A method and apparatus for transforming large unmanned vehicles

Abstract

The application discloses a transformation method and device for large-scale unmanned vehicle architecture, the method comprising: dividing the original architecture unmanned vehicle cluster into a plurality of first sub-regions based on the first region attribute corresponding to each unmanned vehicle in the original architecture unmanned vehicle cluster; dividing the target architecture unmanned vehicle cluster into a plurality of second sub-regions based on the second region attribute corresponding to each unmanned vehicle in the target architecture unmanned vehicle cluster; performing region pairing on the plurality of first sub-regions and the plurality of second sub-regions to generate a region pairing result; pairing the original architecture unmanned vehicle and the target architecture unmanned vehicle based on the region pairing result to obtain a plurality of paired nodes; and performing dynamic obstacle avoidance processing on each of the plurality of paired nodes to generate a path planning of the unmanned vehicle architecture. Thus, the complexity of calculating the path planning can be reduced from O(N!) to O(MN 2 ), the calculation time of the path planning is effectively reduced, and the efficiency of the path planning task is improved.

Description

Technical Field

[0001] This invention belongs to the field of image processing technology, and in particular relates to a transformation method and apparatus for large-scale unmanned structures. Background Technology

[0002] The rapid development of drone technology has led to the widespread application of drones in various civilian fields, including military, aerial filming, environmental monitoring, geographic surveying, and power line inspection. Faced with increasingly complex mission requirements, single drones can hardly complete tasks independently; therefore, multi-drone collaborative mission execution has emerged. Drone path planning is the core of drone collaborative control, making research on multi-drone collaborative path planning of great significance.

[0003] Multi-UAV cooperative path planning essentially involves coordinating the paths of multiple UAVs to complete a collaborative task. Existing path planning methods based on graph search and sampling are highly efficient and exhibit excellent global optimization performance in environmental search; however, these algorithms face dynamic obstacle avoidance and communication problems in large-scale environments. Heuristic path planning methods, such as ant colony optimization, particle swarm optimization, bee colony optimization, genetic algorithms, and simulated annealing, can effectively plan paths and allocate tasks in complex, dynamic, and multi-constraint environments, but they suffer from limitations such as high computational cost and susceptibility to local optima. Learning-based algorithms can adjust their strategies by continuously learning new information from the environment, exhibiting strong adaptability and suitability for dynamic and uncertain environments. However, learning algorithms are heavily reliant on large-scale, high-quality training data; insufficient or inaccurate data can significantly degrade performance, and their interpretability is poor, hindering system debugging and optimization.

[0004] Existing multi-UAV cooperative path planning algorithms primarily address dynamic obstacle avoidance and search coverage problems, with limited coverage of multi-UAV configuration transformations. When transforming multi-UAV configurations, the manual task allocation method, which pre-specifies the target point locations of UAVs, does not consider constraints such as shortest path, minimum energy, or optimal time for task allocation. Traditional algorithms only consider path planning after task allocation; the manual allocation method is time-consuming and unsuitable for transformations of arbitrary configurations, especially as the number of UAVs in the formation increases, significantly increasing the difficulty of task allocation and path planning. Summary of the Invention

[0005] This invention provides a method and apparatus for transforming the configuration of large-scale unmanned aerial vehicles (UAVs); the method can reduce the computation time in the path planning process of transforming the original configuration of the UAV swarm into the target configuration, and improve the path planning efficiency.

[0006] According to a first aspect of the present invention, a method for transforming large-scale unmanned aerial vehicle (UAV) configurations is provided. The method includes: dividing the UAV swarm of the original configuration into several first sub-regions based on a first region attribute corresponding to each UAV in the original configuration; dividing the UAV swarm of the target configuration into several second sub-regions based on a second region attribute corresponding to each UAV in the target configuration; performing region pairing on the several first sub-regions corresponding to the original configuration and the several second sub-regions corresponding to the target configuration to generate region pairing results; performing node pairing on the UAVs of the original configuration and the UAVs of the target configuration based on the region pairing results to obtain several paired nodes; and performing dynamic obstacle avoidance processing on each of the several paired nodes to generate a path plan for the UAV configuration.

[0007] Optionally, the method further includes: constructing a first coordinate system using the centroid of the original configuration drone swarm as the origin; constructing a second coordinate system using the centroid of the target configuration drone swarm as the origin; for any drone in the original configuration: determining first local coordinate information of the drone in the first coordinate system based on the drone's original coordinates in the world coordinate system and the origin coordinates of the first coordinate system; determining a first angle between the drone's oxy plane projection in the first coordinate system and the X-axis based on the first local coordinate information; determining a first region attribute of the drone based on the first angle and a preset sub-region corresponding to the original configuration; for any drone in the target configuration: determining second local coordinate information of the drone in the second coordinate system based on the drone's original coordinates in the world coordinate system and the origin coordinates of the second coordinate system; determining a second angle between the drone's oxy plane projection in the second coordinate system and the X-axis based on the second local coordinate information; and determining a second region attribute of the drone based on the second angle and a preset sub-region corresponding to the target configuration.

[0008] Optionally, the method further includes: optimizing the regional attributes corresponding to each UAV in the first sub-region and the second sub-region respectively; the optimization of the regional attributes corresponding to each UAV in the first sub-region includes: for any target sub-region in the plurality of first sub-regions: determining the centroid position corresponding to the target sub-region based on the centroid position of each UAV in the target sub-region in the world coordinate system; for any UAV in the target sub-region: determining a first distance between the UAV and the target sub-region based on the centroid position of the UAV and the centroid position of the target sub-region; selecting at least two adjacent sub-regions corresponding to the target sub-region from the plurality of first sub-regions; determining the first distance between the UAV and each of the adjacent sub-regions to obtain at least two first distances; determining the sub-region corresponding to the smallest first distance among the at least three first distances as the region to which the UAV belongs, and updating the regional attributes of the UAV based on the attributes of the selected region; recalculating the centroid position corresponding to the target sub-region based on the updated regional attributes of the UAV; repeating the above steps until the number of iterations meets a preset threshold or the centroid position corresponding to the target sub-region does not change, then ending the step of updating the regional attributes corresponding to each UAV in the target sub-region.

[0009] Optionally, the step of performing region pairing on the several first sub-regions corresponding to the original configuration and the several second sub-regions corresponding to the target configuration to generate region pairing results includes: determining the distance between each first sub-region and each second sub-region based on the first centroid position corresponding to each first sub-region in the original configuration and the second centroid position corresponding to each second sub-region in the target configuration to obtain a distance matrix; and using the Hungarian pairing algorithm to perform region pairing on the distance matrix to generate region pairing results.

[0010] Optionally, based on the region pairing results, the original configuration UAV and the target configuration UAV are paired node by node to obtain several paired nodes; this includes: for any paired region in the region pairing results: obtaining a first sub-region and a second sub-region corresponding to the paired region; if the first sub-region and the second sub-region have the same number of UAV nodes, then for any target node in the first sub-region: searching for a paired node corresponding to the target node in the second sub-region based on the shortest path principle to obtain several paired nodes; if the number of UAV nodes in the first sub-region is greater than the number of UAV nodes in the second sub-region, then for any target node in the second sub-region: searching for a paired node corresponding to the target node in the first sub-region based on the shortest path principle. For unpaired nodes in the first sub-region: select adjacent sub-regions from several second sub-regions; search for paired nodes corresponding to the unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes; if the number of drone nodes in the second sub-region is greater than the number of drone nodes in the first sub-region, then for any target node in the first sub-region: search for paired drones corresponding to the target node in the second sub-regions based on the shortest path principle; for unpaired nodes in the second sub-region: select adjacent sub-regions from several first sub-regions; search for paired nodes corresponding to the unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes.

[0011] Optionally, the method further includes: performing global optimization on each paired node based on the principle of shortest path between paired nodes, and outputting the optimal paired node; the step of performing global optimization on each paired node based on the principle of shortest path between paired nodes and outputting the optimal paired node includes: for any paired node among the plurality of paired nodes: obtaining the starting node corresponding to the original configuration and the target node corresponding to the target configuration in the paired node; determining the ideal path of the UAV corresponding to the paired node based on the coordinate information corresponding to the starting node and the coordinate information corresponding to the target node; sorting the ideal paths of the UAV corresponding to each of the plurality of paired nodes in descending order of length, and generating a sorting result; performing UAV node replacement operation on the paired nodes in the plurality of paired nodes in sequence according to the sorting result; if the ideal path corresponding to the paired node after the replacement operation is shorter than the original paired node; then replacing the original paired node with the replaced paired node; repeating the above steps until the total length of the UAV ideal paths generated by the plurality of paired nodes remains unchanged, then ending the UAV node replacement operation in the paired nodes and outputting the optimal paired node.

[0012] Optionally, the step of performing dynamic obstacle avoidance processing on each of the plurality of paired nodes to generate path planning for the unmanned vehicle configuration includes: obtaining a plurality of ideal paths based on the ideal path of the unmanned vehicle corresponding to each of the plurality of paired nodes; sorting the plurality of ideal paths in ascending order of length, and numbering the starting node of the unmanned vehicle corresponding to each of the plurality of paired nodes according to the sorting result; for any of the plurality of paired nodes: expanding the search nodes for the starting node corresponding to the paired node; and searching from the search nodes for a node that satisfies the minimum path cost and meets the safety constraints as a path node; and so on. The path node serves as the next starting node, and the path node search operation continues until the drone reaches the target node. A drone flight path is generated corresponding to the paired node. The path nodes in the search operation are set as temporary obstacles, and the target node is set as a fixed obstacle. The safety constraint indicates that the node is not a temporary or fixed obstacle at the current moment during the search operation. Following the numbering order, the above path node search operation is performed on each of the paired nodes sequentially until each drone in the drone cluster reaches its corresponding target node, generating a path plan for the drone configuration.

[0013] According to a second aspect of the present invention, a transformation device for large-scale unmanned aerial vehicle (UAV) configurations is also provided. The device includes: a first sub-region module, configured to divide the UAV cluster of the original configuration into several first sub-regions based on a first region attribute corresponding to each UAV in the original configuration; a second sub-region module, configured to divide the UAV cluster of the target configuration into several second sub-regions based on a second region attribute corresponding to each UAV in the target configuration; a region pairing module, configured to perform region pairing between the several first sub-regions corresponding to the original configuration and the several second sub-regions corresponding to the target configuration, generating region pairing results; a node pairing module, configured to perform node pairing between the UAVs of the original configuration and the UAVs of the target configuration based on the region pairing results, obtaining several paired nodes; and a dynamic obstacle avoidance processing module, configured to perform dynamic obstacle avoidance processing on each of the several paired nodes, generating path planning for the UAV configuration.

[0014] According to a third aspect of the present invention, an electronic device is also provided, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the method as described in the first aspect.

[0015] According to a fourth aspect of the present invention, a computer-readable medium is also provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the method described in the first aspect.

[0016] This invention provides a method and apparatus for transforming large-scale unmanned aerial vehicle (UAV) configurations. The method includes: first, dividing the original configuration UAV swarm into several first sub-regions based on a first region attribute corresponding to each UAV in the original configuration; second, dividing the target configuration UAV swarm into several second sub-regions based on a second region attribute corresponding to each UAV in the target configuration; then, performing region pairing between the first sub-regions corresponding to the original configuration and the second sub-regions corresponding to the target configuration to generate region pairing results; finally, based on the region pairing results, performing node pairing between the UAVs in the original configuration and the UAVs in the target configuration to obtain several paired nodes; and performing dynamic obstacle avoidance processing on each of the paired nodes to generate path planning for the UAV configuration. This embodiment of the transformation method for large-scale UAV configurations adopts a regional strategy and combines consecutive steps of region attribute optimization, region pairing, node pairing, and paired node optimization. This not only achieves the globally optimal path planning result for the UAV swarm but also reduces the computational complexity from O(N!) to O(MN). 2 M≤N; thus effectively reducing the computation time of path planning and improving the efficiency of path planning tasks. Attached Figure Description

[0017] The following sections will describe some specific embodiments of the invention in detail by way of example and not limitation, with reference to the accompanying drawings. The same reference numerals in the drawings denote the same or similar parts or portions. Those skilled in the art should understand that these drawings are not necessarily drawn to scale. In the drawings:

[0018] Figure 1 This is a flowchart illustrating a method for transforming large-scale unmanned structures according to an embodiment of the present invention.

[0019] Figure 2 A flowchart illustrating a method for transforming large-scale unmanned structures, as provided in another embodiment of the present invention;

[0020] Figure 3 This is a schematic diagram of a conversion device for large-scale unmanned structures, provided as an embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of the embodiments of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0022] A primitive drone swarm configuration typically refers to the state of a drone swarm as it naturally forms or follows a basic assembly pattern before initial deployment or before executing a specific mission plan. It is generally based on simple networking and distribution, without specific formation or structural design for a particular mission. A target-configuration drone swarm configuration, on the other hand, is a carefully planned and designed formation, structure, or layout that the drone swarm aims to achieve to maximize mission performance, based on specific mission requirements, environmental conditions, and tactical needs.

[0023] This embodiment solves the path planning problem of transforming a drone swarm from its original configuration to a target configuration. For example... Figure 1 The diagram shown is a flowchart illustrating a method for transforming large-scale unmanned structures according to an embodiment of the present invention.

[0024] A method for transforming the configuration of large-scale unmanned structures includes at least the following steps:

[0025] S101, based on the first region attribute corresponding to each drone in the original configuration drone cluster, divide the original configuration drone cluster into several first sub-regions.

[0026] S102, based on the second region attribute corresponding to each drone in the drone cluster of the target configuration, divide the drone cluster of the target configuration into several second sub-regions;

[0027] S103, perform region pairing on several first sub-regions corresponding to the original configuration and several second sub-regions corresponding to the target configuration to generate region pairing results;

[0028] S104, Based on the region pairing results, the original configuration UAV and the target configuration UAV are paired node by node to obtain several paired nodes;

[0029] S105, perform dynamic obstacle avoidance processing on each of the several paired nodes to generate path planning for the unmanned structure.

[0030] In S101 and S102, the first region attribute indicates the region information of the UAV located in the preset sub-region corresponding to the original configuration. The second region attribute indicates the region information of the UAV located in the preset sub-region corresponding to the target configuration. The region attribute corresponding to each UAV in the UAV cluster of the original or target configuration can be obtained directly, or it can be obtained through the following methods.

[0031] For example, a first coordinate system is constructed using the centroid of the original configuration drone swarm as the origin; a second coordinate system is constructed using the centroid of the target configuration drone swarm as the origin. For any drone in the original configuration: based on the drone's original coordinates in the world coordinate system and the origin coordinates of the first coordinate system, the first local coordinate information of the drone in the first coordinate system is determined; based on the first local coordinate information, the first angle formed between the drone's projection onto the oxy plane in the first coordinate system and the X-axis is determined; based on the first angle and a preset sub-region corresponding to the original configuration, the first region attribute of the drone is determined. For any drone in the target configuration: based on the drone's original coordinates in the world coordinate system and the origin coordinates of the second coordinate system, the second local coordinate information of the drone in the second coordinate system is determined; based on the second local coordinate information, the second angle formed between the drone's projection onto the oxy plane in the second coordinate system and the X-axis is determined; based on the second angle and a preset sub-region corresponding to the target configuration, the second region attribute of the drone is determined.

[0032] For example: Based on the centroid position of each UAV in the original configuration s, calculate the centroid position c of the UAV s cluster in the original configuration s. s Based on the centroid position of each UAV in the target configuration g, calculate the centroid position c of the UAV swarm in the target configuration g. g Using the centroid of the original UAV swarm configuration as the origin, the x, y, and z axes are parallel to the x, y, and z axes of the coordinate system containing the UAV's position coordinates, respectively, with their positive directions remaining unchanged, thus constructing the first coordinate system o. s x s y s z s A second coordinate system is constructed with the centroid of the UAV swarm configuration as the origin, and the x, y, and z axes parallel to the x, y, and z axes of the coordinate system containing the UAV positions, respectively, with their positive directions remaining unchanged. g x g y g z gThe UAV swarms of the original and target configurations are divided into several smaller swarms of similar size for subsequent path planning. The rule for dividing the UAV swarms of the original or target configurations into k smaller regions is to start from the positive x-axis, rotate counterclockwise, and divide into regions every (360 / k)°, for a total of k smaller regions; these k smaller regions are used as preset sub-regions corresponding to the original or target configurations. The original coordinates of the UAVs in the original configuration and the origin coordinates of the first coordinate system (i.e., the centroid position c) are then compared. s By subtracting the coordinates of the first coordinate system from the first coordinate system's first local coordinate information, the first local coordinate information of the UAV is obtained; then, the UAV's coordinates in the first coordinate system are calculated based on the arctangent function. s x s y s The first angle α formed between the planar projection and the X-axis. The original coordinates of the UAV in the target configuration and the origin coordinates of the second coordinate system (centroid position c) are then used to define the coordinates of the origin (centroid position c) of the second coordinate system. g By subtracting the coordinates from the first coordinate, we obtain the second local coordinate information of the UAV in the second coordinate system; then, based on the arctangent function, we calculate the UAV's coordinates in the second coordinate system. g x g y g The second included angle β is formed between the planar projection and the X-axis. Then, both the first included angle α and the second included angle β are transformed to the range [0, 360) degrees. Based on the size of the transformed first included angle, the UAV is mapped to a preset sub-region of the original configuration, obtaining the UAV's first region attribute. Based on the size of the transformed second included angle, the UAV is mapped to a preset sub-region of the target configuration, obtaining the UAV's second region attribute. This effectively divides the UAV swarm into multiple small regions, providing a foundation for subsequent path planning and scheduling.

[0033] In S103, region pairing is performed on the sub-regions of the original configuration and the target configuration based on preset rules or algorithm models to generate region pairing results.

[0034] For example, based on the first centroid position corresponding to each first sub-region in the original configuration and the second centroid position corresponding to each second sub-region in the target configuration, the distance between each first sub-region and each second sub-region is determined to obtain a distance matrix; the Hungarian pairing algorithm is used to perform region pairing on the distance matrix to generate region pairing results.

[0035] For example: For any first sub-region in the original configuration: obtain the centroid positions of all UAVs within this first sub-region; sum and average the centroid positions of all UAVs to obtain the first centroid position corresponding to the first sub-region. For any second sub-region in the target configuration: obtain the centroid positions of all UAVs within this second sub-region; sum and average the centroid positions of all UAVs to obtain the second centroid position corresponding to the second sub-region. Thus, the centroid positions of each sub-region in the original and target configurations in the global coordinate system are obtained. and

[0036] The distance between the centroids of each subregion of the original configuration and each subregion of the target configuration is calculated to obtain the distance matrix D.

[0037]

[0038] in, This represents the distance between the centroid of the first subregion s1 in the original configuration and the centroid of the second subregion g1 in the target configuration; this distance can be calculated using the Euclidean distance formula.

[0039] Using the distance matrix D as input, the Hungarian algorithm is employed to initially pair sub-regions of the original and target configurations. The Hungarian algorithm finds the optimal region pairings in polynomial time, minimizing the total distance after pairing. The output region pairing results include the matching relationship for each pair of sub-regions.

[0040] This effectively provides preliminary matching relationships for sub-region pairing of UAVs. This method utilizes the geometric properties of the centroid position and combines them with the optimization capabilities of the Hungarian algorithm, thereby improving the efficiency of subsequent UAV pairing and reducing the optimization time required; thus laying the foundation for efficient multi-UAV collaborative operations.

[0041] In S104, based on the region pairing results, the original configuration UAV and the target configuration UAV are paired node by node according to preset rules or model algorithms to obtain several paired nodes. For example, for any paired region in the region pairing results: obtain the first sub-region and the second sub-region corresponding to the paired region; if the first sub-region and the second sub-region have the same number of UAV nodes, then for any target node in the first sub-region: search for a paired node corresponding to the target node in the second sub-region based on the shortest path principle to obtain several paired nodes; if the number of UAV nodes in the first sub-region is greater than the number of UAV nodes in the second sub-region, then for any target node in the second sub-region: search for a paired node corresponding to the target node in the first sub-region based on the shortest path principle; for unpaired nodes in the first sub-region: search for a paired node corresponding to the target node in the first sub-region from several second sub-regions. In the first sub-region, select an adjacent sub-region that is adjacent to the second sub-region; search for a paired node corresponding to the unpaired node in the adjacent sub-region based on the shortest path principle; obtain several paired nodes; if the number of drone nodes in the second sub-region is greater than the number of drone nodes in the first sub-region, then for any target node in the first sub-region: search for a paired drone corresponding to the target node in the second sub-region based on the shortest path principle; for unpaired nodes in the second sub-region: select an adjacent sub-region that is adjacent to the first sub-region from several first sub-regions; search for a paired node corresponding to the unpaired node in the adjacent sub-region based on the shortest path principle, obtain several paired nodes.

[0042] For example: for any paired region (s) i ,g j ): Determine the paired region (s) i ,g j ) in s i and g j The number of drones in the area, if (s i ,g j If the number of drones in the set is the same, then proceed to step S1; if s i The number of internal drones is greater than g j If the number of drones is determined, then steps S1 and S2 are executed; if s i The number of internal drones is less than g j If the number of drones is determined, then steps S1 and S3 are executed.

[0043] S1: For s i The drones within the gj are searched and paired in order according to the principle of the shortest path.

[0044] Distance calculation algorithms (such as Euclidean distance or Manhattan distance) are used to evaluate the distance between the target node and the paired node within the pairing area; the nodes are then sorted by distance from smallest to largest and paired sequentially. Alternatively, the Hungarian algorithm can be used to complete the initial pairing of drones between the target node and the paired node within the pairing area. The Hungarian algorithm can find the optimal node pairing in polynomial time, minimizing the total distance after pairing. The output area pairing results include the drone matching relationship for each pair of nodes.

[0045] S2:s i Unpaired drones within the ensemble take turns searching for target nodes in other nearby areas to pair with. Each drone selects the nearest unpaired target node to pair with. This ensures that already paired drones do not participate in subsequent pairings.

[0046] S3:g j Unpaired drones within the ensemble take turns searching for and pairing with targets in other nearby areas. A similar strategy is employed, selecting the nearest unpaired drone for pairing; this continues until all drones are paired or no more suitable targets can be found.

[0047] Therefore, node pairing is performed on drones within the pairing area to ensure that drones in different areas can effectively find targets. This method improves the pairing efficiency of drones within the pairing area by using the shortest path principle, and it also considers the imbalance between the number of drones in the set and the number of drones within it, so that corresponding remedial measures can be taken.

[0048] In S105, dynamic obstacle avoidance is performed on each of the several paired nodes based on preset rules or algorithm models to generate path planning for the unmanned structure.

[0049] For example, dynamic obstacle avoidance processing is performed on each of the plurality of paired nodes to generate path planning for the unmanned vehicle configuration; this includes: obtaining several ideal paths based on the ideal path of the UAV corresponding to each of the plurality of paired nodes; sorting the plurality of ideal paths in ascending order of length, and numbering the starting node of the UAV corresponding to each of the plurality of paired nodes according to the sorting result; for any of the plurality of paired nodes: expanding the search nodes for the starting node corresponding to the paired node; and searching from the search nodes for a node that satisfies the minimum path cost and meets the safety constraints as a path node; and then... The path node is used as the next starting node, and the path node search operation continues until the drone reaches the target node. The drone flight path corresponding to the paired node is generated. The path node in the search operation is set as a temporary obstacle. The target node is set as a fixed obstacle. The safety constraint is used to indicate that the node is not a temporary obstacle or a fixed obstacle when the search operation is performed at the current time. The above path node search operation is performed on each of the several paired nodes in the order of numbering until each drone in the drone cluster reaches the corresponding target node, and the path planning of the drone structure is generated.

[0050] For example: S1: Calculate the initial estimated cost

[0051] For each drone, calculate the ideal path (i.e., the initial estimated cost) from its starting position to the target position using Euclidean distance or other suitable distance calculation methods. Sort all drones according to the ideal path length and assign each drone a unique number for subsequent processing.

[0052] S2: Expand search nodes

[0053] Following the order of drone numbers, the search nodes for each drone are expanded sequentially: for each drone, the A* algorithm is used to expand its neighboring nodes. The drone selects the path node with the lowest cost to proceed; the path cost calculation includes the current path length and the estimated cost to reach the target.

[0054] S3: Traverse the next path point and handle collisions.

[0055] For each drone's next path node, perform the following operations:

[0056] Traverse all drones' next path nodes, checking for collision risks (i.e., whether the path node is occupied by other drones or will cause a conflict). If a path node that does not meet safety constraints is found, mark it as an obstacle to prevent drones from selecting that path node. Replan the path based on the new state to ensure safety.

[0057] S4: Set up fixed obstacles

[0058] For drones that have reached the target configuration, set their path nodes as fixed obstacles: this is to prevent other drones from flying to that location and thus avoid collisions with drones that have already reached the target.

[0059] S5: Repeated Path Planning

[0060] Repeat steps S2 to S4 until all drones successfully reach their respective target locations: in each iteration, continuously check and update the status of the path nodes.

[0061] Traditional A* algorithms can only avoid static obstacles and cannot handle collisions between multiple UAVs. This embodiment improves upon the A* algorithm by addressing dynamic obstacle avoidance during multi-UAV flight. Its core logic involves numbering and sorting the UAVs, sequentially expanding the search nodes, continuously filtering path nodes, setting nodes that do not meet safety constraints as obstacles, and simultaneously setting the nodes containing UAVs that have reached the target as fixed obstacles. This process iterates until all UAVs have reached the target location. Thus, by improving the A* algorithm through these steps, it not only avoids static obstacles but also effectively handles dynamic collisions between multiple UAVs, significantly improving the safety and efficiency of multi-UAV systems flying in complex environments.

[0062] This embodiment adopts a regional strategy for the transformation method of large-scale unmanned vehicle configurations, and combines regional pairing, node pairing, and dynamic obstacle avoidance processing steps. This not only reduces the computational complexity of path planning, but also effectively handles the collision problem when multiple UAVs are flying, greatly improving the safety and efficiency of multi-UAV systems flying in complex environments.

[0063] like Figure 2 The diagram shown is a flowchart illustrating a transformation method for large-scale unmanned structures according to another embodiment of the present invention.

[0064] A method for transforming the configuration of large-scale unmanned structures includes at least the following steps:

[0065] S201, Based on the first region attributes corresponding to each drone in the original configuration drone cluster, the original configuration drone cluster is divided into several first sub-regions;

[0066] S202, Based on the second region attribute corresponding to each UAV in the UAV cluster of the target configuration, the UAV cluster of the target configuration is divided into several second sub-regions;

[0067] S203, optimize the regional attributes corresponding to each UAV in the first sub-region and the second sub-region respectively; to obtain the optimized first sub-region and the optimized second sub-region;

[0068] S204, perform region pairing on several optimized first sub-regions and several optimized second sub-regions to generate region pairing results;

[0069] S205, Based on the regional pairing results, the original configuration UAV and the target configuration UAV are paired node by node to obtain several paired nodes;

[0070] S206, Based on the principle of shortest path between paired nodes, perform global optimization on each of the several paired nodes and output the optimal paired node;

[0071] S207, Perform dynamic obstacle avoidance processing on each optimal pairing node among several paired nodes to generate path planning for unmanned structures.

[0072] It should be noted that the implementation processes of steps S201, S202, S204, S205, and S207 in this embodiment are respectively different from those of the previous embodiments. Figure 1 The implementation processes of S101, S102, S103, S104, and S105 in the embodiments are similar and will not be repeated here.

[0073] In S203, the regional attributes of UAVs in different configurations are optimized based on preset rules or algorithm models.

[0074] For example, for any target sub-region among the plurality of first sub-regions: based on the centroid position of each UAV in the target sub-region in the world coordinate system, determine the centroid position corresponding to the target sub-region; for any UAV in the target sub-region: based on the centroid position of the UAV and the centroid position of the target sub-region, determine the first distance between the UAV and the target sub-region; select at least two adjacent sub-regions corresponding to the target sub-region from the plurality of first sub-regions; determine the first distance between the UAV and each of the adjacent sub-regions, obtaining at least two first distances; determine the sub-region corresponding to the smallest of the at least three first distances as the region to which the UAV belongs, and update the region attributes of the UAV based on the attributes of the selected region; recalculate the centroid position corresponding to the target sub-region based on the updated region attributes of the UAV; repeat the above steps until the number of iterations meets a preset threshold or the centroid position corresponding to the target sub-region does not change, then end the step of updating the region attributes corresponding to each UAV in the target sub-region.

[0075] For example: S1, calculate the centroid position of each target sub-region.

[0076] S2, Calculate distance: For any UAV in the target sub-region: Calculate the distance between the UAV's centroid and the centroid of the target sub-region, as well as the distance between the UAV's centroid and the centroids of adjacent sub-regions.

[0077] S3, Update Region Attributes: Based on the distance calculation results in S2, determine whether the drone should change its sub-region. If the distance from the drone to the centroid of its current sub-region is greater than the distance to the centroid of a neighboring sub-region, then update the drone's sub-region attribute to the neighboring sub-region.

[0078] S4, Iterative Update: Iteration Process: Repeat steps S1 to S3 until either of the following conditions is met: 1. The maximum number of iterations is reached. 2. The position of the centroid of each target sub-region no longer changes during the iteration process (i.e., convergence).

[0079] S5, Termination Condition: Termination: After the iteration is completed, the regional attributes of all UAVs will be updated to the optimal state, ensuring the successful execution of the path planning task.

[0080] This embodiment continuously iterates and updates the regional attributes of the drones to ensure that each drone is clearly assigned to the most suitable sub-region, thereby reducing mismatches in subsequent path planning and improving the overall mission success rate.

[0081] In S206, for example, for any pairing node among the plurality of paired nodes: obtain the starting node corresponding to the original configuration and the target node corresponding to the target configuration among the paired nodes; determine the ideal path of the UAV corresponding to the paired node based on the coordinate information corresponding to the starting node and the coordinate information corresponding to the target node; sort the ideal paths of the UAV corresponding to each of the plurality of paired nodes in descending order of length to generate a sorting result; perform UAV node replacement operation on the paired nodes among the plurality of paired nodes in turn according to the sorting result; if the ideal path corresponding to the paired node after the replacement operation is shorter than the original paired node; then replace the original paired node with the replaced paired node; repeat the above steps until the total length of the UAV ideal paths generated by the plurality of paired nodes remains unchanged, then end the UAV node replacement operation among the paired nodes and output the optimal paired node.

[0082] For example: S1, calculate the ideal path of the drone corresponding to the paired node;

[0083] S2, iterate through and sort the ideal path lengths; iterate through the ideal path lengths in all paired node sets, sort them in descending order of length, and record the index of each paired node for subsequent optimization. Generate an ordered list {(Lij,i,j)} containing the path length and the corresponding drone index.

[0084] S3, Optimize the pairing node combination; based on the optimization rules for the pairing combination of the drone's starting node and target node, try changing the drone's pairing combination sequence: select the pairing combination (i,j) with the longest current path length for optimization; try pairing drone i with other target points to calculate a new ideal path. Select a new pairing combination; if the path length L′ of the new combination is less than the path length Lij of the original combination, then replace the original combination. Record the new pairing combination and its path length.

[0085] S4: Repeat the optimization process. Repeat steps S1 to S3 until the total length of the UAV's ideal path no longer changes.

[0086] In this embodiment, step S205 completes the initial pairing of UAVs in the original and target configurations. However, the regional strategy is not a complete traversal strategy, and some UAV pairings are not optimal. Therefore, this embodiment performs global optimization on the pairing nodes, which can eliminate the influence of the maximum path length, thereby improving the overall efficiency and accuracy of node pairing, and thus improving the transformation efficiency of UAV clusters with different configurations.

[0087] This embodiment employs a regional strategy for transforming large-scale unmanned aerial vehicle (UAV) configurations. It combines regional attribute optimization, regional pairing, node pairing, and consecutive steps of paired node optimization. This not only achieves globally optimal path planning results for UAV swarms but also reduces computational complexity from O(N!) to O(MN). 2 M≤N; thus effectively reducing the computation time of path planning and improving the efficiency of path planning tasks.

[0088] The following section will provide a detailed description of the transformation method for large-scale unmanned structures provided in this embodiment, using a specific application scenario as an example.

[0089] A method for transforming the configuration of large-scale unmanned structures includes at least the following steps:

[0090] S1. Construct a first coordinate system using the centroid of the original UAV cluster as the origin; construct a second coordinate system using the centroid of the target UAV cluster as the origin; for any UAV in the original configuration: determine the first local coordinate information of the UAV in the first coordinate system based on the UAV's original coordinates in the world coordinate system and the origin coordinates of the first coordinate system; determine the first angle between the UAV's projection onto the oxy plane in the first coordinate system and the X-axis based on the first local coordinate information; determine the first region attribute of the UAV based on the first angle and the preset sub-region corresponding to the original configuration; for any UAV in the target configuration: determine the second local coordinate information of the UAV in the second coordinate system based on the UAV's original coordinates in the world coordinate system and the origin coordinates of the second coordinate system; determine the second angle between the UAV's projection onto the oxy plane in the second coordinate system and the X-axis based on the second local coordinate information; determine the second region attribute of the UAV based on the second angle and the preset sub-region corresponding to the target configuration.

[0091] S2, based on the first region attribute corresponding to each drone in the original configuration drone cluster, divide the original configuration drone cluster into several first sub-regions; based on the second region attribute corresponding to each drone in the target configuration drone cluster, divide the target configuration drone cluster into several second sub-regions.

[0092] S3, for any target sub-region among several first sub-regions: based on the centroid position of each UAV in the target sub-region in the world coordinate system, determine the centroid position corresponding to the target sub-region; for any UAV in the target sub-region: based on the centroid position of the UAV and the centroid position of the target sub-region, determine the first distance between the UAV and the target sub-region; select at least two adjacent sub-regions corresponding to the target sub-region from several first sub-regions; determine the first distance between the UAV and each adjacent sub-region, obtaining at least two first distances; determine the sub-region corresponding to the smallest of the at least three first distances as the region to which the UAV belongs, and update the region attributes of the UAV based on the attributes of the selected region; recalculate the centroid position corresponding to the target sub-region based on the updated region attributes of the UAV; repeat the above steps until the number of iterations meets a preset threshold or the centroid position corresponding to the target sub-region does not change, then end the step of updating the region attributes corresponding to each UAV in the target sub-region.

[0093] S4. Based on the first centroid position corresponding to each first sub-region in the original configuration and the second centroid position corresponding to each second sub-region in the target configuration, determine the distance between each first sub-region and each second sub-region to obtain a distance matrix; use the Hungarian pairing algorithm to perform region pairing on the distance matrix to generate region pairing results.

[0094] S5, for any paired region in the region pairing results: obtain the first sub-region and the second sub-region corresponding to the paired region; if the first sub-region and the second sub-region have the same number of drone nodes, then for any target node in the first sub-region: search for a paired node corresponding to the target node in the second sub-region based on the shortest path principle, and obtain several paired nodes; if the number of drone nodes in the first sub-region is greater than the number of drone nodes in the second sub-region, then for any target node in the second sub-region: search for a paired node corresponding to the target node in the first sub-region based on the shortest path principle; for unpaired nodes in the first sub-region: from several second sub-regions... In the domain, select an adjacent sub-region that is adjacent to the second sub-region; search for paired nodes corresponding to unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes; if the number of drone nodes in the second sub-region is greater than the number of drone nodes in the first sub-region, then for any target node in the first sub-region: search for paired drones corresponding to the target node in the second sub-region based on the shortest path principle; for unpaired nodes in the second sub-region: select an adjacent sub-region that is adjacent to the first sub-region from several first sub-regions; search for paired nodes corresponding to unpaired nodes in the adjacent sub-regions based on the shortest path principle, obtain several paired nodes.

[0095] S6. For any pairing node among several paired nodes: obtain the starting node corresponding to the original configuration and the target node corresponding to the target configuration among the paired nodes; determine the ideal path of the UAV corresponding to the paired node based on the coordinate information corresponding to the starting node and the coordinate information corresponding to the target node; sort the ideal paths of the UAV corresponding to each paired node among several paired nodes in descending order of length to generate a sorting result; perform UAV node replacement operation on the paired nodes among several paired nodes in turn according to the sorting result; if the ideal path corresponding to the paired node after the replacement operation is shorter than the original paired node; then replace the original paired node with the replaced paired node; repeat the above steps until the total length of the ideal paths of the UAV generated by several paired nodes remains unchanged, then end the UAV node replacement operation among the paired nodes and output the optimal paired node.

[0096] S7. Based on the ideal path of the UAV corresponding to each of the several optimal pairing nodes, obtain several ideal paths; sort the several ideal paths in ascending order of length, and number the starting node of the UAV corresponding to each pairing node in the several pairing nodes according to the sorting result; for any pairing node in the several optimal pairing nodes: expand the search nodes for the starting node corresponding to the optimal pairing node; and search for a node that satisfies the minimum path cost and meets the safety constraints as a path node; use the path node as the next starting node and continue the path node search operation until the UAV reaches the target node and the search operation ends; generate the UAV flight path corresponding to the optimal pairing node; set the path nodes in the search operation as temporary obstacles; and set the target node as a fixed obstacle; wherein, the safety constraint is used to indicate that the node is not a temporary roadblock or a fixed obstacle when the search operation is performed at the current time; according to the numbering order, perform the above path node search operation for each of the several optimal pairing nodes in the several optimal pairing nodes in sequence until each UAV in the UAV cluster reaches the corresponding target node, and generate the path planning of the UAV configuration.

[0097] like Figure 3 The diagram shown is a structural schematic of a conversion device for large-scale unmanned structures provided in an embodiment of the present invention.

[0098] A transformation device for large-scale unmanned aerial vehicle (UAV) configurations, the device 300 comprising: a first sub-region module 301, used to divide the original configuration UAV cluster into several first sub-regions based on a first region attribute corresponding to each UAV in the original configuration UAV cluster; a second sub-region module 302, used to divide the target configuration UAV cluster into several second sub-regions based on a second region attribute corresponding to each UAV in the target configuration UAV cluster; a region pairing module 303, used to pair the several first sub-regions corresponding to the original configuration and the several second sub-regions corresponding to the target configuration, generating region pairing results; a node pairing module 304, used to pair the UAVs of the original configuration and the UAVs of the target configuration based on the region pairing results, obtaining several paired nodes; and a dynamic obstacle avoidance processing module 305, used to perform dynamic obstacle avoidance processing on each of the several paired nodes, generating path planning for the UAV configuration.

[0099] In a preferred embodiment of this invention, the device further includes: a first construction module, used to construct a first coordinate system by taking the centroid position of the original configuration of the UAV cluster as the origin; a second construction module, used to construct a second coordinate system by taking the centroid position of the target configuration of the UAV cluster as the origin; and a first determination module, used for any UAV in the original configuration to: determine the first local coordinate information of the UAV in the first coordinate system based on the original coordinates of the UAV in the world coordinate system and the origin coordinates corresponding to the first coordinate system; and based on the first local coordinate information, determine the relationship between the UAV's projection onto the oxy plane in the first coordinate system and the X-axis. The first included angle is formed between the first included angle and the preset sub-region corresponding to the original configuration. The second determining module is used to determine the first region attribute of the UAV based on the first included angle and the preset sub-region corresponding to the original configuration. The second determining module is used to determine the second local coordinate information of the UAV in the second coordinate system based on the original coordinates of the UAV in the world coordinate system and the origin coordinates corresponding to the second coordinate system. Based on the second local coordinate information, the second included angle is formed between the oxy plane projection of the UAV in the second coordinate system and the X-axis. Based on the second included angle and the preset sub-region corresponding to the target configuration, the second region attribute of the UAV is determined.

[0100] In a preferred embodiment of this invention, the device further includes a region attribute optimization module, used to optimize the region attributes corresponding to each UAV in the first sub-region and the second sub-region, respectively. The region attribute optimization module includes: an optimization unit, configured to: for any target sub-region among the plurality of first sub-regions, determine the centroid position corresponding to the target sub-region based on the centroid position of each UAV in the target sub-region in the world coordinate system; for any UAV in the target sub-region, determine a first distance between the UAV and the target sub-region based on the centroid position of the UAV and the centroid position of the target sub-region; select at least two adjacent sub-regions corresponding to the target sub-region from the plurality of first sub-regions; determine the first distance between the UAV and each of the adjacent sub-regions, obtaining at least two first distances; determine the sub-region corresponding to the smallest of the at least three first distances as the region to which the UAV belongs, and update the region attributes of the UAV based on the attributes of the selected region; recalculate the centroid position corresponding to the target sub-region based on the updated region attributes of the UAV; and an iteration unit, configured to repeat the above steps until the number of iterations meets a preset threshold or the centroid position corresponding to the target sub-region does not change, then end the update step of the region attributes corresponding to each UAV in the target sub-region.

[0101] In a preferred embodiment of this example, the region pairing module includes: a determining unit, used to determine the distance between each first sub-region and each second sub-region based on the first centroid position corresponding to each first sub-region in the original configuration and the second centroid position corresponding to each second sub-region in the target configuration, to obtain a distance matrix; and a region pairing unit, used to perform region pairing on the distance matrix using the Hungarian pairing algorithm to generate region pairing results.

[0102] In a preferred embodiment of this example, the node pairing module includes: an acquisition unit, configured to, for any pairing region in the region pairing results, acquire a first sub-region and a second sub-region corresponding to the pairing region; a first node pairing unit, configured to, if the first sub-region and the second sub-region have the same number of drone nodes, for any target node in the first sub-region, search for a pairing node corresponding to the target node in the second sub-region based on the shortest path principle, to obtain several pairing nodes; and a first node pairing unit, configured to, if the number of drone nodes in the first sub-region is greater than the number of drone nodes in the second sub-region, search for a pairing node corresponding to the target node in the first sub-region based on the shortest path principle, for any target node in the second sub-region; for... Unpaired nodes in the first sub-region: Select adjacent sub-regions from several second sub-regions; search for paired nodes corresponding to the unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes; Third node pairing unit, used to: if the number of drone nodes in the second sub-region is greater than the number of drone nodes in the first sub-region, then for any target node in the first sub-region: search for paired drones corresponding to the target node in the second sub-region based on the shortest path principle; for unpaired nodes in the second sub-region: Select adjacent sub-regions from several first sub-regions; search for paired nodes corresponding to the unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes.

[0103] In a preferred embodiment of this example, the device further includes: a global optimization module, used to perform global optimization on each paired node based on the principle of shortest path between paired nodes, and output the optimal paired node. The global optimization module includes: a determination unit, used for any paired node among the plurality of paired nodes to: obtain the starting node corresponding to the original configuration and the target node corresponding to the target configuration among the paired nodes; determine the ideal path of the UAV corresponding to the paired node based on the coordinate information corresponding to the starting node and the coordinate information corresponding to the target node; a replacement unit, used to sort the ideal paths of the UAV corresponding to each of the plurality of paired nodes in descending order of length, and generate a sorting result; perform UAV node replacement operations on the paired nodes among the plurality of paired nodes in sequence according to the sorting result; if the ideal path corresponding to the paired node after the replacement operation is shorter than the original paired node; then replace the original paired node with the replaced paired node; a replacement operation unit, used to repeat the above steps until the total length of the ideal paths of the UAV generated by the plurality of paired nodes remains unchanged, then end the UAV node replacement operation among the paired nodes and output the optimal paired node.

[0104] In a preferred embodiment of this example, the dynamic obstacle avoidance processing module includes: an acquisition unit, configured to obtain several ideal paths based on the ideal path of the UAV corresponding to each of the several paired nodes; a numbering unit, configured to sort the several ideal paths in ascending order of length, and sequentially number the starting node of the UAV corresponding to each of the several paired nodes according to the sorting result; and a dynamic obstacle avoidance unit, configured to: expand the search nodes for the starting node corresponding to any of the several paired nodes; and search for nodes that satisfy the minimum path cost and meet the safety constraints from the search nodes as path nodes; and configure the path... The node serves as the next starting node, continuing the path node search operation until the drone reaches the target node; generating the drone flight path corresponding to the paired node; setting the path nodes in the search operation as temporary obstacles; and setting the target node as a fixed obstacle; wherein, the safety constraint is used to indicate that the node is not a temporary roadblock or a fixed obstacle when the search operation is performed at the current moment; the generation unit is used to sequentially perform the above path node search operation on each of the several paired nodes according to the numbering order, until each drone in the drone cluster reaches the corresponding target node, generating the path planning of the drone configuration.

[0105] The above-described apparatus can execute a transformation method for large-scale unmanned structures provided in an embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing such a method. Technical details not described in detail in this embodiment can be found in the transformation method for large-scale unmanned structures provided in an embodiment of the present invention.

[0106] The present invention also provides an electronic device, comprising: a processor; a memory for storing executable instructions of the processor; the processor being configured to read the executable instructions from the memory and execute the instructions to implement the transformation method for large-scale unmanned structures described in the present invention.

[0107] In addition to the methods and apparatus described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the methods according to various embodiments of this application described in the "Exemplary Methods" section above.

[0108] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0109] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the methods according to the following embodiments of this application described in the "Exemplary Methods" section above.

[0110] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0111] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0112] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0113] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of those different embodiments or examples.

[0114] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0115] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for transforming the configuration of large-scale unmanned structures, characterized in that, include: For any UAV in the original configuration: construct the first coordinate system with the centroid of the UAV swarm in the original configuration as the origin; Based on the original coordinates of the UAV in the world coordinate system and the origin coordinates corresponding to the first coordinate system, the first local coordinate information of the UAV in the first coordinate system is determined; based on the first local coordinate information, the first angle formed between the projection of the line connecting the UAV and the origin onto the oxy plane in the first coordinate system and the X-axis is determined; the first angle is converted to the range [0, 360) degrees; according to the size of the converted first angle, the UAV is mapped to a preset sub-region of the original configuration to obtain the first region attribute of the UAV; Based on the first region attributes corresponding to each drone in the original configuration drone swarm, the original configuration drone swarm is divided into several first sub-regions. For any UAV in the target configuration: A second coordinate system is constructed using the centroid of the UAV cluster in the target configuration as the origin; based on the original coordinates of the UAV in the world coordinate system and the origin coordinates corresponding to the second coordinate system, the second local coordinate information of the UAV in the second coordinate system is determined; based on the second local coordinate information, the second angle formed between the projection of the line connecting the UAV and the origin onto the oxy plane in the second coordinate system and the X-axis is determined; the second angle is transformed to the range [0, 360) degrees; according to the size of the transformed second angle, the UAV is mapped to a preset sub-region of the target configuration to obtain the second region attribute of the UAV; wherein, the original configuration or the UAV cluster of the target configuration... The rule for dividing the area into smaller regions is to start from the positive x-axis and rotate counterclockwise, every [number] [units]. Divided into one area, divided into a total of A small area; Each small region serves as a preset sub-region corresponding to the original configuration or the target configuration; Based on the second region attribute corresponding to each drone in the target configuration drone swarm, the drone swarm of the target configuration is divided into several second sub-regions; Perform region pairing on several first sub-regions corresponding to the original configuration and several second sub-regions corresponding to the target configuration to generate region pairing results; Based on the region pairing results, the original configuration UAV and the target configuration UAV are paired node by node to obtain several paired nodes. For any paired region in the region pairing results: obtain the first sub-region and the second sub-region corresponding to the paired region; if the first sub-region and the second sub-region have the same number of UAV nodes, then for any target node in the first sub-region: search for a paired node corresponding to the target node in the second sub-region based on the shortest path principle to obtain several paired nodes; if the number of UAV nodes in the first sub-region is greater than the number of UAV nodes in the second sub-region, then for any target node in the second sub-region: search for a paired node corresponding to the target node in the first sub-region based on the shortest path principle. For unpaired nodes in the first sub-region: select adjacent sub-regions from several second sub-regions; search for paired nodes corresponding to the unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes; if the number of drone nodes in the second sub-region is greater than the number of drone nodes in the first sub-region, then for any target node in the first sub-region: search for paired drones corresponding to the target node in the second sub-regions based on the shortest path principle; for unpaired nodes in the second sub-region: select adjacent sub-regions from several first sub-regions; search for paired nodes corresponding to the unpaired nodes in the adjacent sub-regions based on the shortest path principle; obtain several paired nodes. Dynamic obstacle avoidance processing is performed on each of the several paired nodes to generate a path plan for the unmanned structure.

2. The method according to claim 1, characterized in that, Before performing region pairing on the first sub-regions corresponding to the original configuration and the second sub-regions corresponding to the target configuration, the method further includes: optimizing the region attributes corresponding to each UAV in the first sub-regions and the second sub-regions respectively. The optimization processing of the regional attributes corresponding to each UAV within the first sub-region includes: For any target sub-region among the plurality of first sub-regions: based on the centroid position of each UAV in the target sub-region in the world coordinate system, determine the centroid position corresponding to the target sub-region; for any UAV in the target sub-region: based on the centroid position of the UAV and the centroid position of the target sub-region, determine the first distance between the UAV and the target sub-region; select at least two adjacent sub-regions corresponding to the target sub-region from the plurality of first sub-regions; determine the first distance between the UAV and each of the adjacent sub-regions, obtaining at least two first distances; determine the sub-region corresponding to the smallest of the at least three first distances as the region to which the UAV belongs, and update the region attributes of the UAV based on the attributes of the selected region; recalculate the centroid position corresponding to the target sub-region based on the updated region attributes of the UAV; Repeat the above steps until the number of iterations meets the preset threshold or the centroid position corresponding to the target sub-region does not change, then end the update step of the region attribute corresponding to each UAV in the target sub-region.

3. The method according to claim 1, characterized in that, The step of performing region pairing on a plurality of first sub-regions corresponding to the original configuration and a plurality of second sub-regions corresponding to the target configuration to generate region pairing results includes: Based on the first centroid position corresponding to each first sub-region in the original configuration and the second centroid position corresponding to each second sub-region in the target configuration, the distance between each first sub-region and each second sub-region is determined to obtain a distance matrix; The distance matrix is ​​paired using the Hungarian pairing algorithm to generate the region pairing results.

4. The method according to claim 1, characterized in that, Before performing dynamic obstacle avoidance processing on each of the plurality of paired nodes, the method further includes: performing global optimization on each paired node based on the principle of shortest path between paired nodes, and outputting the optimal paired node; The process of globally optimizing each paired node based on the principle of finding the shortest path between paired nodes, and outputting the optimal paired node, includes: For any of the paired nodes: obtain the starting node corresponding to the original configuration and the target node corresponding to the target configuration in the paired nodes; based on the coordinate information corresponding to the starting node and the coordinate information corresponding to the target node, determine the ideal path of the UAV corresponding to the paired node; Sort the ideal paths of the UAVs corresponding to each of the several paired nodes in descending order of length to generate a sorting result; perform UAV node replacement operations on the paired nodes in the several paired nodes in turn according to the sorting result; if the ideal path corresponding to the paired node after the replacement operation is shorter than that of the original paired node, then replace the original paired node with the replaced paired node. Repeat the above steps until the total length of the ideal UAV path generated by the paired nodes remains unchanged, then end the UAV node replacement operation in the paired nodes and output the optimal paired node.

5. The method according to claim 1, characterized in that, The step of performing dynamic obstacle avoidance processing on each of the plurality of paired nodes to generate a path plan for the unmanned structure includes: Based on the ideal path of the UAV corresponding to each of the several paired nodes, several ideal paths are obtained; The ideal paths are sorted in ascending order of length, and the starting node of the UAV corresponding to each pair of paired nodes is numbered according to the sorting result. For any of the paired nodes: expand the search nodes to the starting node corresponding to the paired node; and search for a node that satisfies the minimum path cost and meets the safety constraints from the search nodes as a path node; use the path node as the next starting node and continue the path node search operation until the UAV reaches the target node; generate the UAV flight path corresponding to the paired node; set the path nodes in the search operation as temporary obstacles; and set the target node as a fixed obstacle; wherein, the safety constraints are used to indicate that the node is not a temporary obstacle or a fixed obstacle when the search operation is performed at the current moment; According to the numbering order, the above path node search operation is performed on each of the several paired nodes in sequence until each UAV in the UAV cluster reaches the corresponding target node, generating a path plan for the UAV configuration.

6. A conversion device for large-scale unmanned structures, characterized in that, include: The first sub-region module is used to construct a first coordinate system for any UAV in the original configuration, taking the centroid position of the UAV cluster in the original configuration as the origin. Based on the original coordinates of the UAV in the world coordinate system and the origin coordinates of the first coordinate system, the first local coordinate information of the UAV in the first coordinate system is determined; based on the first local coordinate information, the first angle formed between the projection of the line connecting the UAV and the origin onto the oxy plane in the first coordinate system and the X-axis is determined; the first angle is converted to the range [0, 360) degrees; according to the size of the converted first angle, the UAV is mapped to a preset sub-region of the original configuration to obtain the first region attribute of the UAV; based on the first region attribute corresponding to each UAV in the UAV cluster of the original configuration, the UAV cluster of the original configuration is divided into several first sub-regions; The second sub-region module is used for any UAV in the target configuration to: construct a second coordinate system using the centroid of the UAV cluster in the target configuration as the origin; determine the second local coordinate information of the UAV in the second coordinate system based on the original coordinates of the UAV in the world coordinate system and the origin coordinates corresponding to the second coordinate system; determine the second included angle formed between the projection of the line connecting the UAV and the origin onto the oxy plane in the second coordinate system and the X-axis based on the second local coordinate information; transform the second included angle to the range [0, 360) degrees; map the UAV to a preset sub-region of the target configuration according to the size of the transformed second included angle to obtain the second region attribute of the UAV; wherein, the UAV cluster in the original configuration or the target configuration The rule for dividing the area into smaller regions is to start from the positive x-axis and rotate counterclockwise, every [number] [units]. Divided into one area, divided into a total of A small area; Each small region is a preset sub-region corresponding to the original configuration or the target configuration; based on the second region attribute corresponding to each drone in the drone cluster of the target configuration, the drone cluster of the target configuration is divided into several second sub-regions; The region pairing module is used to perform region pairing on a number of first sub-regions corresponding to the original configuration and a number of second sub-regions corresponding to the target configuration, and generate region pairing results. The node pairing module is used to: for any paired region in the region pairing results, obtain the first sub-region and the second sub-region corresponding to the paired region; if the first sub-region and the second sub-region have the same number of drone nodes, then for any target node in the first sub-region: search for a paired node corresponding to the target node in the second sub-region based on the shortest path principle, obtaining several paired nodes; if the number of drone nodes in the first sub-region is greater than the number of drone nodes in the second sub-region, then for any target node in the second sub-region: search for a paired node corresponding to the target node in the first sub-region based on the shortest path principle; for unpaired nodes in the first sub-region: select from several... In the second sub-region, adjacent sub-regions are selected; based on the shortest path principle, paired nodes corresponding to the unpaired nodes are searched from the adjacent sub-regions; several paired nodes are obtained; if the number of drone nodes in the second sub-region is greater than the number of drone nodes in the first sub-region, then for any target node in the first sub-region: based on the shortest path principle, paired drones corresponding to the target node are searched from the second sub-region; for unpaired nodes in the second sub-region: adjacent sub-regions adjacent to the first sub-region are selected from several first sub-regions; based on the shortest path principle, paired nodes corresponding to the unpaired nodes are searched from the adjacent sub-regions; several paired nodes are obtained. The dynamic obstacle avoidance processing module is used to perform dynamic obstacle avoidance processing on each of the several paired nodes to generate a path plan for the unmanned structure.

7. An electronic device, comprising: processor; Memory used to store the processor's executable instructions; The processor is configured to read the executable instructions from the memory and execute the instructions to implement the method as described in any one of claims 1-5.

8. A computer-readable medium having a computer program stored thereon, which, when executed by a processor, implements the method as described in any one of claims 1-5.

Images