Unmanned aerial vehicle cluster path planning method and system based on dynamic optimal flight path

Abstract

The invention provides an unmanned aerial vehicle cluster path planning method and system based on a dynamic optimal flight path, and relates to the technical field of unmanned aerial vehicle cluster path planning. The method comprises the following steps: constructing a three-dimensional model of a real environment based on known unmanned aerial vehicle information and a satellite scanning map, and generating a three-dimensional grid map; based on the three-dimensional grid map, taking the initial position of each unmanned aerial vehicle as a starting point, taking a target point as an end point, taking the shortest group path as a target, and adopting an improved ACO algorithm to plan and obtain an initial static flight path; controlling the unmanned aerial vehicle to fly according to the initial static flight path, and performing terrain scanning and flight monitoring in real time; local path planning is carried out by adopting an improved A * algorithm according to the appearing obstacles, so that flexible obstacle avoidance of the unmanned aerial vehicle is realized; and after all the track points are traversed repeatedly, the unmanned aerial vehicle arrives at the terminal point and executes subsequent tasks. The method has good dynamic obstacle avoidance capability and flight path smoothness while improving the planning efficiency, and is suitable for unmanned aerial vehicle intelligent navigation tasks in a complex three-dimensional environment.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) swarm path planning technology, and in particular to a method and system for UAV swarm path planning based on dynamic optimal flight paths. Background Technology

[0002] With the rapid development of drone technology, drone swarms, with their advantages of collaborative operation, high efficiency, and flexibility, have been widely used in fields such as military reconnaissance, disaster relief, environmental monitoring, and logistics delivery. Path planning is one of the key technologies when drone swarms perform missions; reasonable path planning can effectively improve mission execution efficiency, ensure swarm safety, and reduce energy consumption.

[0003] Currently, UAV swarm path planning methods mainly include traditional path planning methods and intelligent path planning methods. Although they can solve path planning problems in complex environments to a certain extent, they still face many challenges in practical applications. For example, in dynamic environments, when faced with changes in obstacles or adjustments to mission objectives, they cannot quickly and effectively replan paths, making it difficult to guarantee the collaborative operation effect and mission execution success rate of the UAV swarm.

[0004] Therefore, researching a path planning method for UAV swarms that can adapt to complex dynamic environments and achieve efficient collaboration has significant practical implications and application value. Summary of the Invention

[0005] To address the above problems, the present invention aims to provide a method and system for unmanned aerial vehicle (UAV) swarm path planning based on dynamic optimal trajectories, the technical solution of which is as follows:

[0006] On the one hand, a method for UAV swarm path planning based on dynamic optimal trajectories is provided, the method comprising the following steps:

[0007] A 3D model of the real environment is constructed based on known UAV information and satellite scan maps, and a 3D raster map is generated.

[0008] Based on the aforementioned 3D grid map, the initial static trajectory is planned using the improved ACO algorithm, with the initial position of each UAV as the starting point and the target point as the ending point, and the shortest group path as the objective.

[0009] Control the drone to fly along the initial static flight path and perform terrain scanning and flight monitoring in real time;

[0010] Based on the obstacles encountered, an improved A* algorithm is used for local path planning to enable flexible obstacle avoidance for the UAV.

[0011] After repeatedly traversing all waypoints, the drone reaches its destination and performs subsequent tasks.

[0012] Optionally, the process of planning the initial static track using the improved ACO algorithm includes:

[0013] An improved ACO algorithm is used to generate an initial static trajectory that satisfies flight constraints, including minimum turning radius, maximum turning angle, and pitch angle. A local and global dual pheromone update mechanism and a dynamic parameter mechanism are adopted to accelerate the convergence speed of the algorithm while avoiding getting trapped in local optima.

[0014] Optionally, the improved ACO algorithm specifically includes:

[0015] During the path construction process, each drone performs a local pheromone update on the edges it traverses after each step to prevent other drones from over-selecting the same path in the same round; after each iteration, the pheromone of the entire graph is updated globally by the optimal drone path.

[0016] The pheromone update formula in the local pheromone update mechanism is:

[0017] τ ij (n+1)=(1-ξ)·τ ij (n)+ξ·τ0

[0018] Where, τ ij Let ξ be the pheromone concentration on edge (i,j); ξ∈(0,1) is the local volatile coefficient; τ0 is the initial pheromone value, taking a value of Where L nn It is the nearest neighbor path length, and n represents the number of waypoints;

[0019] The pheromone update formula in the global pheromone update mechanism is:

[0020] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij

[0021]

[0022] Where ρ∈(0,1) is the global volatility coefficient; Δτ ij It is the pheromone increment generated by the current optimal path; Q is a constant, and its value ranges from [10, 100]; L best This represents the total cost of the current optimal path.

[0023] Optionally, the dynamic parameter mechanism of the improved ACO algorithm includes:

[0024] The dynamic parameters change as the number of iterations increases:

[0025]

[0026] Where α is the pheromone importance factor; α min The minimum value of the pheromone importance factor; α max β represents the maximum value of the pheromone importance factor; β is the heuristic information importance factor; β min β represents the minimum value of the heuristic importance factor. max t represents the maximum value of the heuristic importance factor; t represents the current iteration number of the algorithm; T represents the maximum number of iterations of the algorithm.

[0027] Optionally, the improved A* algorithm employs a dual-distance estimation mechanism of Manhattan distance and Euclidean distance when searching for the optimal path;

[0028]

[0029] D′ i =|x i -x i-1 |+|y i -y i-1 |+|z i -z i-1 | ←

[0030] Among them, D i For waypoint C i-1 Midpoint C of the feasible region i The cost of the journey, i.e., waypoint C i-1 To track point C i The actual distance is taken as the Euclidean distance; define D′. i For waypoint C i-1 Midpoint C of the feasible region i The cost of the estimated flight path, i.e., waypoint C i-1 To track point C i The estimated distance is taken as the Manhattan distance; (x i y i , z i () is point C i The coordinates, (x i-1 y i-1 , z i-1 () is point C i-1 The coordinates.

[0031] Optionally, the improved A* algorithm employs a dynamic parameter heuristic mechanism, adjusting the exploration strategy according to the algorithm's exploration progress to accelerate the finding of the optimal solution;

[0032] f(C i )=ω1g(C i )+ω2h(C i )

[0033]

[0034] Where, f(C) i ) represents the nodes C traversed from the starting point to the target. i The estimated total cost; g(C) i () represents the distance from the starting point to the current node C. i The actual trajectory cost; h(C i ) represents the current node C i The heuristically estimated path cost to the target point; ω1 and ω2 are dynamic parameters of the actual path cost and the heuristically estimated path cost, respectively, used to adjust the search strategy. The total weight of ω1 and ω2 is 1. In the initial search phase, the algorithm is determined by h(C i The algorithm is dominated by g(C), which can quickly approach the target direction. The later search algorithm is dominated by g(C). i It is dominated by ) and can perform refined local searches.

[0035] Optionally, the improved A* algorithm employs a sparsity mechanism to reduce the number of search nodes in the current node's neighborhood, thereby accelerating the search speed.

[0036] On the other hand, a UAV swarm path planning system based on dynamic optimal trajectories is provided to implement the method described in any of the above-mentioned embodiments, the system comprising:

[0037] The modeling module is used to construct a 3D model of the real environment based on known UAV information and satellite scan maps, and generate a 3D raster map.

[0038] The initial path planning module is used to plan the initial static trajectory based on the three-dimensional grid map, taking the initial position of each UAV as the starting point and the target point as the ending point, with the goal of minimizing the group path, and using the improved ACO algorithm.

[0039] The monitoring module is used to control the UAV to fly according to the initial static flight path and to perform terrain scanning and flight monitoring in real time;

[0040] The local path planning module is used to perform local path planning based on the obstacles encountered, using an improved A* algorithm to enable the UAV to flexibly avoid obstacles.

[0041] The traversal module is used to repeatedly traverse all waypoints until the UAV reaches the destination and executes subsequent tasks.

[0042] On the other hand, an electronic device is provided, the electronic device comprising:

[0043] processor;

[0044] The memory stores computer-readable instructions, which, when loaded and executed by the processor, implement the steps of the UAV swarm path planning method based on dynamic optimal trajectories described above.

[0045] On the other hand, a computer-readable storage medium is provided, wherein program code is stored in the computer-readable storage medium, and the program code can be called by a processor to execute the steps of the above-described UAV swarm path planning method based on dynamic optimal trajectory.

[0046] The beneficial effects of the technical solution provided by this invention include at least the following:

[0047] In this embodiment of the invention, the path planning system information is first initialized based on known UAV information and satellite scan maps. Then, an improved ACO algorithm is used to generate an initial static track that satisfies flight constraints in a known environment. A local and global dual-pheromone update mechanism and a dynamic parameter mechanism are employed to accelerate algorithm convergence while avoiding getting trapped in local optima. During flight, the system senses dynamic obstacles in real time. When track conflicts occur, an improved A* algorithm is used to replan the local path, and a dynamic parameter heuristic mechanism and a cost adjustment mechanism are introduced to ensure track continuity and safety. Simulation results show that the method of this invention improves planning efficiency while possessing good dynamic obstacle avoidance capabilities and track smoothness, making it suitable for intelligent navigation tasks of UAVs in complex three-dimensional environments. Attached Figure Description

[0048] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0049] Figure 1 This is a flowchart of the overall process for the UAV swarm path planning method based on dynamic optimal trajectory provided in this embodiment of the invention.

[0050] Figure 2 This is a flowchart illustrating the improved ACO algorithm provided in an embodiment of the present invention;

[0051] Figure 3 This is a schematic diagram of the traversal process of the improved A* algorithm provided in the embodiments of the present invention;

[0052] Figure 4 This is a schematic diagram of the structure of the UAV swarm path planning system based on dynamic optimal trajectory provided in an embodiment of the present invention;

[0053] Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0054] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0055] In embodiments of the present invention, words such as "exemplarily" and "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or designs. Rather, the term "exemplary" is used to present concepts in a specific manner.

[0056] This invention provides a method for UAV swarm path planning based on dynamic optimal trajectories. This method can be implemented using an electronic device, which can be a terminal or a server. (See reference...) Figure 1 As shown, the processing flow of this method may include the following steps:

[0057] S1. Construct a 3D model of the real environment based on known UAV information and satellite scan maps, and generate a 3D raster map.

[0058] The drone information includes environmental data collected by devices such as optical cameras, lidar, and infrared sensors mounted on the drone, specifically including: multi-angle aerial images, point cloud data, and real-time positioning data. Satellite scan maps refer to large-scale geospatial data obtained through remote sensing satellites, including: digital elevation models (DEMs) (raster data that records surface elevation information), orthophoto maps (DOMs) (geometrically corrected high-resolution satellite images), and multispectral remote sensing data (used to distinguish surface materials, such as vegetation, buildings, and water bodies).

[0059] By integrating UAV information and satellite data, a spatial 3D representation including terrain and features (buildings, vegetation, roads, etc.) is constructed, typically in the form of triangular meshes (.obj, .stl format) or point clouds (.pcd format), forming a 3D model of the real environment. The 3D space is divided into regularly arranged cubic units (voxels), each voxel describing its spatial state through numerical values ​​(e.g., 0 / 1 indicating occupancy, height value, material properties, etc.), resulting in a 3D raster map that can be used for UAV swarm path planning scenarios.

[0060] S2. Based on a 3D grid map, the initial static trajectory is planned using an improved ACO algorithm, with the initial position of each UAV as the starting point and the target point as the ending point, and the shortest group path as the objective.

[0061] The initial static trajectory planned using the improved ACO algorithm includes:

[0062] An improved ACO algorithm is used to generate an initial static trajectory that satisfies flight constraints, including minimum turning radius, maximum turning angle, pitch angle, etc. A local and global dual pheromone update mechanism and a dynamic parameter mechanism are adopted to accelerate the convergence speed of the algorithm while avoiding getting trapped in local optima.

[0063] Specifically, refer to Figure 2 As shown, during the path construction process, each drone performs a local pheromone update on the edges it traverses after each step to prevent other drones from over-selecting the same path in this round; after each iteration, the pheromone of the entire graph is updated globally by the optimal drone path.

[0064] The pheromone update formula in the local pheromone update mechanism is:

[0065] τ ij (n+1)=(1-ξ)·τ ij (n)+ξ·τ0

[0066] Where, τ ij Let ξ be the pheromone concentration on edge (i,j); ξ∈(0,1) is the local volatile coefficient, usually taken as 0.1; τ0 is the initial pheromone value, taking a value of Where L nn is the nearest neighbor path length, and n represents the number of track points.

[0067] The pheromone update formula in the global pheromone update mechanism is:

[0068] τ ij ←(1-ρ)·τ ij +ρ·Δτ ij

[0069]

[0070] Where ρ∈(0,1) is the global volatility coefficient; Δτ ij It is the pheromone increment generated by the current optimal path; Q is a constant, and its value ranges from [10, 100]; L best This represents the total cost of the current optimal path.

[0071] Furthermore, the dynamic parameter mechanism of the improved ACO algorithm includes:

[0072] The dynamic parameters change as the number of iterations increases:

[0073]

[0074] Where α is the pheromone importance factor; α min The minimum value of the pheromone importance factor; α max β represents the maximum value of the pheromone importance factor; β is the heuristic information importance factor; β min β represents the minimum value of the heuristic importance factor. max t represents the maximum value of the heuristic importance factor; t represents the current iteration number of the algorithm; T represents the maximum number of iterations of the algorithm.

[0075] S3. Control the UAV to fly along the initial static trajectory and perform terrain scanning and flight monitoring in real time.

[0076] The initial static flight path typically employs a grid, spiral, or S-shaped path pattern to ensure comprehensive coverage of the target area. The flight path parameters include a series of preset track points, each of which precisely marks the UAV's three-dimensional coordinates (longitude, latitude, and altitude), flight speed, and attitude angle.

[0077] During real-time terrain scanning, UAVs utilize multiple sensors working in tandem to accurately identify different types of obstacles. For example, lidar can be used to quickly capture the 3D contours of obstacles, including static trees and buildings, or dynamic vehicles and pedestrians, all of which can be separated and identified using point cloud clustering algorithms. In low-visibility conditions (such as night or dusty weather), millimeter-wave radar can be used to track fast-moving obstacles or threats in real time using the principle of electromagnetic wave reflection. Alternatively, optical cameras equipped with deep learning algorithms can be used to identify various obstacles in images through target detection models (such as YOLO and Faster R-CNN), improving the obstacle recognition capabilities of UAVs in complex scenarios.

[0078] S4. Based on the obstacles encountered, an improved A* algorithm is used for local path planning to achieve flexible obstacle avoidance for the UAV. The improved A* algorithm includes a dual-distance estimation mechanism, a dynamic parameter heuristic mechanism, and a sparsity mechanism.

[0079] Specifically, the improved A* algorithm employs a dual-distance estimation mechanism of Manhattan distance and Euclidean distance when searching for the optimal path;

[0080]

[0081] D′ i =|x i -x i-1 |+|y i -yi-1 |+|z i -z i-1 | ←

[0082] Among them, D i For waypoint C i-1 Midpoint C of the feasible region i The cost of the journey, i.e., waypoint C i-1 To track point C i The actual distance is taken as the Euclidean distance; define D′. i For waypoint C i-1 Midpoint C of the feasible region i The cost of the estimated flight path, i.e., waypoint C i-1 To track point C i The estimated distance is taken as the Manhattan distance; (x i y i , z i () is point C i The coordinates, (x i-1 y i-1 , z i-1 () is point C i-1 The coordinates.

[0083] Furthermore, the improved A* algorithm employs a dynamic parameter heuristic mechanism, adjusting the exploration strategy according to the algorithm's exploration progress to accelerate the finding of the optimal solution;

[0084] f(C i )=ω1g(C i )+ω2h(C i )

[0085]

[0086] Where, f(C) i ) represents the nodes C traversed from the starting point to the target. i The estimated total cost; g(C) i () represents the distance from the starting point to the current node C. i The actual trajectory cost; h(C i ) represents the current node C i The heuristically estimated path cost to the target point; ω1 and ω2 are dynamic parameters of the actual path cost and the heuristically estimated path cost, respectively, used to adjust the search strategy. The total weight of ω1 and ω2 is 1. In the initial search phase, the algorithm is determined by h(C i The algorithm is dominated by g(C), which can quickly approach the target direction. The later search algorithm is dominated by g(C). i It is dominated by ) and can perform refined local searches.

[0087] Furthermore, the improved A* algorithm employs a sparsity mechanism to reduce the number of search nodes in the current node's neighborhood, thereby accelerating the search speed.

[0088] S5. After repeatedly traversing all waypoints, the drone reaches the destination and performs subsequent tasks.

[0089] refer to Figure 3 As shown, for a 3D raster map, the StarNode is added to the Open list, and the node with the lowest cost is removed from the Open list and added to the Close list, which is then set as the current point. It is then determined whether the current point is the target point. If so, the path is backtracked to obtain the optimal solution; otherwise, feasible child nodes are searched and their trajectory costs are calculated to determine if the constraints are met. For child nodes that meet the constraints, if their trajectory costs are low, the corresponding point in the Open list is replaced, and this process continues until all child nodes have been traversed. After the UAV successfully reaches the destination and completes status confirmation, the system initiates subsequent tasks according to preset logic.

[0090] In this embodiment of the invention, the path planning system information is first initialized based on known UAV information and satellite scan maps. Then, an improved ACO algorithm is used to generate an initial static track that satisfies flight constraints in a known environment. A local and global dual-pheromone update mechanism and a dynamic parameter mechanism are employed to accelerate algorithm convergence while avoiding getting trapped in local optima. During flight, the system senses dynamic obstacles in real time. When track conflicts occur, an improved A* algorithm is used to replan the local path, and a dynamic parameter heuristic mechanism and a cost adjustment mechanism are introduced to ensure track continuity and safety. Simulation results show that the method of this invention improves planning efficiency while possessing good dynamic obstacle avoidance capabilities and track smoothness, making it suitable for intelligent navigation tasks of UAVs in complex three-dimensional environments.

[0091] Accordingly, embodiments of the present invention also provide a path planning system for unmanned aerial vehicle (UAV) swarms based on dynamic optimal trajectories, such as... Figure 4 As shown, the system includes:

[0092] Modeling module 201 is used to construct a 3D model of the real environment based on known UAV information and satellite scan maps, and generate a 3D raster map;

[0093] The initial path planning module 202 is used to plan the initial static track based on the three-dimensional grid map, taking the initial position of each UAV as the starting point and the target point as the ending point, with the goal of minimizing the group path, and using the improved ACO algorithm.

[0094] The monitoring module 203 is used to control the UAV to fly according to the initial static flight path and to perform terrain scanning and flight monitoring in real time;

[0095] The local path planning module 204 is used to perform local path planning based on the obstacles that appear, using an improved A* algorithm to achieve flexible obstacle avoidance for the UAV.

[0096] Traversal module 205 is used to repeatedly traverse all waypoints until the UAV reaches the destination and performs subsequent tasks.

[0097] For ease of explanation, Figure 4 Only the main components of the system are shown. The system of this embodiment can be used to perform... Figure 1 The technical solutions of the method embodiments shown are similar in principle and in effect, and will not be described again here.

[0098] In an exemplary embodiment, the present invention also provides an electronic device, the electronic device comprising:

[0099] processor;

[0100] The memory stores computer-readable instructions, which, when loaded and executed by the processor, implement the steps of the UAV swarm path planning method based on dynamic optimal trajectories described above.

[0101] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention, such as... Figure 5 As shown, the electronic device 300 may include a processor 3001 and a memory 3002. Optionally, the electronic device 300 may also include a transceiver 3003. The processor 3001, memory 3002, and transceiver 3003 may be connected via a communication bus. The memory 3002 stores computer-readable instructions, which, when executed by the processor 3001, implement the steps of the UAV swarm path planning method based on dynamic optimal trajectories described above.

[0102] In a specific implementation, as one example, the processor 3001 may include one or more CPUs, for example... Figure 5 CPU0 and CPU1 are shown in the diagram.

[0103] In a specific implementation, as one example, the electronic device 300 may also include multiple processors, for example... Figure 5 The processors 3001 and 3004 are shown in the diagram. Each of these processors can be a single-core processor or a multi-core processor. Here, "processor" can refer to one or more devices, circuits, and / or processing cores used to process data (e.g., computer program instructions).

[0104] The memory 3002 is used to store the software program that executes the present invention, and is controlled by the processor 3001 to execute it. The specific implementation method can be referred to the above method embodiment, and will not be repeated here.

[0105] The transceiver 3003 is used to communicate with network devices or with terminal devices.

[0106] Optionally, the transceiver 3003 may include a receiver and a transmitter. The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function.

[0107] Optionally, the transceiver 3003 can be integrated with the processor 3001 or exist independently and be coupled to the processor 3001 through the interface circuit of the electronic device 300. This embodiment of the invention does not specifically limit this.

[0108] It should be noted that, Figure 5 The structure of the electronic device 300 shown is not intended to limit the electronic device. Actual electronic devices may include more or fewer components than shown, or combine certain components, or have different component arrangements. Furthermore, the technical effects of the electronic device 300 can be understood by referring to the technical effects of the above-described method embodiments, and will not be repeated here.

[0109] In an exemplary embodiment, the present invention also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the steps of the UAV swarm path planning method based on dynamic optimal trajectories described above. For example, the computer-readable storage medium may be a ROM, random access memory (RAM), CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc.

[0110] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0111] The use of terms such as "an embodiment," "an embodiment," "an exemplary embodiment," and "some embodiments" in the specification indicates that the described embodiment may include a specific feature, structure, or characteristic, but not every embodiment necessarily includes that specific feature, structure, or characteristic. Furthermore, when a specific feature, structure, or characteristic is described in connection with an embodiment, implementing such a feature, structure, or characteristic in conjunction with other embodiments (whether explicitly described or not) should be within the knowledge of those skilled in the art.

[0112] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. A and B can be singular or plural. Additionally, the character " / " in this article generally indicates an "or" relationship between the preceding and following related objects, but it can also represent an "and / or" relationship. Please refer to the context for a more accurate understanding.

[0113] In this invention, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of a single item or a plurality of items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, and c can be a single item or multiple items.

[0114] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0115] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0116] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0117] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0118] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0119] This invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of this invention. To provide the public with a thorough understanding of this invention, specific details are described in detail in the following preferred embodiments; however, those skilled in the art will fully understand the invention even without these details. Furthermore, to avoid unnecessary misunderstanding of the essence of this invention, well-known methods, processes, procedures, components, and circuits are not described in detail.

[0120] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for UAV swarm path planning based on dynamic optimal trajectories, characterized in that, Includes the following steps: A 3D model of the real environment is constructed based on known UAV information and satellite scan maps, and a 3D raster map is generated. Based on the aforementioned 3D grid map, the initial static trajectory is planned using the improved ACO algorithm, with the initial position of each UAV as the starting point and the target point as the ending point, and the shortest group path as the objective. Control the drone to fly along the initial static flight path and perform terrain scanning and flight monitoring in real time; Based on the obstacles encountered, an improved A* algorithm is used for local path planning to enable flexible obstacle avoidance for the UAV. After repeatedly traversing all waypoints, the drone reaches its destination and performs subsequent tasks.

2. The UAV swarm path planning method based on dynamic optimal trajectory according to claim 1, characterized in that, The initial static trajectory planned using the improved ACO algorithm includes: An improved ACO algorithm is used to generate an initial static trajectory that satisfies flight constraints, including minimum turning radius, maximum turning angle, and pitch angle. A local and global dual pheromone update mechanism and a dynamic parameter mechanism are adopted to accelerate the convergence speed of the algorithm while avoiding getting trapped in local optima.

3. The UAV swarm path planning method based on dynamic optimal trajectory according to claim 2, characterized in that, The improved ACO algorithm specifically includes: During the path construction process, each drone performs a local pheromone update on the edges it traverses after each step to prevent other drones from over-selecting the same path in the same round; after each iteration, the pheromone of the entire graph is updated globally by the optimal drone path. The pheromone update formula in the local pheromone update mechanism is: t ij (n+1)=(1-ξ)·τ ij (n)+ξ·τ0 Where, τ ij Let ξ be the pheromone concentration on edge (i,j); ξ∈(0,1) is the local volatile coefficient; τ0 is the initial pheromone value, taking a value of Where L nn It is the nearest neighbor path length, and n represents the number of waypoints; The pheromone update formula in the global pheromone update mechanism is: t ij ←(1-r)·t ij +ρ·Δτ ij Where ρ∈(0,1) is the global volatility coefficient; Δτ ij It is the pheromone increment generated by the current optimal path; Q is a constant, and its value ranges from [10, 100]; L best This represents the total cost of the current optimal path.

4. The UAV swarm path planning method based on dynamic optimal trajectory according to claim 3, characterized in that, The dynamic parameter mechanism of the improved ACO algorithm includes: The dynamic parameters change as the number of iterations increases: Where α is the pheromone importance factor; α min The minimum value of the pheromone importance factor; α max β represents the maximum value of the pheromone importance factor; β is the heuristic information importance factor; β min β represents the minimum value of the heuristic importance factor. max t represents the maximum value of the heuristic importance factor; t represents the current iteration number of the algorithm; T represents the maximum number of iterations of the algorithm.

5. The UAV swarm path planning method based on dynamic optimal trajectory according to claim 1, characterized in that, The improved A* algorithm employs a dual-distance estimation mechanism of Manhattan distance and Euclidean distance when searching for the optimal path; D′ i =|x i -x i-1 |+|y i -y i-1 |+|z i -z i-1 |← Among them, D i For waypoint C i-1 Midpoint C of the feasible region i The cost of the journey, i.e., waypoint C i-1 To track point C i The actual distance, taken as the Euclidean distance; D' i For waypoint C i-1 Midpoint C of the feasible region i The cost of the estimated flight path, i.e., waypoint C i-1 To track point C i The estimated distance is taken as the Manhattan distance; (x i y i , z i () is point C i The coordinates, (x i-1 y i-1 , z i-1 () is point C i-1 The coordinates.

6. The UAV swarm path planning method based on dynamic optimal trajectory according to claim 1, characterized in that, The improved A* algorithm employs a dynamic parameter heuristic mechanism, adjusting the exploration strategy according to the algorithm's exploration progress to accelerate the finding of the optimal solution. f(C i )=ω1g(C i )+ω2h(C i ) Where, f(C) i ) represents the nodes C traversed from the starting point to the target. i The estimated total cost; g(C) i () represents the distance from the starting point to the current node C. i The actual trajectory cost; h(C i ) represents the current node C i The heuristically estimated path cost to the target point; ω1 and ω2 are dynamic parameters of the actual path cost and the heuristically estimated path cost, respectively, used to adjust the search strategy. The total weight of ω1 and ω2 is 1. In the initial search phase, the algorithm is determined by h(C i The algorithm is dominated by g(C), which can quickly approach the target direction. The later search algorithm is dominated by g(C). i It is dominated by ) and can perform refined local searches.

7. The UAV swarm path planning method based on dynamic optimal trajectory according to claim 1, characterized in that, The improved A* algorithm employs a sparsity mechanism to reduce the number of search nodes in the current node's neighborhood, thereby accelerating the search speed.

8. A path planning system for unmanned aerial vehicle (UAV) swarms based on dynamic optimal trajectories, the system being used to implement the method as described in any one of claims 1 to 7, characterized in that, The system includes: The modeling module is used to construct a 3D model of the real environment based on known UAV information and satellite scan maps, and generate a 3D raster map. The initial path planning module is used to plan the initial static trajectory based on the three-dimensional grid map, taking the initial position of each UAV as the starting point and the target point as the ending point, with the goal of minimizing the group path, and using the improved ACO algorithm. The monitoring module is used to control the UAV to fly according to the initial static flight path and to perform terrain scanning and flight monitoring in real time; The local path planning module is used to perform local path planning based on the obstacles encountered, using an improved A* algorithm to enable the UAV to flexibly avoid obstacles. The traversal module is used to repeatedly traverse all waypoints until the UAV reaches the destination and executes subsequent tasks.

9. An electronic device, characterized in that, The electronic device includes: processor; A memory storing computer-readable instructions, which, when loaded and executed by the processor, implement the UAV swarm path planning method based on dynamic optimal trajectories as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores program code that can be called by a processor to execute the UAV swarm path planning method based on dynamic optimal trajectory as described in any one of claims 1 to 7.

Images