Dynamic path planning method and system of hovercar, flight equipment and medium

Abstract

The invention discloses a dynamic path planning method and system for a hovercar, flight equipment and a medium, and belongs to the field of hovercar path planning, and the method comprises the following steps: judging whether a sampling point is in an obstacle, selecting a node closest to the verified sampling point in a search tree or a target tree, and determining whether the node is in the obstacle; calculating to-be-expanded nodes according to the dynamic step length, adding the to-be-expanded nodes to the search tree or the target tree for expansion after the to-be-expanded nodes pass safety distance detection, and repeating the steps until the search tree and the target tree are connected to obtain a plurality of complete paths; and evaluating the plurality of complete paths by using an obstacle distance evaluation function and a target point distance evaluation function, and selecting to obtain an optimal path. According to the invention, the improved bidirectional fast extended random tree algorithm and the DWA algorithm are fused, so that the problem that the existing global path and local path planning algorithm cannot accurately avoid complex obstacles is solved.

Description

Technical Field

[0001] The present invention belongs to the field of flying car path planning, and in particular relates to a flying car dynamic path planning method, system, flying equipment and medium. Background Art

[0002] As an emerging means of transportation, flying cars have higher requirements for path planning due to their power systems and flight mechanisms. In complex urban airspace, flying cars must face dynamic obstacles such as buildings, other aircraft, and bad weather during flight. These factors make it difficult for traditional path planning methods to take into account both global optimization and local obstacle avoidance. Existing global path planning algorithms perform poorly when faced with complex obstacles, while local path planning algorithms are prone to falling into local optimal solutions and have limited response speeds, making flying car path planning more complicated in urban airspace. Summary of the invention

[0003] The purpose of the present invention is to provide a dynamic path planning method, system, flight equipment and medium for a flying car, which integrates an improved bidirectional rapidly expanding random tree (Bidirectional Rapidly-exploring Random Trees, Bi-RRT) algorithm and a DWA (Dynamic Window Approach, DWA) algorithm to solve the problem that existing global path and local path planning algorithms cannot accurately avoid complex obstacles.

[0004] In order to solve the above technical problems, the embodiment of the present application provides a dynamic path planning method for a flying car, comprising the following steps: Construct a three-dimensional space and determine the starting and destination points of the flying car; The starting point and the target point are used as root nodes to expand the search tree and the target tree respectively, and a sampling point is randomly selected in the three-dimensional space to verify whether the sampling point is within the obstacle. If the sampling point is within the obstacle, the sampling point is discarded and another sampling point is selected again until it is verified that the current sampling point is not within the obstacle. Select the node in the search tree or target tree that is closest to the sampling point after verification, and calculate the node to be expanded according to the dynamic step size. After the node to be expanded passes the safety distance detection, add it to the search tree or target tree for expansion, and repeat the above steps until the search tree and the target tree are connected to obtain multiple complete paths; The plurality of complete paths are evaluated using an obstacle distance evaluation function and a target point distance evaluation function to select an optimal path.

[0005] In order to solve the above technical problems, the present application embodiment provides a dynamic path planning system for a flying car, including: A three-dimensional space construction module is used to construct a three-dimensional space and determine the starting point and target point of the flying car; A sampling point random selection module is used to use the starting point and the target point as root nodes to expand the search tree and the target tree respectively, randomly select a sampling point in the three-dimensional space, and verify whether the sampling point is within the obstacle. If the sampling point is within the obstacle, the sampling point is discarded and another sampling point is selected again until it is verified that the current sampling point is not within the obstacle; A complete path planning module is used to select the node in the search tree or the target tree that is closest to the verified sampling point, and obtain the node to be expanded according to the dynamic step length calculation. After the node to be expanded passes the safety distance detection, it is added to the search tree or the target tree for expansion, and the above steps are repeated until the search tree and the target tree are connected to obtain multiple complete paths; The optimal path selection module is used to evaluate the multiple complete paths using an obstacle distance evaluation function and a target point distance evaluation function to select the optimal path.

[0006] In order to solve the above technical problems, an embodiment of the present application provides a flying device, including a memory and a processor, wherein a computer program is stored in the processor, and when the processor executes the computer program, the steps of the dynamic path planning method of a flying car are implemented.

[0007] In order to solve the above technical problems, an embodiment of the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the dynamic path planning method of a flying car are implemented.

[0008] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a dynamic path planning method for a flying car. The method comprises the following steps: taking a starting point and a target point as root nodes to respectively expand a search tree and a target tree, randomly selecting a sampling point in the three-dimensional space, verifying whether the sampling point is within an obstacle, discarding the sampling point if the sampling point is within the obstacle, and reselecting another sampling point until verifying that the current sampling point is not within the obstacle; selecting a node in the search tree or the target tree that is closest to the verified sampling point, and obtaining a node to be expanded according to a dynamic step length calculation, adding the node to be expanded to the search tree or the target tree after passing a safety distance detection, and repeating the above steps until a plurality of complete paths are obtained by connecting the search tree and the target tree; and selecting an optimal path after evaluating the plurality of complete paths using an obstacle distance evaluation function and a target point distance evaluation function. This method combines the global planning capability of the improved Bi-RRT algorithm with the local obstacle avoidance advantage of the DWA algorithm. It can not only ensure the global optimality of the flight path, but also realize flexible and real-time obstacle avoidance operations in complex and changeable flight environments. By setting a safe distance, it ensures that the flying car can avoid collisions when executing the path, while improving the efficiency and safety of path planning, so as to better adapt to the needs of flying cars in complex urban airspace and accurately avoid obstacles when facing complex obstacles. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 A schematic diagram of the structure of a flight device provided by an embodiment of the present invention; Figure 2 A schematic diagram of a safety distance provided by an embodiment of the present invention; Figure 3 A schematic diagram of a flow chart of a dynamic path planning method provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the fusion algorithm flow of the present invention; Figure 5 A schematic diagram of a flow chart of path detection performed by a flight device according to an embodiment of the present invention; Figure 6 A path planning diagram of the fusion algorithm provided in an embodiment of the present invention; Figure 7 A path planning diagram for a fusion algorithm provided in an embodiment of the present invention in which there are dynamic obstacles; Figure 8 A schematic diagram of the structure of a dynamic path planning system for a flying device provided by an embodiment of the present invention; In the figure, 1. Top box fixing device; 2. Data processor; 3. LiDAR; 4. GPS; 5. Camera; 6. Temperature and humidity sensor; 7. Inertial measurement unit; 8. Flying car thrust device; 9. Memory. DETAILED DESCRIPTION

[0010] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by technicians in the technical field to which this application belongs; the terms used in the specification of the application are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" in the specification and claims of this application and the above-mentioned figure descriptions and any variations thereof are intended to cover non-exclusive inclusions.

[0011] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0012] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0013] like Figure 1 As shown, this embodiment provides a specific flying car as a flying device, and a top box fixing device 1, a data processor 2, a laser radar 3, a GPS 4, a camera 5, a temperature and humidity sensor 6, an inertial measurement unit (IMU) 7, a flying car thrust device 8 and a memory 9 are installed on the flying car, wherein the data processor 2 is installed at the center of the flying car top box, and is used to process and manage the data collected by the sensor, and to calculate, store and analyze the data. The data processor 2 stores a computer program, and the data processor 2 implements the steps of a dynamic path planning method for a flying car when executing the computer program. The laser radar 3 is installed on both sides of the flying car top box, and is used to identify obstacles, buildings, etc., and provide high-precision map data. The memory 9 is connected to the data processor, and is used to store and provide the necessary computer program functions so that the processor can perform corresponding calculations and operations according to these programs.

[0014] The data processor 2 is an integration of a central processing unit (CPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), etc. It is the computing core and control core of the terminal, which is suitable for implementing one or more instructions, and is specifically suitable for loading and executing one or more instructions in a computer storage medium to implement a corresponding method flow or a corresponding function; the processor described in the embodiment of the present invention can be used for the operation of a dynamic path planning method for a flying car.

[0015] GPS 4 is installed on the rear side of the flying car top box to provide real-time location information and determine the current location of the flying car or dynamic obstacles. Cameras 5 are installed around the flying car to obtain information about the surrounding environment. Temperature and humidity sensors 6 are installed on the rear side of the flying car to measure temperature and humidity data in the environment and predict weather changes. Inertial measurement unit 7 is installed on the rear side of GPS 4 to measure the acceleration, angular velocity and direction of the flying car. Flying car thrust devices 8 are installed on both sides of the tail of the flying car to change the flight speed and direction.

[0016] like Figure 3 As shown, this embodiment provides a dynamic path planning method for a flying car, which is used for the specific flying car provided in the above embodiment, and includes the following steps: S1, build the above flying car structure and construct the three-dimensional space: use the environmental information obtained by the sensor and combine it with MATLAB to build a three-dimensional simulation space, without considering the take-off and landing of the flying car.

[0017] S1.1, a high-precision three-dimensional point cloud is generated by LiDAR 3, and the camera 5 provides visual information. The sensor data is processed and fused in combination with MATLAB to create a detailed three-dimensional space with a size of (8000, 8000, 300) in meters.

[0018] S1.2, use the GPS coordinate system to determine the starting point of the flying car and target point , unit is m.

[0019] S2, set initialization parameters: set the dynamic step size, heuristic function, and safety distance parameters between the path and obstacles based on the detected environmental information to ensure flight safety.

[0020] S2.1, set the heuristic function: when the obstacles in the environment are densely distributed, a large fixed probability will cause the search tree to be overly biased towards the target point when sampling and fall into a local trap; when the environment is relatively empty, a small fixed probability will lead to slow convergence. Set the heuristic function Instead of fixing the probability, the formula is as follows: (1) In the formula, is the initial value of probability; is the rate of change of derivative; is the independent variable.

[0021] S2.2, set dynamic step size: the obstacle distribution in complex environments is usually uneven. Compared with the fixed step size, the dynamic step size can make full use of the known environmental information to adjust the current expansion step size to an appropriate size. Expand the search tree; in the middle of the iteration, the search tree is initially formed and the selection To expand; in the later iteration, the search space is small, use Set the dynamic step size , the formula is as follows: (2) In the formula, and are the minimum and maximum step lengths respectively; is the shortest distance between the search tree and the target point; The current number of nodes in the search tree.

[0022] S2.3, set safety distance: Figure 2 As shown, is the node to be expanded. for The parent node of is the road section to be detected, and At the same time about and the vertical plane in which it lies, and On the same vertical plane Symmetric. The distance between , This is the safety distance, set to 2m. Perform collision detection at the same time. If no collision occurs, For the passable road section, is an expandable node; if at least one line segment collides, then There are safety risks and resampling is required.

[0023] S3, design evaluation function: evaluate the obstacle distance and target point distance, and determine the score of each path by weighted combination of these factors in order to select the optimal path.

[0024] S3.1, obstacle distance evaluation function: the information of known obstacles is used as the input of the collision detection function, and the information of unknown obstacles is used as the obstacle distance evaluation function The inertial measurement unit is used to collect data such as the flying car's speed and angular velocity. The obstacles within are judged as threatening obstacles. The evaluation function formula for judging obstacle distance is as follows: (3) In the formula, Used to measure the shortest distance between the current complete trajectory and the obstacle. The larger the distance, the higher the score; and are the linear velocity and angular velocity of the flying car (scalar); For speed The shortest distance between the flying car and obstacles; The distance radius set with the flying car as the center.

[0025] S3.2, target point distance evaluation function: measures the shortest distance between the current predicted trajectory of the flying car and the target point. The target point distance evaluation function and the total evaluation function formula are as follows: (4) (5) In the formula, is the target point distance evaluation function; For flying cars The shortest distance between the predicted trajectory and the target point at speed; is the distance threshold; is the total evaluation function; is the deviation between the current heading of the flying car and the direction of the target point; Used to adjust the speed; and are the coefficients of each sub-function respectively.

[0026] S4, Fusion Algorithm Path Planning: Combine the global path planning of Bi-RRT algorithm with the local obstacle avoidance of DWA algorithm, such as Figure 4 As shown, the optimal path of the flying car is planned and smoothed.

[0027] S4.1, create two tree search trees and target tree , respectively from and Start expanding.

[0028] S4.2, use the camera to capture the environment image and randomly select a point in space , and verify the random point Is it within the obstacle? If it is within the obstacle, discard the point and repeat this step. The random point formula is as follows: (6) (5) In the formula, and are sampling points and target points respectively; They are all random values ​​taken from a uniform probability distribution; The output value of is the sampling probability of the search tree for the target point; is the increment of the independent variable, Is the collision detection function; , indicating that the path is passable; Indicates that the paths collided.

[0029] S4.3, select the search tree The closest node ,calculate arrive , get the new node , and make a collision safety distance If no collision occurs, the road is passable. is an expandable node. If at least one line segment collides, there is a safety hazard in the connecting segment. Repeat S4.2 to generate a new random point . Expand from the target tree in the same way. The formula for the nearest node and the new node is as follows: (8) (9) S4.4, new nodes to be passed Added to the current tree, the parent node of the new node is set to , maintaining the structure of the tree, the formula is as follows: (10) S4.5, repeat steps S4.2 and S4.3 to generate new random points and expand until the search tree and the target tree are successfully connected. Use a safe distance , detect whether the search tree and the target tree meet. If they do, try to connect the two trees to form a complete path. The safety distance detection formula is as follows: (11) S4.6, combining the obstacle distance evaluation function and the target point distance evaluation function, selects the optimal simulated motion path, moves along the optimal path of global planning, and avoids local unknown obstacles.

[0030] S4.7, use B-spline curve to smooth the planned path and eliminate the more tortuous path at the nodes to make the path more continuous and smooth, such as Figure 6 As shown, the gray one is a static obstacle with a height of 230m.

[0031] S5, path execution: Generate flight control instructions according to the planned path, and receive signals through the data processor 2 to guide the flying car to perform corresponding operations.

[0032] S5.1, Generate flight control instructions: The system uses the PID controller to generate detailed control instructions based on the optimal path, covering the position, speed and other parameters of each node to ensure that the flying car smoothly executes the entire flight process.

[0033] S5.2, data processor processing instructions: use the data processor to receive and analyze control instruction parameters, convert them into recognizable signals, and accurately transmit them to the flying car control system.

[0034] S5.3, guiding the flying car to perform operations: The processed instructions are transmitted to the control system through the data processor, driving the flying car to adjust its attitude and speed, accurately perform flight operations, and safely reach the destination along the planned path.

[0035] S6, such as Figure 5 As shown in the figure, the flying car performs path detection, monitors the surrounding environment in real time through sensor data, identifies and predicts the location and movement of obstacles, and automatically adjusts the flight trajectory, such as Figure 7 As shown in the figure, the yellow path represents a safe path without dynamic obstacles; the blue and green spheres represent the moving starting point and end point of each dynamic obstacle, respectively. The radius of the dynamic obstacle is assumed to be between 25 and 30 meters; and the red area represents the area affected by local weather changes.

[0036] S6.1, when a dynamic obstacle is detected, the system identifies the obstacle and predicts its motion trajectory by fusing the data of the laser radar 3 and the camera 5. If the obstacle is less than the set safety distance from the flying car, the system will re-execute S4.3 to generate new random sampling points. At this time, the flying car's system will issue an alarm in time and automatically adjust the flight trajectory to ensure flight safety.

[0037] S6.2, when encountering special weather conditions, the temperature and humidity sensor 6 will monitor the temperature and humidity of the environment in real time. If high humidity is detected, the system will promptly issue an alarm and re-execute S4.3 to generate new random sampling points. The system will automatically adjust the flight trajectory to cope with changing weather conditions.

[0038] The dynamic path planning method provided in this embodiment combines the global path planning of the Bi-RRT algorithm with the local obstacle avoidance of the dynamic window algorithm to avoid obstacles in real time and maintain the smoothness of the path; the safe distance between nodes is designed to ensure that the flying car can avoid collisions when executing the path, and the planned path is used to guide the flying car to perform corresponding operations through sensors. Real-time monitoring of environmental temperature and humidity, automatic adjustment of flight trajectory to deal with special weather. The flying car combines global optimal path planning, real-time obstacle avoidance capabilities and automatic adjustment of environmental monitoring and other functions to ensure stability and safety under different climatic conditions and improve flight efficiency.

[0039] like Figure 8 As shown, this embodiment provides a dynamic path planning system for a flying car, including: a three-dimensional space construction module, a sampling point random selection module, a complete path planning module and an optimal path selection module; The three-dimensional space construction module is used to construct the three-dimensional space and determine the starting point and target point of the flying car; after determining the starting point and target point of the flying car, the initialization parameters are set.

[0040] A sampling point random selection module is used to use the starting point and the target point as root nodes to expand the search tree and the target tree respectively, randomly select a sampling point in the three-dimensional space, and verify whether the sampling point is within the obstacle. If the sampling point is within the obstacle, the sampling point is discarded and another sampling point is selected again until it is verified that the current sampling point is not within the obstacle; A complete path planning module is used to select the node in the search tree or the target tree that is closest to the verified sampling point, and obtain the node to be expanded according to the dynamic step length calculation. After the node to be expanded passes the safety distance detection, it is added to the search tree or the target tree for expansion, and the above steps are repeated until the search tree and the target tree are connected to obtain multiple complete paths; The complete path planning module includes: The safety distance detection module is used to detect whether the distance between the section to be detected and the section to be detected meets the safety distance, taking the line between the node to be expanded and its corresponding parent node as the section to be detected, and the section to be detected symmetrically on the vertical plane where the section to be detected is located, and the section to be detected symmetrically on the vertical plane. If at least one of the sections does not meet the safety distance, a sampling point is randomly selected in the three-dimensional space again.

[0041] The optimal path selection module is used to evaluate the multiple complete paths using an obstacle distance evaluation function and a target point distance evaluation function to select the optimal path.

[0042] The optimal path selection module includes: An obstacle distance evaluation module is used to obtain the linear velocity and angular velocity of the flying car, and use the obstacle distance evaluation function to evaluate the shortest distance between the current complete path and the obstacle and then output an obstacle distance score value. The greater the shortest distance between the complete path and the obstacle, the higher the obstacle distance score value; A target point distance evaluation module is used to combine the linear velocity and angular velocity of the flying car, and use the target point distance evaluation function to evaluate the shortest distance between the current complete path and the target point, and then output a target point distance score value. The greater the shortest distance between the complete path and the target point, the higher the target point distance score value; The weighted evaluation module is used to obtain the deviation between the current heading of the flying car and the direction of the target point, and after adjusting the linear speed and angular speed of the flying car according to the deviation, the total score of the multiple complete paths is obtained after weighted combination in combination with the obstacle distance score and the target point distance score; the optimal path is selected by comparing the total score of the multiple complete paths, and the optimal path is smoothed by using a B-spline curve.

[0043] This embodiment 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 a dynamic path planning method for a flying car in the above embodiment.

[0044] 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.

[0045] 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.

[0046] 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 1 A function specified in one or more boxes.

[0047] 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.

[0048] 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 dynamic path planning method for a flying car, characterized in that: The following steps are involved: Construct a three-dimensional space and determine the starting and destination points of the flying car; The starting point and the target point are used as root nodes to expand the search tree and the target tree respectively, and a sampling point is randomly selected in the three-dimensional space to verify whether the sampling point is within the obstacle. If the sampling point is within the obstacle, the sampling point is discarded and another sampling point is selected again until it is verified that the current sampling point is not within the obstacle. Select the node in the search tree or target tree that is closest to the sampling point after verification, and calculate the node to be expanded according to the dynamic step size. After the node to be expanded passes the safety distance detection, add it to the search tree or target tree for expansion, and repeat the above steps until the search tree and the target tree are connected to obtain multiple complete paths; The plurality of complete paths are evaluated using an obstacle distance evaluation function and a target point distance evaluation function to select an optimal path.

2. A method for dynamic path planning of a flying car according to claim 1, characterized in that: The following steps are also included: After determining the starting point and the target point of the flying car, the heuristic function is set and then the starting point and the target point are used as root nodes to expand the search tree and the target tree respectively.

3. The dynamic path planning method for a flying car according to claim 1, characterized in that: The step of the node to be expanded passing the safety distance detection specifically includes: The line between the node to be expanded and its corresponding parent node is the section to be detected. The sections symmetrical about the vertical plane where the section to be detected is located, and the sections symmetrical about the section to be detected on the vertical plane, are detected to see whether the distance between them and the section to be detected meets the safety distance. If at least one of the sections does not meet the safety distance, a sampling point is randomly selected in the three-dimensional space again.

4. The method for dynamic path planning of a flying car according to claim 1, characterized in that: The step of evaluating the plurality of complete paths using the obstacle distance evaluation function specifically includes: The linear velocity and angular velocity of the flying car are obtained, and the obstacle distance evaluation function is used to evaluate the shortest distance between the current complete path and the obstacle, and then the obstacle distance score value is output. The greater the shortest distance between the complete path and the obstacle, the higher the obstacle distance score value.

5. The method for dynamic path planning of a flying car according to claim 4, characterized in that: The step of evaluating the plurality of complete paths using the target point distance evaluation function specifically includes: Combining the linear velocity and angular velocity of the flying car, and using the target point distance evaluation function to evaluate the shortest distance between the current complete path and the target point, the target point distance score value is output. The greater the shortest distance between the complete path and the target point, the higher the target point distance score value.

6. A method for dynamic path planning of a flying car according to claim 5, characterized in that: The step of evaluating the plurality of complete paths by using an obstacle distance evaluation function and a target point distance evaluation function and then selecting the optimal path specifically comprises: Obtaining the deviation between the current heading of the flying car and the direction of the target point, and adjusting the linear speed and angular speed of the flying car according to the deviation, and combining the obstacle distance score value and the target point distance score value for weighted combination to obtain the total score value of the multiple complete paths; By comparing the total score values ​​of the multiple complete paths, the optimal path is selected.

7. The method for dynamic path planning of a flying car according to claim 1, characterized in that: The following steps are also included: The optimal path is smoothed using a B-spline curve.

8. A dynamic path planning system for a flying car, characterized in that: include: A three-dimensional space construction module is used to construct a three-dimensional space and determine the starting point and target point of the flying car; A sampling point random selection module is used to use the starting point and the target point as root nodes to expand the search tree and the target tree respectively, randomly select a sampling point in the three-dimensional space, and verify whether the sampling point is within the obstacle. If the sampling point is within the obstacle, the sampling point is discarded and another sampling point is selected again until it is verified that the current sampling point is not within the obstacle; A complete path planning module is used to select the node in the search tree or the target tree that is closest to the verified sampling point, and obtain the node to be expanded according to the dynamic step length calculation. After the node to be expanded passes the safety distance detection, it is added to the search tree or the target tree for expansion, and the above steps are repeated until the search tree and the target tree are connected to obtain multiple complete paths; The optimal path selection module is used to evaluate the multiple complete paths using an obstacle distance evaluation function and a target point distance evaluation function to select the optimal path.

9. A flying device, characterized in that: The method comprises a memory and a processor, wherein a computer program is stored in the processor, and when the processor executes the computer program, the steps of the dynamic path planning method for a flying car as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a dynamic path planning method for a flying car according to any one of claims 1 to 7 are implemented.

Images