Multi-vehicle path planning method, device, equipment, storage medium and system

Abstract

The present invention belongs to the field of intelligent driving technology, and discloses a multi-vehicle path planning method, device, equipment, storage medium and system. According to the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle, all paths from the starting point to the end point of each vehicle are obtained, and the focused path from the starting point to the end point of each vehicle is obtained by a focused search method; according to the focused path from the starting point to the end point of each vehicle, the focused path from the starting point to the end point of each vehicle is formed into a tree root diagram from the starting point to the end point, and the end point is searched from the starting point according to the tree root diagram of each vehicle. During the search process, according to a preset node selection method, nodes are selected from the open node set, the clear node set and the focused node set as extension nodes, and the path is extended according to the preset constraint restriction conditions, and the path with the least number of conflicts between each vehicle and other vehicles is selected as the planning path of each vehicle. The multi-vehicle path planning speed is improved and conflicts between multiple vehicles are avoided.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent driving technology and relates to a multi-vehicle path planning method, device, equipment, storage medium and system. Background Art

[0002] Path planning refers to finding a fault-free path from the starting point to the end point according to certain evaluation criteria in an environment with faults. It is mainly used in the field of autonomous driving. However, as the environment becomes more and more complex, path planning is no longer just about planning a reasonable path for a single vehicle. The problem of multi-vehicle path planning needs to be solved urgently, so the evaluation standards for path planning are getting higher and higher.

[0003] The core problem of multi-vehicle path planning is to solve path conflicts. There are many ways to solve path conflicts. Among them, the commonly used methods to solve path conflicts generally include the following two. The first is a conflict-based path planning method. The implementation process of this method is to find a node that satisfies the constraints of the constraint tree and has the lowest cost. First, it is determined whether the node has a conflict. If there is no conflict, the node is the target node. Otherwise, the node is divided into two, and then additional constraints are set for the generated child nodes, that is, one of the child nodes is set to wait at the time of the conflict or plan other paths for it. This method uses the node with the lowest cost for expansion each time, and the search is relatively blind, resulting in a slow search speed. The second is a conflict path planning method based on parallelism. This method considers that the node with the lowest cost in the constraint tree is not the optimal node. At the same time, a multi-threading method is used to speed up the search speed in the process of node splitting and expansion. However, the use of multi-threading cannot guarantee expansion from the node with the lowest cost, so the suboptimal solution is obtained. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the above-mentioned prior art of slow multi-vehicle path planning and inaccurate results, and to provide a multi-vehicle path planning method, device, equipment, storage medium and system.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] In a first aspect of the present invention, a multi-vehicle path planning method comprises:

[0007] Obtain the road condition information of the multi-vehicle route planning area and the starting and ending point information of each vehicle;

[0008] According to the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle, all paths from the starting point to the end point of each vehicle are obtained, and the focused path from the starting point to the end point of each vehicle is obtained by using a focused search method;

[0009] According to the focused paths from the starting point to the end point of each vehicle, the focused paths from the starting point to the end point of each vehicle are combined into a tree root graph from the starting point to the end point, and the nodes of the tree root graph are the path points that may overlap in the paths of multiple vehicles;

[0010] Obtain the nodes in the tree root graph that can generate child nodes to obtain the open node set, and use the focused search method to take out some nodes from the open node set to form a focused node set, set the clear node set, and transfer the expanded nodes in the open node set to the clear node set;

[0011] According to the tree root graph of each vehicle, the search for the end point starts from the starting point. During the search process, according to the preset node selection method, nodes are selected from the open node set, the clear node set and the focused node set as expansion nodes, and the path is expanded according to the preset constraint conditions, and the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path for each vehicle.

[0012] Optionally, the method of obtaining the focused path from the starting point to the end point of each vehicle by using the focused search method includes: selecting from all the paths from the starting point to the end point of each vehicle a path that satisfies f(n)≤w*f(best f ) path, and obtain the focused path from the starting point to the end point of each vehicle; where f(n) = g(n) + h(n), f(n) represents the total cost of the path, g(n) represents the cost from the starting point to the intermediate point, h(n) represents the cost from the intermediate point to the end point, and the intermediate point is an arbitrarily selected path point in the path from the starting point to the end point; w>1 represents the preset suboptimal factor; f(best f ) represents the minimum value of the total cost of all paths from the starting point to the end point of each vehicle.

[0013] Optionally, the method of taking out some nodes from the open node set to form a focused node set by using a focused search method includes: selecting nodes from the open node set that satisfy ^f(N)≤w*^f(best ^f ) nodes form a focused node set; where ^f(N) = cost(N) + ^h(N), ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point, cost(N) represents the total cost of the nodes extended by node N, ^h(N) represents the minimum value of the path cost among the nodes extended by node N, and w>1 represents the preset suboptimal factor; ^f(best ^f ) represents the minimum total estimated cost of each vehicle from the starting point to the end point.

[0014] Optionally, the ^h(N) is obtained by the following formula:

[0015]

[0016] in, Represents εh The average value of (N), εh(N) = cost(bc(N))-cost(N), ε h (N) represents the cost error of node N, bc(N) represents the node in node N that satisfies the minimum path cost, cost(bc(N)) represents the total cost of the nodes extended by node bc(N), Represents ε d The average value of (N), ε d (N)=hc(bc(N))-(hc(N)-1),ε d (N) represents the distance error of node N, hc(bc(N)) represents the distance from the starting point to the end point of each vehicle passing through node bc(N), and hc(N) represents the distance from the starting point to the end point of each vehicle passing through node N.

[0017] Optionally, the preset node selection method includes:

[0018] When cost(best hc )≤w*f(best f ), select a node from the focused node set as the expansion node; otherwise, when cost(best ^f )≤w*f(best f ), select a node from the open node set as an expansion node, when cost(best ^f )>w*f(best f ), select a node from the cleared node set as the expansion node; where cost(best hc ) represents the cost of the best node among the focused nodes; w>1 represents the preset suboptimal factor; f(best f ) represents the minimum value of the total cost of all paths from the starting point to the end point of each vehicle; cost(best ^f ) represents the cost of the best node among the open nodes; when selecting a node as an expansion node, if there is a node whose cost is the same as the current search node and the number of conflicts of the node is less than the number of conflicts of the current search node, the node is used as the expansion node and other nodes are discarded; otherwise, the node with the smallest number of conflicts is selected as the expansion node.

[0019] Optionally, the path extension according to preset constraint conditions includes: according to different priorities, when vehicles encounter a road occupation situation, the vehicle with the highest priority passes, and the vehicles with other priorities wait or detour; wherein, when the expansion node is a node in the open node set, the priority of the vehicle is determined by ^f(N); wherein ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point; when the expansion node is a node in the focus node set, the priority of the vehicle is determined by hc; wherein hc represents the distance of the vehicle from the starting point to the end point; when the expansion node is a node in the clear node set, the priority of the vehicle is determined by f(N); wherein represents the total cost of the path passing through node N.

[0020] In a second aspect of the present invention, a multi-vehicle path planning device comprises:

[0021] The acquisition module is used to obtain the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle;

[0022] The lower-level planning module is used to obtain all paths from the starting point to the end point of each vehicle according to the road condition information of the area to be planned for multiple vehicle paths and the starting and ending point information of each vehicle, and obtain the focused path from the starting point to the end point of each vehicle by using a focused search method;

[0023] A first preprocessing module is used to form a tree root graph from the starting point to the end point according to the focused paths from the starting point to the end point of each vehicle, wherein the nodes of the tree root graph are the path points that may overlap in the paths of multiple vehicles;

[0024] The second preprocessing module is used to obtain nodes in the tree root graph that can generate child nodes to obtain an open node set, and to take out some nodes from the open node set to form a focused node set by a focused search method, to set a clear node set, and to transfer the expanded nodes in the open node set to the clear node set;

[0025] The upper-level planning module is used to search for the end point from the starting point according to the tree root diagram of each vehicle. During the search process, nodes are selected from the open node set, the clear node set and the focused node set as expansion nodes according to the preset node selection method, and the path is expanded according to the preset constraint conditions. The path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path for each vehicle.

[0026] In a third aspect of the present invention, a computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned multi-vehicle path planning method when executing the computer program.

[0027] A fourth aspect of the present invention is a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the multi-vehicle path planning method are implemented.

[0028] In a fifth aspect of the present invention, a multi-vehicle path planning system includes a cloud server, a plurality of roadside devices and a plurality of vehicle-mounted devices; the plurality of roadside devices are respectively provided with a plurality of road tests in a multi-vehicle path planning area, for obtaining road condition information in a plurality of preset areas and sending the information to the cloud server; the vehicle-mounted device is mounted inside the vehicle, for obtaining the starting and ending point information of the vehicle, and sending the starting and ending point information of the vehicle to the cloud server; the cloud server is used to obtain the planned path of each vehicle through the multi-vehicle path planning device as described above, based on the starting and ending point information of the vehicle sent by each vehicle-mounted device and the road condition information sent by the roadside device, and send the planned path to the vehicle-mounted device of each vehicle.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The multi-vehicle path planning method of the present invention obtains the focused path from the starting point to the end point of each vehicle by adopting a focused search method, and adopts a focused search method to reduce the amount of path data of each subsequent vehicle during the multi-vehicle path collaborative planning, thereby reducing the planning difficulty. In addition, when selecting the extended nodes, a focused search method is adopted to take out some nodes from the open node set to form a focused node set, and the focused search method is adopted again, which ultimately improves the multi-vehicle path planning speed to a certain extent. At the same time, after the path is expanded according to the preset constraint restriction conditions, the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path of each vehicle, which effectively solves the contradiction problem in the multi-vehicle path planning, and can effectively complete the multi-vehicle path planning, so that each vehicle has a reasonable driving path, and the conflict between multiple vehicles is avoided as much as possible during driving. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A flow chart of a multi-vehicle path planning method according to an embodiment of the present invention;

[0032] Figure 2 A detailed flow chart of a multi-vehicle path planning method according to an embodiment of the present invention;

[0033] Figure 3 A schematic diagram of the framework structure of a multi-vehicle path planning system according to an embodiment of the present invention;

[0034] Figure 4 Schematic diagram of the structure of the roadside terminal device according to an embodiment of the present invention.

[0035] Among them: 1- camera; 2- protection device; 3- support device. DETAILED DESCRIPTION

[0036] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0037] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof 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 that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0038] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0039] See also Figure 1 In one embodiment of the present invention, a multi-vehicle path planning method is provided to effectively solve the problem of multi-vehicle path planning contradictions, and can effectively complete multi-vehicle path planning so that each vehicle has a reasonable driving path and no conflict occurs during driving. Specifically, the method includes the following steps:

[0040] S1: Obtain the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle.

[0041] S2: According to the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle, all paths from the starting point to the end point of each vehicle are obtained, and a focused path from the starting point to the end point of each vehicle is obtained by a focused search method.

[0042] S3: According to the focused paths from the starting point to the end point of each vehicle, the focused paths from the starting point to the end point of each vehicle are combined into a tree root graph from the starting point to the end point, and the nodes of the tree root graph are the path points that may overlap in the paths of multiple vehicles.

[0043] S4: Obtain the nodes in the tree root graph that can generate child nodes to obtain an open node set, and use a focused search method to take out some nodes from the open node set to form a focused node set, set a clear node set, and transfer the expanded nodes in the open node set to the clear node set;

[0044] S5: According to the tree root graph of each vehicle, the end point is searched from the starting point. During the search process, according to the preset node selection method, nodes are selected from the open node set, the clear node set and the focus node set as expansion nodes, and the path is expanded according to the preset constraint conditions, and the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path of each vehicle.

[0045] Specifically, the multi-vehicle path planning method of the present invention defines conflict as the number of overlapping path nodes in the paths of multiple vehicles at a certain moment when planning the path for each vehicle; the solution is that each vehicle has a conflict-free path to travel; and the optimal solution is the minimum value of the total cost of these paths.

[0046] In summary, the multi-vehicle path planning method of the present invention obtains the focused path from the starting point to the end point of each vehicle by adopting a focused search method. The focused search method reduces the amount of path data of each subsequent vehicle during the multi-vehicle path collaborative planning, thereby reducing the planning difficulty. In addition, when selecting the extended nodes, the focused search method is adopted to take out some nodes from the open node set to form a focused node set, and the focused search method is adopted again, which ultimately improves the multi-vehicle path planning speed to a certain extent. At the same time, after the path is expanded according to the preset constraint conditions, the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path of each vehicle, which effectively solves the contradiction problem in multi-vehicle path planning, and can effectively complete the multi-vehicle path planning, so that each vehicle has a reasonable driving path, and the conflict between multiple vehicles is avoided as much as possible during driving.

[0047] In one possible implementation, after obtaining the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle, the road condition information can be converted into a grid map, and the vehicles and obstacles can be marked in the grid map. By marking the starting and ending points of the vehicles in the grid map and then expanding from the starting point, all paths from the starting point to the end point of each vehicle can be obtained.

[0048] See also Figure 2Specifically, the multi-vehicle path planning method of the present invention can also be understood as using a node search method to plan, and the entire algorithm is made more robust through the upper and lower layer structures. The lower layer algorithm performs single-vehicle path planning, and sends path nodes that are less likely to conflict to the upper layer by setting conditions, so as to accelerate the search speed of the upper layer. At the same time, after receiving the path nodes of the lower layer, the upper layer expands these path nodes by setting conditions, and combines the constraint conditions to resolve the path conflict and output the path information. Among them, the path conflict mainly includes the number of overlapping path nodes in the paths of multiple vehicles at a certain moment in the vehicle's driving path. When a path conflict occurs, the constraint conditions used are to determine the priority according to the setting conditions of the upper and lower layer algorithms. The higher priority will pass first, and the lower priority will wait or detour. The conflict can be calculated by the vehicle speed and the distance length.

[0049] In a possible implementation manner, the method of obtaining the focused path from the starting point to the end point of each vehicle by using the focused search method includes: selecting from all the paths from the starting point to the end point of each vehicle a path that satisfies f(n)≤w*f(best f ) path, and obtain the focused path from the starting point to the end point of each vehicle; where f(n) = g(n) + h(n), f(n) represents the total cost of the path, g(n) represents the cost from the starting point to the intermediate point, h(n) represents the cost from the intermediate point to the end point, and the intermediate point is an arbitrarily selected path point in the path from the starting point to the end point; w>1 represents the preset suboptimal factor; f(best f ) represents the minimum value of the total cost of all paths from the starting point to the end point of each vehicle.

[0050] Specifically, the lower-level algorithm maintains two path sets, namely the open path set and the focused path set. The open path set is used to save all the paths extended based on the starting point and the end point for each vehicle in the map; the focused path set uses a focused search method to select paths from the open path set for saving. The open path set uses the method of f(n) = g(n) + h(n) to calculate the cost of searching for paths for each vehicle. The priority order of each vehicle in the open path set is determined by the size of f(n). Among them, n is a media point set in the path from the starting point to the end point. The selection of the media point must meet the following requirements: 1) This point is included in the path point set of the path from the starting point to the end point; 2) This point is a path point arbitrarily selected from the point set of the path from the starting point to the end point.

[0051] Specifically, a suboptimal factor w is artificially introduced, and the path that satisfies f(n)≤w*f(best f ) are put into the focused path set. During the expansion process of the focused path set, the paths are sorted according to the number of conflicts in the paths, and the number of conflicts determines the priority order.

[0052] Optionally, after the lower-level algorithm has completed searching for the path for each vehicle, it puts all the path information into an information table, which can share the path-related information of all vehicles. The table also contains the priority order of the vehicles. The upper-level algorithm performs multi-vehicle path planning based on the information table, and the main purpose is to resolve path conflicts. Because the lower-level algorithm selects multiple paths for each vehicle, on this basis, the multiple paths of each vehicle are combined into a tree root graph from the starting point to the end point, that is, starting from the starting point as the root node, all paths to the end point are explored, and an empty constraint is set for the root node (the root node is defined as a node that can generate child nodes). This information is passed to the upper layer, and at the same time, constraints are set (the high priority passes first, and other vehicles wait or re-plan new paths) to re-expand the tree root graph. The nodes in the expansion are called constraint nodes. On the basis of resolving conflicts, a reasonable path is explored for each vehicle from multiple paths.

[0053] The upper algorithm sets three node sets: an open node set, a clear node set, and a focused node set. Specifically, the nodes in the root graph that can generate child nodes are obtained to obtain the open node set, and a focused search method is used to extract some nodes from the open node set to form a focused node set, and a clear node set is set, and the expanded nodes in the open node set are transferred to the clear node set.

[0054] In a possible implementation manner, the method of taking out some nodes from the open node set to form a focused node set by using a focused search method includes: selecting nodes from the open node set that satisfy ^f(N)≤w*^f(best ^f ) nodes form a focused node set; where ^f(N) = cost(N) + ^h(N), ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point, cost(N) represents the total cost of the nodes extended by node N, ^h(N) represents the minimum value of the path cost among the nodes extended by node N, and w>1 represents the preset suboptimal factor; ^f(best ^f ) represents the minimum total estimated cost of each vehicle from the starting point to the end point.

[0055] In one possible implementation, according to different priorities, when vehicles encounter a road occupation situation, the vehicle with the highest priority passes, and vehicles with other priorities wait or detour; when the expansion node is a node in the open node set, the priority of the vehicle is determined by ^f(N); wherein ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point; when the expansion node is a node in the focus node set, the priority of the vehicle is determined by hc; wherein hc represents the distance of the vehicle from the starting point to the end point; when the expansion node is a node in the clear node set, the priority of the vehicle is determined by f(N); wherein represents the total cost of the path passing through node N.

[0056] Specifically, the open node set expands each root node in the tree root graph and estimates the total cost of each vehicle from the starting point to the end point in the form of ^f(N)=cost(N)+^h(N), where represents the total cost of the nodes extended by the root node N. ^h(N) is used to estimate the best path cost among the nodes extended by the root node N. The priority is determined by the size of ^f. At the same time, constraints are set. According to the priority, the vehicle will wait or detour when encountering a road occupation situation. The nodes saved in the focus node set are selected from the open node set to meet ^f(N)≤w*^f(best ^f ) nodes, when the focused node set is expanded, it will estimate the distance h of each vehicle from the starting point to the end point c , and according to h c The nodes saved in the cleared node set are the nodes after the open node set is expanded, and the path cost is calculated according to f(N)=g(N)+h(N), and the priority is determined by f(N).

[0057] In a possible implementation, the h(N) is obtained by the following formula:

[0058]

[0059] in, Represents ε h The average value of (N), εh(N) = cost(bc(N))-cost(N), ε h (N) represents the cost error of node N, bc(N) represents the node in node N that satisfies the minimum path cost, cost(bc(N)) represents the total cost of the nodes extended by node bc(N), Represents ε d The average value of (N), ε d (N)=hc(bc(N))-(hc(N)-1),ε d (N) represents the distance error of node N, hc(bc(N)) represents the distance from the starting point to the end point of each vehicle passing through node bc(N), and hc(N) represents the distance from the starting point to the end point of each vehicle passing through node N.

[0060] Specifically, because there may be a certain error between the actual path selection and the estimated path, the cost error of node N is defined as ε h (N) = cost(bc(N))-cost(N), the distance error is ε d (N) = h c (bc(N))-(h c(N)-1), where bc(N) represents the node in the root node N that satisfies the minimum path cost estimate. The distance error and cost error are used to more accurately estimate the actual cost, so the actual estimated cost is in, With ε d (N) is the average value of the above cost error and distance error.

[0061] In a possible implementation manner, the preset node selection method includes: when cost(best hc )≤w*f(best f ), select a node from the focused node set as the expansion node; otherwise, when cost(best ^f )≤w*f(best f ), select a node from the open node set as an expansion node, when cost(best ^f )>w*f(best f ), select a node from the cleared node set as the expansion node; where cost(best hc ) represents the cost of the best node among the focused nodes; w>1 represents the preset suboptimal factor; f(best f ) represents the minimum value of the total cost of all paths from the starting point to the end point of each vehicle; cost(best ^f ) represents the cost of the best node among the open nodes; when selecting a node as an expansion node, if there is a node whose cost is the same as the current search node and the number of conflicts of the node is less than the number of conflicts of the current search node, the node is used as the expansion node and other nodes are discarded; otherwise, the node with the smallest number of conflicts is selected as the expansion node.

[0062] Specifically, the search for the end point starts from the starting point. During the search process, the nodes to be expanded at each step are stored in the open node set, and then the nodes after the expansion of the open node set are stored in the cleared node set. Then, the nodes that meet the requirements (^f(N)≤w*^f(best) are selected from the open node set. ^f )) nodes are put into the focused node set. Because the focused node set stores the nodes selected from the open node set, the focused node set is easier to find the target node, so it is given priority. The node selection function is as follows: 1: If cost(best hc )≤w*f(best f ), then a node will be selected from the focused node set for expansion; 2: If cost(best ^f )≤w*f(best f), then nodes will be selected from the open node set for expansion; if the above two conditions are not met, nodes will be selected from the cleared node set for expansion, and then the best node will be reconsidered in the next iteration. hc and best ^f .

[0063] Optionally, in order to speed up the algorithm in resolving conflicts and improve the efficiency of the algorithm, an improved method is introduced into the algorithm, namely, the conflict bypassing method. This method is only used for expanding nodes within open nodes and focus nodes. That is, when selecting nodes for expansion, in the process of generating expansion nodes, if the cost of one of the nodes is the same as that of the current search node, and the number of conflicts of this node is less than that of the current search node, then this node is selected for expansion and the other nodes are discarded.

[0064] Since the improved method does not select nodes for expansion in the cleared node set, after the node generates an expansion node, the cost of each path of the expansion node is within the suboptimal bound under the constraint tree of the corresponding node: N'.paths[i]≤w*; the number of conflicts of the expansion node generated by the node is less than that of the node, and after the node generates an expansion node, the cost of the expansion node is within w*f(bestf). When the above conditions are met, the expansion node can be used to replace the node, and all optional expansion nodes except this node are discarded to improve the efficiency of the algorithm. Then, the constraint set in the constraint tree is used to determine whether the number of conflicts between the expansion nodes generated by other root nodes in the path of the expansion node is small. If the expansion node has no conflict or less conflict, then this expansion node is the target node, and the vehicle can travel according to the path of this node. If the expansion node still has a conflict, continue to judge until the target node is generated. After the target node is generated, the target node information is put into the storage table, and the path information planned for each vehicle is stored in the storage table, so as to solve the conflict when multiple vehicles are driving at a certain time.

[0065] The following are device embodiments of the present invention, which can be used to implement the method embodiments of the present invention. For details not disclosed in the device embodiments, please refer to the method embodiments of the present invention.

[0066] In another embodiment of the present invention, a multi-vehicle path planning device is provided, which can be used to implement the above-mentioned multi-vehicle path planning method. Specifically, the multi-vehicle path planning device includes an acquisition module, a lower-level planning module, a first preprocessing module, a second preprocessing module and an upper-level planning module.

[0067] Among them, the acquisition module is used to obtain the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle; the lower-level planning module is used to obtain all the paths from the starting point to the end point of each vehicle according to the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle, and adopt a focused search method to obtain the focused path from the starting point to the end point of each vehicle; the first preprocessing module is used to form a tree root diagram from the starting point to the end point according to the focused path from the starting point to the end point of each vehicle, and the nodes of the tree root diagram are the path points that may overlap in the paths of multiple vehicles; the second preprocessing module is used to obtain the tree root diagram that can The nodes that can generate child nodes are used to obtain the open node set, and some nodes are taken out from the open node set by means of focused search to form a focused node set, a clear node set is set, and the nodes expanded in the open node set are transferred to the clear node set; the upper-level planning module is used to search for the end point from the starting point according to the tree root graph of each vehicle. During the search process, nodes are selected from the open node set, the clear node set and the focused node set as expansion nodes according to the preset node selection method, and the path is extended according to the preset constraint conditions, and the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path of each vehicle.

[0068] In a possible implementation manner, the method of obtaining the focused path from the starting point to the end point of each vehicle by using the focused search method includes: selecting from all the paths from the starting point to the end point of each vehicle a path that satisfies f(n)≤w*f(best f ) to obtain the focused path from the starting point to the end point of each vehicle.

[0069] In a possible implementation manner, the method of taking out some nodes from the open node set to form a focused node set by using a focused search method includes: selecting nodes from the open node set that satisfy ^f(N)≤w*^f(best ^f ) form a focused node set.

[0070] In a possible implementation, the h(N) is obtained by the following formula:

[0071]

[0072] In a possible implementation manner, the preset node selection method includes: when cost(best hc )≤w*f(best f ), select a node from the focused node set as the expansion node; otherwise, when cost(best ^f )≤w*f(best f ), select a node from the open node set as an expansion node, when cost(best ^f )>w*f(best f), select a node from the cleared node set as the expanded node.

[0073] Among them, when selecting a node as an expansion node, if there is a node whose cost is the same as the current search node and the number of conflicts of the node is less than the number of conflicts of the current search node, the node will be used as the expansion node and other nodes will be discarded; otherwise, the node with the smallest number of conflicts will be selected as the expansion node.

[0074] In a possible implementation, the path extension according to preset constraint restrictions includes: according to different priorities, when vehicles encounter a road occupation situation, the vehicle with the highest priority passes, and vehicles with other priorities wait or detour; wherein, when the extended node is a node in the open node set, the priority of the vehicle is determined by ^f(N); when the extended node is a node in the focus node set, the priority of the vehicle is determined by hc; when the extended node is a node in the clear node set, the priority of the vehicle is determined by f(N).

[0075] All relevant contents of each step involved in the aforementioned embodiment of the multi-vehicle path planning method can be referred to the functional description of the functional module corresponding to the multi-vehicle path planning device in the embodiment of the present invention, and will not be repeated here. The division of modules in the embodiment of the present invention is schematic, which is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present invention can be integrated into a processor, or it can exist physically separately, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of software functional modules.

[0076] In another embodiment of the present invention, a computer device is provided, the computer device comprising a processor and a memory, the memory being used to store a computer program, the computer program comprising program instructions, and the processor being used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc., which are the computing core and control core of the terminal, which are suitable for implementing one or more instructions, and are specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a multi-vehicle path planning method.

[0077] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a computer device for storing programs and data. It is understandable that the computer-readable storage medium here can include both built-in storage media in the computer device and, of course, extended storage media supported by the computer device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The processor can load and execute one or more instructions stored in the computer-readable storage medium to implement the corresponding steps of the multi-vehicle path planning method in the above embodiment.

[0078] See also Figure 3In another embodiment of the present invention, a multi-vehicle path planning system is provided, including a cloud server, a plurality of roadside devices, and a plurality of vehicle-mounted devices. Among them, the plurality of roadside devices are respectively provided with a plurality of road tests in the multi-vehicle path planning area for obtaining the road condition information in the plurality of preset areas and sending the road condition information to the cloud server; the vehicle-mounted device is mounted inside the vehicle for obtaining the starting and ending point information of the vehicle, and sending the starting and ending point information of the vehicle to the cloud server; the cloud server is used to obtain the planned path of each vehicle through the multi-vehicle path planning device as described above, according to the starting and ending point information of the vehicle sent by each vehicle-mounted device and the road condition information sent by the roadside device, and send the planned path to the vehicle-mounted device of each vehicle.

[0079] Optionally, the roadside terminal device can also establish communication with the vehicle-mounted terminal device through the network, and transmit the path information of the local area to the vehicle-mounted terminal device in the form of broadcasting, so that the vehicle-mounted terminal device can know the intersection information, road section information and lane information of the area in real time. At the same time, the vehicle-mounted terminal device collects surrounding information through multi-sensor fusion technology. The vehicle-mounted terminal device then contacts the cloud server through the network communication platform, and digitizes the obtained information and transmits it to the cloud server. The cloud server and the roadside terminal device establish data interaction through the network. After obtaining the vehicle driving information and path information, the cloud server converts the obtained map information into a grid map through the above algorithm, and marks the vehicle and obstacles in the grid map. Then, a reasonable path is planned for each vehicle through a multi-vehicle path planning method, and transmitted to the vehicle-mounted terminal device through the network. The vehicle then drives according to the received information to complete the path planning.

[0080] Optionally, the cloud server platform includes two systems. The two systems perform their respective functions and do not interfere with each other. One of the systems is configured as a road condition information monitoring system, which receives real-time information about surrounding road conditions transmitted by the vehicle-mounted terminal device and intersection information, road section information, lane information, and traffic sign information collected in real time by the roadside terminal device, and monitors the overall road condition information in real time to respond to emergency situations that occur when the vehicle is driving.

[0081] Another system is configured as a receiving system, a processing system and a service system. The receiving system is configured to receive the driving demand of the driver, locate the position of the vehicle that issued the demand and the destination position set by the driver according to the driver's demand, and receive the real-time traffic information and vehicle obstacle information transmitted from the roadside terminal device. Through network transmission, the receiving system receives the path planning demand information, the road condition information around the vehicle, and the path information and road condition information collected in real time by the roadside terminal device from the vehicle-mounted terminal device. The receiving system converts the above information into a digital form and transmits it to the processing system; the processing system is configured to process the information from the receiving system, and the multi-vehicle path planning method is set inside the processing system. The multi-vehicle path planning method adopts the form of upper and lower layer search paths, that is, the lower layer plans a path for a single vehicle and stores the path information in the information table. The upper layer sets constraints based on the information table to solve the path conflict, and then stores the planned path information in the storage table. The service system extracts the path information from the storage table and transmits it to the central control platform of the vehicle-mounted terminal device; the service system is configured to transmit the information processed by the processing system to the vehicle-mounted terminal device. The cloud server establishes data interaction with the roadside device and the vehicle-mounted device through the network, and each port can complete information transmission with low latency and high reliability.

[0082] The vehicle-mounted device is configured as a central control platform, a receiving device and a processor. The receiving device receives information from the service system in the cloud server demand system, and transmits the information to the processor after conversion; the processor is configured as a processing device and a transmission device, the processing device is configured to process the information of the receiving device, and transmit the path information after conversion to the transmission device, and the transmission device is configured to transmit the processing result of the processing device to the display screen of the vehicle.

[0083] See also Figure 4 , the roadside device is configured as camera 1, protection device 2 and support device 3. Camera 1 is configured to connect to the cloud server using intranet penetration and use public network IP for communication. In addition, camera 1 and cloud server use encrypted data transmission to improve the security of the entire device. That is, the port of the cloud server can receive private network IPs from different cameras. In addition, camera 1 and cloud server use public network IP as an intermediate connection, so that the cloud server can receive information obtained by the camera. Because the roadside device is exposed to the outdoors for a long time, the protection device 2 is made of aluminum alloy, and the height of the support device 3 should be more than one meter, so that the overall height of the roadside device is greater than one meter. Installing it too low will result in incomplete information collection, and installing it too high will cause material waste.

[0084] Vehicles traveling on urban roads basically travel according to where the driver wants to go and the driver's starting point. However, the number of vehicles on urban roads has increased dramatically. In many cases, there will be conflicts when multiple vehicles choose the same destination, which will cause traffic jams and other conditions. The multi-vehicle path planning system of the present invention can provide a path with few or no conflicts for each vehicle using the system on urban roads, thereby reducing the probability of traffic jams, improving the safety of vehicle driving and the driver's driving experience. Each vehicle is set with a unique identifier, which can be stored inside the cloud server. The vehicle-mounted terminal device is operated by the driver to send the demand to the cloud server. The cloud server can be set with a satellite positioning system to quickly locate the geographical location of each vehicle. The information transmitted from the roadside terminal device can more accurately display the road conditions and traffic flow information around the located vehicle, so that this information is reflected in the map. After receiving the driver's demand, the cloud server is processed by the processing system, and then the processed result is returned to the vehicle-mounted terminal device through the service system to solve the problem of multi-vehicle path conflicts.

[0085] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0086] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A multi-vehicle path planning method, characterized in that: include: Obtain the road condition information of the multi-vehicle route planning area and the starting and ending point information of each vehicle; According to the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle, all paths from the starting point to the end point of each vehicle are obtained, and the focused path from the starting point to the end point of each vehicle is obtained by using a focused search method; According to the focused paths from the starting point to the end point of each vehicle, the focused paths from the starting point to the end point of each vehicle are combined into a tree root graph from the starting point to the end point, and the nodes of the tree root graph are the path points that may overlap in the paths of multiple vehicles; Obtain the nodes in the tree root graph that can generate child nodes to obtain the open node set, and use the focused search method to take out some nodes from the open node set to form a focused node set, set the clear node set, and transfer the expanded nodes in the open node set to the clear node set; According to the tree root graph of each vehicle, the end point is searched from the starting point. During the search process, nodes are selected from the open node set, the clear node set and the focus node set as expansion nodes according to the preset node selection method, and the path is expanded according to the preset constraint conditions, and the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path of each vehicle; The method of taking out some nodes from the open node set to form a focused node set by using a focused search method includes: Select from the open node set the node that satisfies ^f(N)≤w*^f(best ^f ) nodes form a focused node set; where ^f(N) = cost(N) + ^h(N), ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point, cost(N) represents the total cost of the nodes extended by node N, ^h(N) represents the minimum value of the path cost among the nodes extended by node N, and w>1 represents the preset suboptimal factor; ^f(best ^f ) represents the minimum value of the total estimated cost of each vehicle from the starting point to the end point; The ^h(N) is obtained by the following formula: in, Represents ε h The average value of (N), εh(N) = cost(bc(N))-cost(N), ε h (N) represents the cost error of node N, bc(N) represents the node in node N that satisfies the minimum path cost, cost(bc(N)) represents the total cost of the nodes extended by node bc(N), Represents ε d The average value of (N), ε d (N)=hc(bc(N))-(hc(N)-1),ε d (N) represents the distance error of node N, hc(bc(N)) represents the distance from the starting point to the end point of each vehicle passing through node bc(N), and hc(N) represents the distance from the starting point to the end point of each vehicle passing through node N.

2. The multi-vehicle path planning method according to claim 1, characterized in that: The method of obtaining the focused path from the starting point to the end point of each vehicle by using the focused search method includes: Select the path from the starting point to the end point of each vehicle that satisfies f(n)≤w*f(best f ) path, and obtain the focused path from the starting point to the end point of each vehicle; where f(n) = g(n) + h(n), f(n) represents the total cost of the path, g(n) represents the cost from the starting point to the intermediate point, h(n) represents the cost from the intermediate point to the end point, and the intermediate point is an arbitrarily selected path point in the path from the starting point to the end point; w>1 represents the preset suboptimal factor; f(best f ) represents the minimum value of the total cost of all paths from the starting point to the end point of each vehicle.

3. The multi-vehicle path planning method according to claim 1, characterized in that: The preset node selection method includes: When cost(best hc )≤w*f(best f ), select a node from the focused node set as the expansion node; otherwise, when cost(best ^f )≤w*f(best f ), select a node from the open node set as an expansion node, when cost(best ^f )>w*f(best f ), select a node from the cleared node set as the expansion node; where cost(best hc ) represents the cost of the best node among the focused nodes; w>1 represents the preset suboptimal factor; f(best f ) represents the minimum value of the total cost of all paths from the starting point to the end point of each vehicle; cost(best ^f ) represents the cost of the best node among the open nodes; Among them, when selecting a node as an expansion node, if there is a node whose cost is the same as the current search node and the number of conflicts of the node is less than the number of conflicts of the current search node, the node will be used as the expansion node and other nodes will be discarded; otherwise, the node with the smallest number of conflicts will be selected as the expansion node.

4. The multi-vehicle path planning method according to claim 1, characterized in that: The path extension according to the preset constraint conditions includes: According to the different priorities, when vehicles encounter a road occupation situation, the vehicle with the highest priority will pass, and the vehicles with other priorities will wait or detour; When the extended node is a node in the open node set, the priority of the vehicle is determined by ^f(N); wherein ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point; When the extended node is a node in the focused node set, the priority of the vehicle is determined by hc, where hc represents the distance from the starting point to the end point of the vehicle; When the expansion node is a node in the clearing node set, the priority of the vehicle is determined by f(N), where represents the total cost of the path passing through node N.

5. A multi-vehicle path planning device, characterized in that: include: The acquisition module is used to obtain the road condition information of the multi-vehicle path planning area and the starting and ending point information of each vehicle; The lower-level planning module is used to obtain all paths from the starting point to the end point of each vehicle according to the road condition information of the area to be planned for multiple vehicle paths and the starting and ending point information of each vehicle, and obtain the focused path from the starting point to the end point of each vehicle by using a focused search method; A first preprocessing module is used to form a tree root graph from the starting point to the end point according to the focused paths from the starting point to the end point of each vehicle, wherein the nodes of the tree root graph are the path points that may overlap in the paths of multiple vehicles; The second preprocessing module is used to obtain nodes in the tree root graph that can generate child nodes to obtain an open node set, and to take out some nodes from the open node set to form a focused node set by a focused search method, to set a clear node set, and to transfer the expanded nodes in the open node set to the clear node set; The upper-level planning module is used to search for the end point from the starting point according to the tree root diagram of each vehicle. During the search process, according to the preset node selection method, nodes are selected from the open node set, the clear node set and the focus node set as expansion nodes, and the path is expanded according to the preset constraint conditions, and the path with the least number of conflicts between each vehicle and other vehicles is selected as the planned path of each vehicle; The method of taking out some nodes from the open node set to form a focused node set by using a focused search method includes: Select from the open node set the node that satisfies ^f(N)≤w*^f(best ^f ) nodes form a focused node set; where ^f(N) = cost(N) + ^h(N), ^f(N) represents the total estimated cost of the vehicle passing through node N from the starting point to the end point, cost(N) represents the total cost of the nodes extended by node N, ^h(N) represents the minimum value of the path cost among the nodes extended by node N, and w>1 represents the preset suboptimal factor; ^f(best ^f ) represents the minimum value of the total estimated cost of each vehicle from the starting point to the end point; The ^h(N) is obtained by the following formula: in, Represents ε h The average value of (N), εh(N) = cost(bc(N))-cost(N), ε h (N) represents the cost error of node N, bc(N) represents the node in node N that satisfies the minimum path cost, cost(bc(N)) represents the total cost of the nodes extended by node bc(N), Represents ε d The average value of (N), ε d (N)=hc(bc(N))-(hc(N)-1),ε d (N) represents the distance error of node N, hc(bc(N)) represents the distance from the starting point to the end point of each vehicle passing through node bc(N), and hc(N) represents the distance from the starting point to the end point of each vehicle passing through node N.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the multi-vehicle path planning method according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the multi-vehicle path planning method according to any one of claims 1 to 4 are implemented.

8. A multi-vehicle path planning system, characterized in that: It includes a cloud server, several roadside devices and several vehicle-mounted devices; Several roadside devices are respectively provided with several road tests in the multi-vehicle path planning area, for obtaining the road condition information in several preset areas and sending it to the cloud server; The vehicle-mounted device is installed inside the vehicle and is used to obtain the vehicle's starting and ending point information and send the vehicle's starting and ending point information to the cloud server; The cloud server is used to obtain the planned path of each vehicle based on the vehicle's starting and ending point information sent by each vehicle-mounted terminal device and the road condition information sent by the roadside terminal device through the internally arranged multi-vehicle path planning device as described in claim 5, and send it to the vehicle-mounted terminal device of each vehicle.

Images