajectory length from the multiple connected paths as the target path based on the trajectory lengths of the multiple connected paths, the method further includes:

[0255] Perform collision detection on nodes on multiple connected paths to obtain multiple candidate connected paths without collision;

[0256] According to the trajectory lengths of multiple connected paths, the path with the shortest trajectory length is determined as the target path from the multiple connected paths, including:

[0257] Based on the trajectory lengths of the multiple candidate connected paths, a path with the shortest trajectory length is determined from the multiple candidate connected paths as the target path.

[0258] Optionally, determining multiple connected paths from the start point to the end point according to the first path search tree and the second path search tree includes:

[0259] If there is no path intersection between the first path in the first path search tree and the second path on the second path search tree, calculating a vehicle steering angle at a path endpoint based on a curvature of any path endpoint on the first path and the second path;

[0260] Adjusting the path where the path endpoint is located according to the vehicle steering angle so that the adjusted path intersects with another path to obtain a first connected path;

[0261] If the third path in the first path search tree and the third path in the second path search tree intersect, the third path and the fourth path are directly connected to generate a second connected path.

[0262] Optionally, before determining the path with the shortest trajectory length from the multiple connected paths as the target path based on the trajectory lengths of the multiple connected paths, the method further includes:

[0263] Perform reversal detection on the connection points on each connected path;

[0264] If a vehicle turning requirement is detected at the connection point, a line of a preset length is extended from the connection point;

[0265] Based on the trajectory lengths of each connected path and line, the trajectory length of each connected path is calculated.

[0266] Optionally, the method further comprises:

[0267] Optimize the target path based on the starting point and the end point.

[0268] Optionally, the target path is optimized based on the starting point and the end point, including:

[0269] Based on the starting point and the end point, double clothoid curves are used to optimize the target path.

[0270] Optionally, obtaining an obstacle map of the driving scene where the target vehicle is located includes:

[0271] Obtain three-dimensional point cloud data of the driving scene;

[0272] Build obstacle maps based on 3D point cloud data.

[0273] Optionally, the three-dimensional point cloud data includes: environmental point cloud data and obstacle point cloud data;

[0274] Based on 3D point cloud data, an obstacle map is constructed, including:

[0275] Construct a raster map based on the environment point cloud data and obstacle point cloud data.

[0276] In the grid map, the obstacle point cloud data is expanded to obtain the obstacle map.

[0277] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0278] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0279] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0280] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) or a processor (English: processor) to perform some steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (English: Read-Only Memory, abbreviated: ROM), a random access memory (English: Random Access Memory, abbreviated: RAM), a disk or an optical disk, and other media that can store program code.

[0281] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A path planning method for an articulated vehicle, characterized in that: include: Obtaining an obstacle map of a driving scene where a target vehicle is located; wherein the target vehicle includes a front body and a rear body that are articulated; Based on a starting point and an end point, respectively, a path search is performed on the obstacle map to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point; A target path from the starting point to the end point for the target vehicle is generated based on the first path search tree and the second path search tree.

2. The method according to claim 1, characterized in that The method of performing path search on the obstacle map based on the starting point and the end point, respectively, to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point, comprises: Based on the starting point and the end point, searching the obstacle map for a plurality of first extension paths from the starting point to the sampling point, and a plurality of second extension paths from the end point to the sampling point; The first path search tree and the second path search tree are generated based on the plurality of the first extension paths and the plurality of the second extension paths, respectively.

3. The method according to claim 2, characterized in that The step of searching, based on the starting point and the end point, a plurality of first extension paths from the starting point to the sampling point and a plurality of second extension paths from the end point to the sampling point in the obstacle map comprises: Based on the starting point and the end point, respectively screening a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point in the obstacle map; Based on the starting point and the end point, multiple first candidate nodes and multiple second candidate nodes are extended respectively to obtain multiple first extended paths and multiple second extended paths.

4. The method according to claim 3, characterized in that The method of screening, based on the starting point and the end point, a plurality of first candidate nodes closest to the starting point and a plurality of second candidate nodes closest to the end point in the obstacle map respectively includes: Based on the starting point and the end point, construct a first coordinate system and a second coordinate system respectively; Converting the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes; Based on the starting point and the first coordinates of all the nodes, screening a plurality of the first candidate nodes from the obstacle map; Based on the end point and the second coordinates of all the nodes, screening a plurality of the second candidate nodes from the obstacle map; The step of extending from the plurality of first candidate nodes and the plurality of second candidate nodes based on the starting point and the end point to obtain a plurality of first extended paths and a plurality of second extended paths includes: In the first coordinate system, extending from the starting point to the plurality of first candidate nodes to obtain a plurality of first extension paths; In the second coordinate system, the path is extended from the end point to the plurality of second candidate nodes to obtain a plurality of second extended paths.

5. The method according to claim 4, characterized in that The step of converting the coordinates of all nodes in the obstacle map from the map coordinate system to the first coordinate system and the second coordinate system to obtain the first coordinates and the second coordinates of all nodes includes: Based on the vehicle steering angle corresponding to each node, the coordinates of all nodes in the obstacle map are converted from the map coordinate system to the first coordinate system and the second coordinate system respectively to obtain the first coordinates and the second coordinates of all nodes; wherein the vehicle steering angle is the angle between the front body and the rear body of the target vehicle.

6. The method according to claim 5, characterized in that The step of selecting a plurality of the first candidate nodes from the obstacle map based on the starting point and the first coordinates of all the nodes includes: According to the following first relationship, a plurality of the first candidate nodes are screened from the obstacle map based on the starting point and the first coordinates of all the nodes: Among them, x1 and y1 are used to represent the position of the node in the first coordinate system, and θ1 is used to represent the vehicle steering angle of the node of the target vehicle in the first coordinate system.

7. The method according to claim 5, characterized in that The step of selecting a plurality of second candidate nodes from the obstacle map based on the end point and the second coordinates of all the nodes includes: According to the following second relational expression, a plurality of second candidate nodes are screened from the obstacle map based on the end point and the second coordinates of all the nodes: Among them, x2 and y2 are used to represent the position of the node in the second coordinate system, and θ2 is used to represent the vehicle steering angle of the node of the target vehicle in the second coordinate system.

8. The method according to claim 3, characterized in that The step of extending the plurality of first candidate nodes and the plurality of second candidate nodes based on the starting point and the end point to obtain the plurality of first extended paths and the plurality of second extended paths includes: Based on the starting point and the end point, a double clothoid curve is used to extend to the first candidate nodes and the second candidate nodes respectively, so as to obtain the first extension paths and the second extension paths.

9. The method according to claim 1, characterized in that: The step of generating a target path from the starting point to the end point for the target vehicle according to the first path search tree and the second path search tree comprises: Determine a plurality of connected paths from the starting point to the end point according to the first path search tree and the second path search tree; According to the trajectory lengths of the plurality of connected paths, a path with the shortest trajectory length is determined from the plurality of connected paths as the target path.

10. The method according to claim 9, characterized in that Before determining, according to the trajectory lengths of the plurality of connected paths, a path with the shortest trajectory length from the plurality of connected paths as the target path, the method further includes: Performing collision detection on nodes on the plurality of connected paths to obtain a plurality of candidate connected paths without collision; The step of determining, according to the trajectory lengths of the plurality of connected paths, a path with the shortest trajectory length from the plurality of connected paths as the target path comprises: Based on the trajectory lengths of the plurality of candidate connected paths, a path with the shortest trajectory length is determined from the plurality of candidate connected paths as the target path.

11. The method according to claim 9, characterized in that The step of determining a plurality of connected paths from the starting point to the end point according to the first path search tree and the second path search tree comprises: If there is no path intersection between the first path in the first path search tree and the second path in the second path search tree, calculating the vehicle steering angle at the path endpoint based on the curvature of any path endpoint on the first path and the second path; According to the steering angle of the vehicle, the path where the path endpoint is located is adjusted so that the adjusted path intersects with another path to obtain a first connected path; If the third path in the first path search tree and the third path in the second path search tree intersect, the third path and the fourth path are directly connected to generate a second connected path.

12. The method according to claim 11, characterized in that Before determining, according to the trajectory lengths of the plurality of connected paths, a path with the shortest trajectory length from the plurality of connected paths as the target path, the method further includes: Performing reversal detection on the connection points on each connected path; If it is detected that there is a vehicle turning demand at the connection point, a line of length is extended from the connection point; Based on each of the communication paths and the trajectory length of the line, the trajectory length of each of the communication paths is calculated.

13. The method according to claim 1, characterized in that The method further comprises: The target path is optimized based on the starting point and the end point.

14. The method according to claim 13, characterized in that The optimizing the target path based on the starting point and the end point includes: Based on the starting point and the end point, the target path is optimized using double clothoid curves respectively.

15. The method according to claim 1, characterized in that The step of obtaining an obstacle map of a driving scene where the target vehicle is located includes: Acquiring three-dimensional point cloud data of the driving scene; The obstacle map is constructed based on the three-dimensional point cloud data.

16. The method according to claim 15, characterized in that The three-dimensional point cloud data includes: environmental point cloud data and obstacle point cloud data; The step of constructing the obstacle map based on the three-dimensional point cloud data includes: Constructing a grid map according to the environment point cloud data and the obstacle point cloud data; In the grid map, the obstacle point cloud data is expanded to obtain the obstacle map.

17. A path planning device for an articulated vehicle, characterized in that: include: An acquisition module, used to acquire an obstacle map of a driving scene where a target vehicle is located; wherein the target vehicle includes a front body and a rear body that are articulated; A search module, configured to perform path search on the obstacle map based on a starting point and an end point, respectively, to obtain a first path search tree starting from the starting point and a second path search tree starting from the end point; A generating module is used to generate a target path from the starting point to the end point for the target vehicle according to the first path search tree and the second path search tree.

18. A computer device, characterized in that: include: A processor, a storage medium and a bus, wherein the storage medium stores program instructions executable by the processor, and when the computer device is running, the processor and the storage medium communicate via the bus, and the processor executes the program instructions to implement the path planning method for an articulated vehicle as described in any one of claims 1 to 16.

19. A readable storage medium, characterized in that: The readable storage medium stores program instructions, and the program instructions, when executed by a processor, implement the path planning method for an articulated vehicle according to any one of claims 1 to 16.

Images