Path planning method and device for unmanned aerial vehicle cluster, medium and equipment

Abstract

The invention discloses a path planning method and device for an unmanned aerial vehicle cluster, a medium and equipment, and relates to the technical field of unmanned aerial vehicles. According to the method, the use environment of the unmanned aerial vehicle cluster is considered, the node accumulation cost based on the path length cost and the accumulation detector detection probability cost is constructed, and the path generation quality of the Astar algorithm and the optimality and search speed of the algorithm are improved in combination with the heuristic cost based on the path length; a marshalling path of an unmanned aerial vehicle cluster is efficiently generated through an Astar algorithm, once space conflicts occur in the marshalling path, constraint conditions are added to path planning, then the Astar algorithm is executed again, marshalling influenced by constraints is subjected to path planning again under the same constraint conditions, priority division is not needed any more, and the marshalling path planning efficiency is improved. The target path obtained by such circulation is a globally optimal solution, and the path planning effect of the unmanned aerial vehicle cluster is improved.

Description

Technical Field

[0001] This application relates to the field of unmanned aerial vehicle (UAV) technology, specifically to a path planning method, apparatus, medium, and equipment for UAV swarms. Background Technology

[0002] Unmanned aerial vehicles (UAVs) are devices operated using radio remote control equipment and their own program control devices. Path planning is a key aspect of UAV control, referring to finding a flight path from the starting point to the target point in an environment with obstacles, based on certain performance indicators and constraints.

[0003] Traditional path planning algorithms, such as the ASTAR algorithm, can only generate one path. However, in the case of drone swarms, multiple groups need to plan a single path, inevitably leading to conflicts. Existing solutions decouple tasks and perform priority-based path searching. First, each group is assigned a unique priority, and paths are searched for higher-priority groups. For lower-priority groups, the entire path generated by higher-priority groups is treated as an obstacle, and the ASTAR algorithm is used for pathfinding. However, this method is ineffective. Limiting the priority levels compromises completeness and optimality; the decoupled search algorithm can only obtain suboptimal path solutions and has a high probability of path search failure. Summary of the Invention

[0004] In summary, the main objective of this application is to provide a path planning method, apparatus, medium, and device for drone swarms, aiming to solve the problem of poor performance of existing path planning algorithms for drone swarms.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows: In a first aspect, embodiments of this application provide a path planning method for a drone swarm, comprising the following steps: The node accumulation cost is obtained based on the target path length cost and the cumulative detector detection probability cost. Based on the heuristic cost and node accumulation cost based on path length, path planning based on the Astar algorithm is performed on the target UAV swarm to obtain the grouping path; If a spatial conflict is detected in the grouping path, a target constraint is added to the path planning, and the steps of performing path planning based on the Astar algorithm for the target UAV cluster based on the heuristic cost and node accumulation cost based on the path length are returned until no spatial conflict is detected and the target path is obtained. The target constraint is used to restrict the grouping path that has a conflict and to occupy the space where the conflict occurs at the time of the conflict.

[0006] In one possible implementation of the first aspect, before obtaining the node accumulation cost based on the target path length cost and the cumulative detector detection probability cost, the method further includes: Calculate the distance between nodes based on the coordinates of the current node and the coordinates of its parent node; The target path length cost is obtained based on the path length cost of the current node's parent node and the node distance.

[0007] In one possible implementation of the first aspect, before obtaining the node accumulation cost based on the target path length cost and the cumulative detector detection probability cost, the method further includes: The cumulative detector detection probability cost is obtained based on the number of detectors in the planning environment and the instantaneous detection probability of each detector for the current node.

[0008] In one possible implementation of the first aspect, before performing path planning based on the Astar algorithm for the target UAV swarm to obtain the grouping path according to the heuristic cost based on path length and the node accumulation cost, the method further includes: A hierarchical path planning algorithm based on multi-agent structures is constructed. The hierarchical structure includes a bottom layer and a top layer. The bottom layer performs path planning based on the Astar algorithm, and the top layer constructs a constraint tree for spatial conflict detection.

[0009] In one possible implementation of the first aspect, before adding the target constraint to the path planning if a spatial conflict is detected in the marshalling path, the method further includes: In the path planning process based on the Astar algorithm, the node with the minimum cost is obtained from the constraint tree; Based on the defined conflict rules, conflict detection is performed on the node with the lowest cost to confirm whether there is a spatial conflict in the marshalling path.

[0010] In one possible implementation of the first aspect, if a spatial conflict is detected in the marshalling path, a target constraint is added to the path planning, including: If a spatial conflict is detected in the grouping path, the conflicting nodes are split to obtain two new split nodes; Inherit the information of the conflicting nodes into the new split nodes, and add the target constraints to the corresponding constraint set of the constraint tree based on the conflict information.

[0011] In one possible implementation of the first aspect, before performing path planning based on the Astar algorithm for the target UAV swarm to obtain the grouping path according to the heuristic cost based on path length and the node accumulation cost, the method further includes: Expanding the scope of target threats within environmental threats yields the target environmental threats; among them, the target threats are those that are impassable. The planned environment is discretized based on the target environmental threats to obtain a grid map; Based on the heuristic cost and node accumulation cost based on path length, path planning is performed on the target UAV swarm using the Astar algorithm to obtain the grouping path, including: Based on the heuristic cost and node accumulation cost based on path length, path planning based on the Astar algorithm is performed on the target UAV cluster in the grid map to obtain the grouping path.

[0012] Secondly, embodiments of this application provide a path planning device for a drone swarm, comprising: The cost construction module is used to obtain the node accumulation cost based on the target path length cost and the cumulative detector detection probability cost; The path planning module is used to perform path planning for the target UAV swarm based on the Astar algorithm, according to the heuristic cost based on path length and the node accumulation cost, to obtain the grouping path. The conflict reduction module is used to add target constraints to the path planning if spatial conflicts are detected in the grouping path, and return the path planning of the target UAV cluster based on the Astar algorithm according to the heuristic cost based on path length and node accumulation cost, to obtain the grouping path until no spatial conflict is detected and the target path is obtained; wherein, the target constraint is used to restrict the grouping path that has a conflict, and occupies the space where the conflict occurs at the time of the conflict.

[0013] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the path planning method for a drone swarm as provided in any of the first aspects above.

[0014] Fourthly, embodiments of this application provide an electronic device, including a processor and a memory, wherein, Memory is used to store computer programs; The processor is used to load and execute computer programs to enable electronic devices to perform path planning methods for drone swarms as provided in any of the first aspects above.

[0015] Compared with the prior art, the beneficial effects of this application are: This application proposes a path planning method, apparatus, medium, and device for a drone swarm. The method includes: obtaining a node accumulation cost based on a target path length cost and an accumulated detector detection probability cost; performing path planning on the target drone swarm based on the Astar algorithm based on a path length heuristic cost and a node accumulation cost to obtain a grouping path; if a spatial conflict is detected in the grouping path, adding a target constraint to the path planning, and returning to the steps of performing path planning on the target drone swarm based on the Astar algorithm based on the path length heuristic cost and a node accumulation cost to obtain the grouping path, until no spatial conflict is detected and the target path is obtained; wherein, the target constraint is used to restrict the grouping path that has a conflict, occupying the space where the conflict occurs at the time of the conflict. This application considers the usage environment of UAV swarms and constructs a node accumulation cost based on path length cost and cumulative detector detection probability cost. Combined with a heuristic cost based on path length, it improves the path generation quality, optimality, and search speed of the Astar algorithm. The Astar algorithm efficiently generates grouping paths for UAV swarms. If spatial conflicts occur in the grouping paths, constraints are added to the path planning, and the Astar algorithm is re-executed. The grouping affected by the constraints is re-planned under the same constraints, without priority division. The target path obtained by this loop is the globally optimal solution, thus improving the path planning effect of UAV swarms. Attached Figure Description

[0016] Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of this application; Figure 2 A flowchart illustrating the path planning method for a drone swarm provided in this application embodiment; Figure 3 A schematic diagram of a path planning device for a drone swarm provided in an embodiment of this application; The diagram is labeled as follows: 101-Processor, 102-Communication bus, 103-Network interface, 104-User interface, 105-Memory. Detailed Implementation

[0017] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0018] See attached document Figure 1 , attached Figure 1This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of this application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. The communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 105 may be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as at least one disk storage device. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component.

[0019] Those skilled in the art will understand that the appendix Figure 1 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0020] As attached Figure 1 As shown, the memory 105, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a path planning device for a drone swarm.

[0021] In the appendix Figure 1 In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device. The electronic device calls the path planning device of the UAV cluster stored in the memory 105 through the processor 101 and executes the path planning method of the UAV cluster provided in the embodiment of this application.

[0022] See attached document Figure 2 Based on the hardware device described in the foregoing embodiments, embodiments of this application provide a path planning method for a drone swarm, comprising the following steps: S10: Obtain the node accumulation cost based on the target path length cost and the cumulative detector detection probability cost.

[0023] In its implementation, the A* algorithm, also known as the Astar algorithm, is a heuristic search algorithm widely used in path planning and graph traversal, aiming to efficiently find the shortest path from the starting point to the destination. It combines the advantages of breadth-first search (BFS) and greedy algorithms, dynamically optimizing the search direction through an evaluation function. In the Astar algorithm, the design of the node accumulation cost function and the heuristic cost function has a crucial impact on the quality of the generated path, as well as the algorithm's optimality and search speed. The design of the node accumulation cost directly affects the quality of the obtained path. Considering that drone swarms may conduct special operations and face detection by detectors (such as radar), if the cost design does not include a cost for entering dangerous areas, the generated path might pass through the center of the radar, which is clearly unreasonable.

[0024] Considering the risk of detection when drone swarms fly within the detection area, they need to choose low-probability routes while maintaining their range, making full use of blind spots created by terrain obstruction to increase their chances of not being detected. Furthermore, due to interference from Earth's curvature and ground clutter, detectors have difficulty detecting near-ground targets. Therefore, drone swarms should utilize terrain undulations to fly close to the ground as much as possible to reduce the probability of detection. Thus, this application provides a node accumulation cost based on range cost, threat cost, and flight altitude cost, constructing the node accumulation cost of the current node. as follows:

[0025] in, This represents the path length cost from the initial node to the current node (occ), i.e., the target path length cost. In actual engineering, the cost is normalized to the order of [0,1] to ensure that the weighted cost logic remains consistent. This represents the cumulative detector detection probability cost from the initial node to the current node's occ. and They represent the weights, The larger the value, the more likely the shortest path is generated in the path planning, saving flight time and fuel consumption; A larger value indicates that threat avoidance is prioritized in path planning, improving the drone's survival rate. When the algorithm is applied to detector-free scenarios, it can... Set it to 0 to meet the needs of the scenario.

[0026] In one embodiment, before obtaining the node accumulation cost based on the target path length cost and the accumulated detector detection probability cost, the method further includes: Calculate the distance between nodes based on the coordinates of the current node and the coordinates of its parent node; The target path length cost is obtained based on the path length cost of the current node's parent node and the node distance.

[0027] In the specific implementation process, the target path length cost Calculated using a recursive method:

[0028] Where pre is the parent node of the current node occ. p occ This represents the coordinates of node occ. p pre This represents the coordinates of node pre. The target path length cost of the current node occ can be derived from the path length cost of its parent node. L (pre) is obtained by adding the distance between the parent node and the current node.

[0029] In one embodiment, before obtaining the node accumulation cost based on the target path length cost and the accumulated detector detection probability cost, the method further includes: The cumulative detector detection probability cost is obtained based on the number of detectors in the planning environment and the instantaneous detection probability of each detector for the current node.

[0030] In the specific implementation process, the cumulative detector detection probability cost of the current node. Calculated using a recursive method:

[0031] in, This represents the cumulative detector detection probability cost of the parent node pre of the current node occ. To plan the number of detectors in the environment, For the first j The weighting coefficients of each detector, For the first j The instantaneous detection probability of a detector for a node occ.

[0032] S20: Based on the heuristic cost and node accumulation cost based on path length, perform path planning for the target UAV cluster using the Astar algorithm to obtain the grouping path.

[0033] In practical implementation, the target drone swarm is the drone swarm to be path-planned and controlled. The drone swarm is a formation of multiple drones, typically including a master and slave drones. Heuristic cost affects the algorithm's search speed and optimality. This application's embodiment provides a heuristic cost based on path length for the current node. To improve efficiency; if Then the node will expand evenly in all directions, and when When this happens, nodes will tend to expand in the direction of larger function values, thus reducing the number of nodes searched and improving the computational efficiency of the algorithm. When there exists In this case, the search direction of a node will be dominated by the heuristic cost, and the optimality of the path will not be guaranteed.

[0034] Based on the above analysis, the function for heuristic cost should be set to a relatively large value, but should not exceed [a certain value]. In the traditional Astar algorithm, the heuristic cost function is usually the Manhattan distance or Euclidean distance between the current node and the target node. However, these functions do not closely match the function of node accumulation cost. When there are many insurmountable obstacles between the current node and the target node, the efficiency of this heuristic cost function will be very low. Therefore, this application provides a heuristic cost that considers path length. Ultimately, the heuristic cost of the current node based on path length. It can be represented as: =λ3

[0035] λ represents the shortest distance from the current node to the target node, and λ3 is an adjustment coefficient used to ensure the optimality of the Astar algorithm. It is typically set to λ3 ≤ 1 to ensure that the heuristic cost does not overestimate the actual distance in the initial stage. This is to reduce computational complexity. To reduce the complexity, a path length heuristic can be established first. This involves using the target node as the starting node and employing Dijkstra's algorithm to calculate the distance cost to any node within the raster map. In subsequent use, this cost can be obtained simply by looking up a table. The value of . In path planning tasks, once the target node is determined, it will not be easily changed. However, due to the need to deal with various unexpected situations, the path needs to be replanned in real time. Each replanning will execute the Astar algorithm once. However, the path length heuristic field only needs to be updated once at the beginning when the target node is determined. Therefore, this method of establishing the heuristic field only consumes a certain amount of computing resources at the initial moment, which can greatly improve the heuristic efficiency.

[0036] The grid map is the basis for executing the Astar algorithm, which requires discretizing the entire planning environment, which is the environment used for UAV swarm path planning.

[0037] In traditional grid map construction, the entire space is divided into several square (corresponding to a 2D map) or cube (corresponding to a 3D map) nodes, and each node has three possible states: occupied, idle, and unknown. If a node is occupied, it means that there is an obstacle within the node, and a collision will occur when a drone travels to the node; if a node is idle, it means that there is no obstacle within the node; if a node is unknown, it means that information about the node is missing.

[0038] In simple terms, traditional grid maps only distinguish between obstacles and non-obstacles. However, the special operational requirements of UAV swarms make the actual planning environment much more complex. To simplify algorithm design, environmental threats are divided into impassable and traversable threats. Terrain peaks, special air defense equipment, and flight paths of other formations within the swarm are considered impassable threats. Grids containing impassable threats and their surrounding areas are considered obstacles, meaning UAVs must detour and cannot traverse them. Early warning radars and similar devices are considered traversable threats. Grids containing traversable threats and their detection coverage areas are considered hazards. This application discretizes the planning environment map and labels the discrete grids with four types: occupied, hazardous, idle, and unknown. However, in actual implementation, unknown grids are treated as occupied grids. Meanwhile, path planning targets the host drone in the swarm. To ensure that other slave drones in the formation can also avoid obstacles, insurmountable threats can be expanded when constructing the grid map. This ensures that the planned host-based routes have a safe distance from obstacles, thereby achieving safe flight for all drones in the swarm. Specifically, based on the heuristic cost and node accumulation cost based on path length, path planning is performed on the target drone swarm using the Astar algorithm. Before obtaining the formation path, the method also includes: Expanding the scope of target threats within environmental threats yields the target environmental threats; among them, the target threats are those that are impassable. The planned environment is discretized based on the target environmental threats to obtain a grid map; Accordingly, S20 may specifically include: Based on the heuristic cost and node accumulation cost based on path length, path planning based on the Astar algorithm is performed on the target UAV cluster in the grid map to obtain the grouping path.

[0039] S30: If a spatial conflict is detected in the grouping path, add the target constraint to the path planning and return the steps of performing path planning for the target UAV cluster based on the Astar algorithm according to the heuristic cost based on the path length and the node accumulation cost, until no spatial conflict is detected and the target path is obtained; wherein, the target constraint is used to restrict the grouping path that has a conflict and occupy the space where the conflict occurs at the time of the conflict.

[0040] In practical implementation, multi-group cooperative route planning requires finding a path for each UAV swarm group, but the path search algorithm based on the Astar algorithm can only generate one path. If each group searches its own path using the Astar algorithm, route conflicts will inevitably occur, meaning that the distance between the updated path points of two groups at a certain moment is less than the required safety constraint distance. To mitigate this conflict, this application embodiment constructs a hierarchical path planning algorithm based on a multi-agent structure, using the Conflict-Based Search (CBS) algorithm as a foundation. Specifically, before S30, the method further includes: A hierarchical path planning algorithm based on multi-agent structures is constructed. The hierarchical structure includes a bottom layer and a top layer. The bottom layer performs path planning based on the Astar algorithm, and the top layer constructs a constraint tree for spatial conflict detection.

[0041] In the specific implementation process, the above algorithm adopts a two-layer search architecture. The top layer constructs a constraint tree to resolve route conflicts between different formations, and the bottom layer uses path planning based on the Astar algorithm. In the search process, in addition to the original map constraints, it is also necessary to consider the constraints obtained from the constraint tree.

[0042] In one embodiment, if a spatial conflict is detected in the marshalling path, the method further includes, before adding the target constraint to the path planning, the following: In the path planning process based on the Astar algorithm, the node with the minimum cost is obtained from the constraint tree; Based on the defined conflict rules, conflict detection is performed on the node with the lowest cost to confirm whether there is a spatial conflict in the marshalling path.

[0043] In the specific implementation process, for N groups A1, A2...A N Each group The starting point is The destination is , i Belongs to N, where N is a natural number. Grouping. The path starts from the origin. To the finish line A series of pathpoints with distance constraints are used to represent the path, meaning the distance between two adjacent pathpoints must be less than a set threshold, typically equivalent to the map resolution. In the CBS algorithm, conflicts are only categorized as vertex and edge conflicts. However, in the spatial collaboration of multiple UAV swarms, stricter conflict rules need to be defined. t Time, grouping and The occupied grid cells are respectively and If satisfied That is, the distance between two grid cells does not exceed the set distance threshold. d conflict Considered as a group and The path encountered a spatial conflict. With a clear definition of spatial conflict, a solution is considered valid if and only if the generated solution does not have any conflicts.

[0044] The constraint tree is a priority queue where each node consists of a solution, its cost, and a set of constraints to be assigned. The priority of the constraint tree is determined by the cost of the solutions. During algorithm execution, the node with the lowest cost is selected from the constraint tree at each step, and conflict checks are performed on the solutions within that node. If no spatial conflict occurs, the solution is considered the optimal solution that ensures all grouped paths do not conflict, and the algorithm terminates.

[0045] In one embodiment, if a spatial conflict is detected in the grouping path, a target constraint is added to the path planning, including: If a spatial conflict is detected in the grouping path, the conflicting nodes are split to obtain two new split nodes; Inherit the information of the conflicting nodes into the new split nodes, and add the target constraints to the corresponding constraint set of the constraint tree based on the conflict information.

[0046] In practice, when a spatial conflict is detected, new constraints are added to the calculation before re-execution. Assuming that... t Time, grouping Occupied grid and Occupied grid A spatial conflict has occurred. To mitigate this conflict, two constraint design schemes exist: restricting grouping. exist t Occupy time and restricted grouping exist t Occupy time Based on these two different constraints, the node splits into two new nodes, i.e., the split-new nodes. The split-new nodes inherit all the contents of the original node and add new constraints to the constraint set.

[0047] At this point, the constrained group needs to replan its path. The new node passes the constraint set and the group number requiring path replanning down to the underlying search module. The underlying search module uploads the newly planned path to the new node based on the received instructions. The new node updates the solution and its cost based on the returned information, and after updating, it is pushed back into the constraint tree. The algorithm then continues to retrieve nodes from the constraint tree and repeat the same process until a solution without spatial conflicts is found. This solution is the optimal solution for path planning, i.e., the target path.

[0048] In summary, this application embodiment, by considering the usage environment of UAV swarms, constructs a node accumulation cost based on path length cost and cumulative detector detection probability cost, and combines it with a heuristic cost based on path length to improve the path generation quality, optimality, and search speed of the Astar algorithm. The Astar algorithm efficiently generates grouping paths for UAV swarms. If spatial conflicts occur in the grouping paths, constraints are added to the path planning, and the Astar algorithm is re-executed. The grouping affected by the constraints is re-planned under the same constraints, without priority division. The target path obtained by this loop is the globally optimal solution, thus improving the path planning effect of UAV swarms.

[0049] See attached document Figure 3 Based on the same inventive concept as in the foregoing embodiments, this application also provides a path planning device for a drone swarm, comprising: The cost construction module is used to obtain the node accumulation cost based on the target path length cost and the cumulative detector detection probability cost; The path planning module is used to perform path planning for the target UAV swarm based on the Astar algorithm, according to the heuristic cost based on path length and the node accumulation cost, to obtain the grouping path. The conflict reduction module is used to add target constraints to the path planning if spatial conflicts are detected in the grouping path, and return the path planning of the target UAV cluster based on the Astar algorithm according to the heuristic cost based on path length and node accumulation cost, to obtain the grouping path until no spatial conflict is detected and the target path is obtained; wherein, the target constraint is used to restrict the grouping path that has a conflict, and occupies the space where the conflict occurs at the time of the conflict.

[0050] Those skilled in the art should understand that the division of the various modules in the embodiments is merely a logical functional division. In actual applications, they can be fully or partially integrated into one or more actual carriers. These modules can be implemented entirely in software through processing unit calls, entirely in hardware, or a combination of software and hardware. It should be noted that each module in the path planning device of the UAV swarm in this embodiment corresponds one-to-one with each step in the path planning method of the UAV swarm in the aforementioned embodiments. Therefore, the specific implementation of this embodiment can refer to the implementation of the path planning method of the aforementioned UAV swarm, which will not be repeated here.

[0051] Based on the same inventive concept as in the foregoing embodiments, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the path planning method for a drone swarm as provided in the embodiments of this application.

[0052] Based on the same inventive concept as in the foregoing embodiments, embodiments of this application also provide an electronic device, including a processor and a memory, wherein, Memory is used to store computer programs; The processor is used to load and execute computer programs to enable electronic devices to perform path planning methods for drone swarms as provided in the embodiments of this application.

[0053] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0054] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0055] As an example, executable instructions may, but do not necessarily, correspond to files in the file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborative files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0056] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0057] 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 system 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 system. 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 system that includes that element.

[0058] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0059] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a multimedia terminal device (which may be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0060] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A path planning method for a drone swarm, characterized in that, Includes the following steps: The node accumulation cost is obtained based on the target path length cost and the cumulative detector detection probability cost. Based on the heuristic cost based on path length and the node accumulation cost, path planning based on the Astar algorithm is performed on the target UAV cluster to obtain the grouping path; If a spatial conflict is detected in the grouping path, a target constraint is added to the path planning, and the step of performing path planning on the target UAV cluster based on the Astar algorithm according to the heuristic cost based on the path length and the node accumulation cost is returned to obtain the grouping path, until no spatial conflict is detected and the target path is obtained; wherein, the target constraint is used to restrict the grouping path that has a conflict, and occupies the space where the conflict occurs at the time of the conflict.

2. The path planning method for unmanned aerial vehicle (UAV) swarms according to claim 1, characterized in that, Before obtaining the node accumulation cost based on the target path length cost and the accumulated detector detection probability cost, the method further includes: Calculate the distance between nodes based on the coordinates of the current node and the coordinates of its parent node; The target path length cost is obtained based on the path length cost of the parent node of the current node and the distance to the node.

3. The path planning method for a drone swarm according to claim 1, characterized in that, Before obtaining the node accumulation cost based on the target path length cost and the accumulated detector detection probability cost, the method further includes: The cumulative detector detection probability cost is obtained based on the number of detectors in the planning environment and the instantaneous detection probability of each detector for the current node.

4. The path planning method for a drone swarm according to claim 1, characterized in that, Before performing path planning based on the Astar algorithm for the target UAV swarm to obtain the grouping path according to the heuristic cost based on path length and the node accumulation cost, the method further includes: A hierarchical path planning algorithm based on multi-agent structures is constructed; wherein the hierarchical structure includes a bottom layer and a top layer, the bottom layer executes the path planning based on the Astar algorithm, and the top layer constructs a constraint tree, which is used for the detection of spatial conflicts.

5. The path planning method for a drone swarm according to claim 4, characterized in that, Before adding target constraints to the path planning if a spatial conflict is detected in the grouping path, the method further includes: During the path planning based on the Astar algorithm, the node with the minimum cost is obtained from the constraint tree; According to the defined conflict rules, conflict detection is performed on the node with the lowest cost to confirm whether there is a spatial conflict in the grouping path.

6. The path planning method for a drone swarm according to claim 4, characterized in that, If a spatial conflict is detected in the grouping path, then adding a target constraint to the path planning includes: If a spatial conflict is detected in the grouping path, the conflicting nodes are split to obtain two new split nodes. The information of the conflicting nodes is inherited to the new split node, and the target constraints are added to the corresponding constraint set of the constraint tree according to the conflict information.

7. The path planning method for a drone swarm according to claim 1, characterized in that, Before performing path planning based on the Astar algorithm for the target UAV swarm to obtain the grouping path according to the heuristic cost based on path length and the node accumulation cost, the method further includes: The scope of the target threats existing in the environmental threats is expanded to obtain the target environmental threats; wherein, the target threats are impassable threats; Based on the target environmental threats, the planned environment is discretized to obtain a grid map; The step of performing path planning on the target UAV swarm based on the Astar algorithm, according to the heuristic cost based on path length and the node accumulation cost, to obtain the grouping path, includes: Based on the heuristic cost based on path length and the node accumulation cost, path planning based on the Astar algorithm is performed on the target UAV cluster in the grid map to obtain the grouping path.

8. A path planning device for a drone swarm, characterized in that, include: The cost construction module is used to obtain the node accumulation cost based on the target path length cost and the cumulative detector detection probability cost; The path planning module is used to perform path planning for the target UAV cluster based on the Astar algorithm, according to the heuristic cost based on path length and the node accumulation cost, to obtain the grouping path. The conflict reduction module is used to add target constraints to the path planning if spatial conflicts are detected in the grouping path, and return the path planning based on the Astar algorithm for the target UAV cluster according to the heuristic cost based on the path length and the node accumulation cost to obtain the grouping path until no spatial conflicts are detected and the target path is obtained; wherein, the target constraint is used to restrict the grouping path that has conflicts to occupy the space where the conflict occurs at the time of the conflict.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the path planning method for the drone swarm as described in any one of claims 1-7.

10. An electronic device, characterized in that, Including processor and memory, among which, The memory is used to store computer programs; The processor is used to load and execute the computer program to enable the electronic device to perform the path planning method for the drone swarm as described in any one of claims 1-7.

Images