A method for searching path planning of a flying vehicle diagram, a terminal device, and a medium

Abstract

The present invention discloses a method for searching and path planning of a flight vehicle map, a terminal device, and a medium, including: inputting a starting point and an ending point, connecting the starting point as the first key search node to the ending point; defining the adjacent node of the first obstacle crossed by the connection line as a new key search node and connecting it to the previous-level key search node; determining whether the connection line crosses an obstacle; if not, recording the path, if so, if the adjacent node of the obstacle has been defined as a key search node, then the node expands eight adjacent child nodes, repeating the connection process, and the child nodes where the connection line does not cross the obstacle are defined as key search nodes; the key search node continues to connect to the ending point, defining a new key search node, and repeating the connection process with the previous-level node; deleting the transitional path nodes; and finding the shortest path therefrom. The advantages of the present invention are: reducing the number of search nodes of the graph search algorithm, improving the planning efficiency, and planning a multi-modal path that reasonably considers the switching of air and ground motion modes.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and particularly to a flight vehicle graph search path planning method, a terminal device, and a medium. Background Art

[0002] Graph search algorithms have been proven to be effective means for solving path planning problems. They find a shortest path by searching for path points in a grid map and calculating corresponding cost values. A basic problem of existing algorithms, such as Dijkstra, A*, and their improvements, etc., is how to find the shortest path among as few search nodes as possible. They face a trade-off between path distance and planning efficiency.

[0003] The above problems restrict the application of graph search algorithms in the path planning of flight vehicles. A flight vehicle has two motion modes, namely a ground driving mode and an air flight mode. The path planning of a flight vehicle needs to consider both the planning of ground / air paths and judge the appropriate timing and position of different mode switches. The complex planning mechanism requires the algorithm to have a high planning efficiency to obtain the shortest path with fewer search nodes.

[0004] Prior Art:

[0005] (1) Dijkstra

[0006] As a classic graph search algorithm, the Dijkstra algorithm can find a shortest path in a grid map. It adopts a greedy idea to search globally. Starting from the starting point, it traverses all nodes in the map, calculates the path distance cost to each node, and finds a shortest path from them. [1] .

[0007] Disadvantages:

[0008] Since Dijkstra traverses all nodes in the map, the number of search nodes is too large and the search efficiency is poor. It does not meet the high-efficiency planning requirements of flight vehicles.

[0009] (2) A*

[0010] Based on the Dijkstra algorithm, the A* algorithm adds heuristic information. In this algorithm, the path distance cost to each node in the map consists of two parts: the known path distance cost from the starting point to the current search node and the estimated path distance cost from the current search node to the end point. The calculation of the known path distance cost is the same as that of Dijkstra. The estimated path distance cost is a newly added heuristic information item, which can be calculated using the Euclidean distance. The A* algorithm usually adopts an eight-neighborhood search method, that is, the starting point is used as the parent neighborhood, and the search expands to eight child neighborhoods in different directions. The child neighborhood with the minimum path distance cost is selected as the parent neighborhood for the next search, and the eight-neighborhood search is continued until the end point is reached. [2] 。

[0011] Disadvantages:

[0012] Compared with Dijkstra, A* effectively reduces the number of search nodes, and the planning efficiency is improved. However, this improvement is relative. A* still has many redundant search nodes, and there is still room for further improvement in the planning efficiency. [3] 。

[0013] Disadvantages of the existing technology:

[0014] 1. Existing graph search algorithms face the problems of redundant search nodes and low planning efficiency. How to find the shortest path among as few search nodes as possible is a technical problem that needs in-depth study.

[0015] 2. Due to the constraints of the above problems, existing graph search algorithms are difficult to plan a short multi-modal path for flying vehicles with high efficiency.

[0016] 3. The multi-modal path planning of flying vehicles needs to comprehensively consider the planning of ground / air paths and the reasonable switching of different motion modes. Existing multi-modal path planning technologies are not yet perfect.

[0017] References

[0018] [1] Kang Ning. Research on Emergency Path Planning in Coal Mines Based on Improved Dijkstra Algorithm [D]. Xi'an University of Science and Technology, 2020. DOI: 10.27397 / d.cnki.gxaku.2020.000281;

[0019] [2] Tan Chengzhi. Application Research of A* Algorithm Integrated with Improved Artificial Potential Field in Robot Global Path Planning [D]. Guangxi University, 2022. DOI: 10.27034 / d.cnki.ggxiu.2022.001294;

[0020] [3]L. Xie, S. Xue, J. Zhang, M. Zhang, W. Tian, S. Haugen, “A path planning approach based on multi-direction A* algorithm for ships navigating within wind farm waters,” Ocean Engineering, vol. 184, pp. 311 - 322, 2019。 Summary of the Invention

[0021] The present invention addresses the deficiencies of the prior art and provides a method for graph search path planning of a flying vehicle, a terminal device, and a medium.

[0022] To achieve the above invention objectives, the technical solutions adopted by the present invention are as follows:

[0023] A method for graph search path planning of a flying vehicle, the specific steps are as follows:

[0024] Step1: Input the starting point and the ending point, and connect the starting point as the first key search node to the ending point.

[0025] Create a connection table NODE and a path table PATH to record the key search nodes and the directed paths between the nodes respectively. Input the starting point and the ending point, and record the starting point in the table NODE as the first key search node. Connect the key search node in NODE to the ending point, and the adjacent node of the first obstacle crossed by the connection line is defined as a new key search node and recorded in the table NODE.

[0026] Step2: Node search. Connect the newly added key search node in the connection table NODE to its upper-level key search node. Determine whether the connection line crosses an obstacle;

[0027] If not, then this connection line is a directed path from the upper-level node to the newly added node and is recorded in the table PATH.

[0028] If it crosses an obstacle, then determine whether the obstacle is a new obstacle. If the adjacent node of the obstacle is not defined, then update NODE, add the adjacent node as a new key search node, and repeat the connection process in Step2 to update the directed path in PATH.

[0029] If the adjacent node of the obstacle has been defined as a key search node, then expand eight adjacent child nodes outward from this node. The child nodes repeat the connection process in Step2, and the child nodes whose connection lines do not cross obstacles are defined as key search nodes, recorded in NODE, and the directed path in PATH is updated.

[0030] Continue to connect the key search nodes in the NODE to the end point, record the new key search nodes, and repeat Step 2 and the above judgment process.

[0031] Step 3: Node check. Check whether there are redundant transition path nodes in the directed path in the PATH. If there are transition path nodes, delete the transition path nodes. Use the key search nodes and directed paths in the NODE table and the PATH table to form a dynamic directed graph. As the search progresses, the dynamic directed graph is gradually improved, and the shortest path is found from it.

[0032] Furthermore, the judgment of redundant transition path nodes in Step 3: Sequentially judge whether there is a situation where the nodes in a directed path can be directly connected to the nodes in non-adjacent positions. If so, delete all other nodes between the two nodes, that is, the transition path nodes.

[0033] Furthermore, if the flying vehicle is in the ground driving mode, the adjacent nodes of the obstacle and the eight adjacent child nodes only have nodes in the two-dimensional plane.

[0034] Furthermore, if the flying vehicle is in the air flight mode, the adjacent nodes of the obstacle and the eight adjacent child nodes have nodes in the two-dimensional plane and the height nodes of the obstacle. Let H flight be the flight height required to fly over the obstacle area; H max be the maximum flight height of the flying vehicle; judge whether H flight is greater than H max , if it is greater, it is defined as the area of the obstacle to be flown over, and if it is less, it is defined as the obstacle area;

[0035] Furthermore, let D ground be the two-dimensional distance cost of the directed path; D flight be the flight height cost of the directed path;

[0036] The total cost of the directed path passing through the area of the obstacle to be flown over includes both D ground and D flight . And the directed path that does not pass through the above area only includes D ground .

[0037] Find the path with the minimum cost, that is, the shortest distance, from all the directed paths.

[0038] The present invention also discloses a computer terminal device, which is installed in a flying car to control the route planning of the flying car, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above-mentioned flying vehicle graph search path planning method is implemented.

[0039] The present invention also discloses a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned flight vehicle graph search path planning method is implemented.

[0040] Compared with the prior art, the advantages of the present invention are as follows:

[0041] 1. Key search nodes in the grid map are dynamically extracted, and a dynamic directed graph is constructed for shortest path planning, effectively reducing the number of search nodes of the graph search algorithm and improving the planning efficiency.

[0042] 2. Applied to the path planning of flight vehicles, the area of the obstacle to be flown is redefined, and the flight height cost is added to the cost calculation of the directed path. A multi-modal path that reasonably switches between air and ground motion modes is planned, which can save the driving cost in the way of combining air and ground motion. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic structural diagram of a flight vehicle graph search path planning method according to an embodiment of the present invention;

[0044] Figure 2 is a schematic diagram of flight vehicle graph search path planning according to an embodiment of the present invention;

[0045] Figure 3 is a flowchart of adding flight height cost to flight vehicle graph search path planning according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to make the purpose, technical solutions and advantages of the present invention clearer, the following further describes the present invention in detail with reference to the drawings and by way of examples.

[0047] The present invention proposes a new graph search algorithm called Dynamic Directed Graph Algorithm (DDGA). In the planning process of the DDGA algorithm, the current search node is connected to the end point. The adjacent nodes of the obstacle crossed by the connection line are defined as key search nodes. Generally, the present invention only records the adjacent nodes of the first obstacle crossed. As the search progresses, the current search node changes continuously, and the defined key search nodes are also updated dynamically. The above key search nodes and the directed paths between the nodes form a dynamic directed graph. In the dynamic directed graph, the directed path with the minimum cost (shortest distance) between the starting point and the end point is the finally planned shortest path.

[0048] As Figure 1 shown, a flight vehicle graph search path planning method includes the following steps:

[0049] Step 1: Algorithm initialization. Create Table NODE and Table PATH to record the key search nodes and the directed paths between the nodes respectively. Record the starting point as the first key search node in Table NODE. Connect the key search nodes in NODE with the end point. The adjacent node of the first obstacle passed by the connecting line is defined as a new key search node and recorded in Table NODE. The key search node connected to the end point mentioned above is called the upper-level node of the newly defined key search node.

[0050] Step 2: Node search. Connect the newly added key search node in Table NODE with its upper-level search node. Judge whether the connecting line passes through an obstacle. If not, the connecting line is the directed path from the upper-level node to the newly added node and is recorded in Table PATH. If it passes through an obstacle, judge whether the obstacle is a new obstacle (that is, whether the adjacent node of the obstacle has been defined as a key search node and recorded in Table NODE). If the adjacent node of the obstacle has not been defined, update NODE, add the adjacent node as a new key search node, and repeat the connection process in Step 2 to update the directed path in PATH. If the adjacent node of the obstacle has been defined as a key search node (can be found in NODE), expand eight adjacent child nodes outward from this node. The child nodes repeat the connection process in Step 2. The child nodes whose connecting lines do not pass through obstacles are defined as key search nodes, recorded in NODE, and the directed path in PATH is updated. Continue to connect the key search nodes in NODE with the end point, record the new key search nodes, and repeat Step 2 and the above judgment process.

[0051] Step 3: Node check. Check whether there are redundant transition path nodes in the directed paths in PATH. For example, if a directed path is starting point → A → B → C, and actually the starting point can be directly connected to node C, then A and B are redundant transition path nodes. The finally updated directed path is starting point → C. Use the key search nodes and directed paths in Table NODE and Table PATH to form a dynamic directed graph. As the search progresses, the dynamic directed graph is gradually improved, and the shortest path is found from it.

[0052] For the detailed diagram of the DDGA algorithm, see Figure 2 。

[0053] (a) In the figure, the starting point is recorded as the first key search node in the table NODE. Connect the starting point and the ending point, and the connecting line passes through obstacle 1 and obstacle 2. Define the adjacent nodes of obstacle 1 as key search nodes and record them in the table NODE, such as n2 and n3. The starting point is the upper-level node of n2 and n3. (b) In the figure, connect the starting point and n2, and the starting point and n3. Among them, the connecting line between the starting point and n3 does not pass through any obstacle, so the directed path starting point → n3 is recorded in the table PATH. (c) In the figure, the connecting line between the starting point and n2 passes through an obstacle, and the adjacent nodes of this obstacle have been defined as key search nodes (n2, n3). Expand eight adjacent child nodes outward with n2 as the center. Connect the starting point and the child nodes in sequence, and the child nodes whose connecting lines do not pass through any obstacle are defined as new key search nodes and recorded in NODE, such as n4, n5, n6, n7. The directed paths from the starting point to n2 are starting point → n4 → n2, starting point → n5 → n2, starting point → n6 → n2, starting point → n7 → n2, and update the table PATH. (d) In the figure, connect n2 and the ending point, and the connecting line does not pass through any obstacle. Then the directed paths from the starting point passing through n2 to the ending point are starting point → n4 → n2 → ending point, starting point → n5 → n2 → ending point, starting point → n6 → n2 → ending point, starting point → n7 → n2 → ending point, and update the table PATH. Connect n3 and the ending point, and the connecting line passes through obstacle 2. Define the adjacent nodes of obstacle 2 as key search nodes and record them in the table NODE, such as n8 and n9. n3 is the upper-level node of n8 and n9. (e) In the figure, connect n3 and n8, and n3 and n9. The connecting lines do not pass through any obstacle. The directed paths from the starting point to n8 and n9 are starting point → n3 → n8, starting point → n3 → n9, and update the table PATH. (f) In the figure, connect n8 and the ending point, and n9 and the ending point. Among them, the connecting line between n8 and the ending point does not pass through any obstacle. The path from the starting point passing through n8 to the ending point is starting point → n3 → n8 → ending point, and update the table PATH. (g) In the figure, the connecting line between n9 and the ending point passes through an obstacle, and the adjacent nodes of this obstacle have also been defined as key search nodes (n8, n9). Expand eight adjacent child nodes outward with n9 as the center. Connect the ending point and the child nodes in sequence, and the child nodes whose connecting lines do not pass through any obstacle are recorded in NODE, such as n 10 、n 11 、n 12 。 The paths from the starting point passing through n9 to the ending point are starting point → n3 → n9 → n 10 → ending point, starting point → n3 → n9 → n 11 → ending point, starting point → n3 → n9 → n 12→ End point, update table PATH. In figure (h), check whether there are redundant transition path nodes in the directed path in PATH. After checking, n4 and n5 can directly reach the end point. Therefore, in the directed paths starting point → n4 → n2 → end point and starting point → n5 → n2 → end point, n2 is a redundant transition path node. Remove n2, and the updated paths are starting point → n4 → end point and starting point → n5 → end point. Update table PATH. Similarly, n3 can be directly connected to n 11 and n 12 directly. In the directed paths starting point → n3 → n9 → n 11 → end point and starting point → n3 → n9 → n 12 → end point, n9 is a redundant transition path node. Remove n9, and the updated paths are starting point → n3 → n 11 → end point and starting point → n3 → n 12 → end point. Update table PATH. Tables NODE and PATH gradually improve the dynamic directed graph. The final complete directed graph is shown in (i). In figure (i), between the starting point and the end point, the directed path with the minimum two-dimensional distance cost is the final shortest path. The shortest path is starting point → n3 → n8 → end point.

[0054] As can be seen from the above analysis, DDGA extracts the key search nodes in the grid map and constructs a dynamic directed graph for shortest path planning. In Figure 2 (h), DDGA only needs 13 search nodes to achieve the final shortest path planning, effectively reducing the number of search nodes in the graph search algorithm and improving the planning efficiency.

[0055] The DDGA algorithm can also be used for the path planning of flying vehicles. The specific process is shown in Figure 3 . Among them, H flight is the flight height required to fly over the obstacle area; H max is the maximum flight height of the flying vehicle; D ground is the two-dimensional distance cost of the directed path; D flight is the flight height cost of the directed path.

[0056] Step1: The flying vehicle has two motion modes, namely the ground driving mode and the air flight mode. The obstacle area where H flight does not exceed H max is redefined as the to-be-flown obstacle area. The vehicle has the ability to fly over the above area.

[0057] Step 2: The DDGA algorithm plans the multimodal path. It should be noted that directed paths are allowed to cross the area of obstacles to be flown over, and the above-mentioned directed paths will also be recorded in the table PATH; in the dynamic directed graph, the calculation cost of the directed path includes not only the initial two-dimensional distance cost but also the flight altitude cost, ensuring a reasonable switch of the air-ground movement mode. Among the paths between the starting point and the ending point, the directed path with the minimum total cost is the final shortest multimodal path of the flying vehicle.

[0058] In another embodiment of the present invention, a terminal device is provided. The terminal device is installed in a flying car for controlling the route planning of the flying car, including a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a Central Processing Unit (CPU), or may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions to implement the corresponding method flow or corresponding function; the processor described in the embodiment of the present invention can be used for the operation of the method for searching the path planning of a flying vehicle, including the following steps:

[0059] Step 1: Algorithm initialization. Create table NODE and table PATH to record the key search nodes and the directed paths between the nodes respectively. Record the starting point as the first key search node in table NODE. Connect the key search nodes in NODE to the ending point, and the adjacent node of the first obstacle crossed by the connection line is defined as a new key search node and recorded in table NODE. The key search node connected to the ending point mentioned above is called the upper-level node of the newly defined key search node.

[0060] Step 2: Node Search. Connect the newly added key search nodes in the NODE connection table with their upper-level search nodes. Determine whether the connection line passes through an obstacle. If not, this connection line is a directed path from the upper-level node to the newly added node and is recorded in the PATH table. If it passes through an obstacle, determine whether the obstacle is a new obstacle (i.e., whether the adjacent nodes of the obstacle have been defined as key search nodes and are recorded in the NODE table). If the adjacent nodes of the obstacle have not been defined, update the NODE, add the adjacent nodes as new key search nodes, and repeat the connection process in Step 2 to update the directed path in the PATH. If the adjacent nodes of the obstacle have been defined as key search nodes (which can be found in the NODE), then expand eight adjacent child nodes outward from this node. The child nodes repeat the connection process in Step 2, and the child nodes whose connection lines do not pass through obstacles are defined as key search nodes, recorded in the NODE, and the directed path in the PATH is updated. Continue to connect the key search nodes in the NODE with the end point, record the new key search nodes, and repeat Step 2 and the above judgment process.

[0061] Step 3: Node Check. Check whether there are redundant transition path nodes in the directed paths in the PATH. For example, if a directed path is Start → A → B → C, and in fact the start point can be directly connected to the C node, then A and B are redundant transition path nodes. The finally updated directed path is Start → C. Using the key search nodes and directed paths in the NODE table and the PATH table, a dynamic directed graph is constructed. As the search progresses, the dynamic directed graph is gradually improved, and the shortest path is found from it.

[0062] In another embodiment of the present invention, the present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is the memory device in the terminal device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and, of course, the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. And, one or more instructions suitable for being loaded and executed by the processor are also stored in this storage space. 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.

[0063] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the flight vehicle map search path planning method in the above embodiments; the one or more instructions in the computer-readable storage medium are loaded and executed by the processor to perform the following steps:

[0064] Step1: Algorithm initialization. Create Table NODE and Table PATH to record the key search nodes and the directed paths between the nodes respectively. Record the starting point as the first key search node in Table NODE. Connect the key search nodes in NODE with the end point, and the adjacent node of the first obstacle passed by the connection line is defined as a new key search node and recorded in Table NODE. The key search node connected to the end point mentioned above is called the upper-level node of the newly defined key search node.

[0065] Step2: Node search. Connect the newly added key search node in Table NODE with its upper-level search node. Determine whether the connection line passes through an obstacle. If not, the connection line is a directed path from the upper-level node to the newly added node and is recorded in Table PATH. If it passes through an obstacle, determine whether the obstacle is a new obstacle (that is, whether the adjacent node of the obstacle has been defined as a key search node and recorded in Table NODE). If the adjacent node of the obstacle has not been defined, update NODE, add the adjacent node as a new key search node, and repeat the connection process in Step2 to update the directed path in PATH. If the adjacent node of the obstacle has been defined as a key search node (can be found in NODE), expand eight adjacent child nodes outward from this node. The child nodes repeat the connection process in Step2, and the child nodes whose connection lines do not pass through obstacles are defined as key search nodes and recorded in NODE, and the directed path in PATH is updated. Continue to connect the key search nodes in NODE with the end point, record the new key search nodes, and repeat Step2 and the above judgment process.

[0066] Step3: Node check. Check whether there are redundant transition path nodes in the directed path in PATH. For example, if a directed path is starting point → A → B → C, in fact, the starting point can be directly connected to node C, then A and B are redundant transition path nodes. The finally updated directed path is starting point → C. Use the key search nodes and directed paths in Table NODE and Table PATH to form a dynamic directed graph. As the search progresses, the dynamic directed graph is gradually improved, and the shortest path is found from it.

[0067] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can 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.) that contain computer-usable program code.

[0068] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows 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 the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0069] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including instruction means that implement the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device, such that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process, and thus the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0071] Those of ordinary skill in the art will realize that the embodiments described herein are for helping readers understand the implementation methods of the present invention, and it should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific deformations and combinations that do not depart from the essence of the present invention based on the technical revelations disclosed in the present invention, and these deformations and combinations are still within the protection scope of the present invention.

Claims

1. A method for searching path planning of a flying vehicle, characterized in that, The specific steps are as follows: Step1: Input the starting point and the ending point, and connect the starting point as the first key search node to the ending point. Create a connection table NODE and a path table PATH to record the key search nodes and the directed paths between the nodes respectively; Input the starting point and the ending point, and record the starting point in the table NODE as the first key search node. Connect the key search node in NODE to the ending point, and the adjacent node of the first obstacle passed by the connection line is defined as a new key search node and recorded in the table NODE. Step2: Node search; Connect the newly added key search node in the connection table NODE to its upper-level key search node; Determine whether the connection line passes through an obstacle. If not, then this connection line is the directed path from the upper-level key search node to the newly added key search node, and record it in the table PATH. If it passes through an obstacle, then determine whether the obstacle is a new obstacle. If the adjacent node of the obstacle is not defined, then update NODE, add the adjacent node as a new key search node, and repeat the connection process in Step2 to update the directed path in PATH. If the adjacent node of the obstacle has been defined as a key search node, then expand eight adjacent child nodes outward from this node. The child nodes repeat the connection process in Step2, and the child nodes whose connection lines do not pass through obstacles are defined as key search nodes and recorded in NODE, and update the directed path in PATH. Continue to connect the key search nodes in NODE to the ending point, record the new key search nodes, and repeat Step2 and the above judgment process. Step3: Node check; Check whether there are redundant transition path nodes in the directed paths in PATH. If there are transition path nodes, delete the transition path nodes; Use the key search nodes and directed paths in the table NODE and the table PATH to form a dynamic directed graph; As the search progresses, the dynamic directed graph is gradually improved, and find the shortest path from it.

2. The method for searching path planning of a flight vehicle diagram according to claim 1, wherein: Judgment of redundant transition path nodes in Step3: Sequentially judge whether there is a situation where the nodes in a directed path can be directly connected to the nodes in non-adjacent positions. If so, then delete all other nodes between the two nodes, that is, the transition path nodes.

3. A method for searching path planning of a flight vehicle diagram according to claim 1, characterized in that: If the flying vehicle is in the ground driving mode, the adjacent nodes and the eight adjacent child nodes of the obstacle only have nodes in the two-dimensional plane.

4. A method for searching path planning of a flying vehicle diagram according to claim 1, characterized in that: If the flying vehicle is in the air flight mode, there are nodes in the two-dimensional plane and height nodes of the obstacle for the adjacent nodes and eight adjacent child nodes of the obstacle; let H filigh be the flight height required to fly over the obstacle area; H max be the maximum flight height of the flying vehicle; determine whether H fligh is greater than H max . If it is greater, it is defined as the area of the obstacle to be flown over. If it is less, it is defined as the obstacle area.

5. A method for searching path planning of a flight vehicle diagram according to claim 1, characterized in that: Let D ground be the two-dimensional distance cost of a directed path; D flight be the flight altitude cost of a directed path; The total cost of a directed path through the area of obstacles to be flown contains both D ground and D flight , while the directed path that does not pass through the above area only contains D ground ; Find the path with the minimum cost, that is, the shortest distance, from all the directed paths.

6. A computer terminal device, characterized in that: This terminal device is installed in the flying car to control the route planning of the flying car, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the flight vehicle graph search path planning method described in any one of claims 1 to 5.

7. A computer-readable storage medium, characterized in that: A computer program is stored on a computer-readable storage medium. When the program is executed by a processor, it implements the flight vehicle graph search path planning method described in any one of claims 1 to 5.

Images