Replanning method and device for UAV swarm operation tasks

Abstract

This invention discloses a method and apparatus for replanning unmanned aerial vehicle (UAV) swarm operations, relating to the field of UAV path planning technology. The method includes: acquiring the current operational path of the UAV swarm; performing deviation correction on the current path of each individual UAV in the swarm using a predetermined path; simulating the path using the situational information data of the UAV swarm after deviation correction; performing deviation analysis on the simulated path using a deviation analysis model and outputting the deviation analysis results; the deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path; the deviation analysis results include whether the simulated path is qualified; if the simulated path is qualified, generating task data for the UAV swarm and the target task using the path simulation results; and replanning the future tasks of the UAV swarm using the task data. This invention can improve the efficiency and accuracy of UAV swarm task replanning.

Description

Technical Field

[0001] This invention relates to the field of unmanned aerial vehicle (UAV) path planning technology, and in particular to a method and apparatus for replanning UAV swarm operations. Background Technology

[0002] This section is intended to provide background or context for the embodiments of the invention set forth in the claims. The description herein is not an admission that it is prior art simply because it is included in this section.

[0003] In recent years, drones have been widely used in search and patrol, reconnaissance and surveillance, disaster relief, logistics and distribution, power line inspection, and agricultural irrigation due to their high flexibility, maneuverability, low safety risk, and low cost. Based on this, swarm intelligence has become an important future development direction for drones. Forming large-scale drone swarms can solve the problems of limited functionality, poor reliability, and low intelligence of existing drones, enabling them to complete more complex tasks.

[0004] In existing technologies, when allocating or planning tasks for drone swarm operations, task commands are typically sent to the drone swarm to plan its future tasks, calculate the future path information of the drone swarm, and then use an optimization model to allocate tasks. These methods offer good real-time performance, but they cannot guarantee the efficiency and accuracy of collaborative task allocation for drone swarms. Summary of the Invention

[0005] This invention provides a method for replanning UAV swarm operations, aimed at improving the efficiency and accuracy of UAV swarm task replanning. The method includes:

[0006] Obtain the current task path of the drone cluster;

[0007] Deviation correction is performed on the current path of each individual drone in the drone swarm using a predetermined path;

[0008] The system acquires situational information data of the UAV swarm after deviation correction, uses the situational information data to perform path simulation, and obtains path simulation results. The path simulation results include the simulated path, UAV flight parameters, and UAV performance parameters. In particular, the situational information data is subjected to cluster analysis, and the various types of situational data obtained from the cluster analysis are used to simulate future paths.

[0009] A deviation analysis model is used to perform deviation analysis on the simulated path and output the deviation analysis results. The deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path. The deviation analysis results include whether the simulated path is qualified.

[0010] If the simulated path is satisfactory, the path simulation results are used to generate task data for the drone cluster and the target mission.

[0011] Use mission data to replan the future missions of the drone swarm.

[0012] This invention also provides a replanning device for UAV swarm operations, used to improve the efficiency and accuracy of UAV swarm task replanning. The device includes:

[0013] The deviation correction module is used to obtain the current task path of the drone cluster; and to perform deviation correction on the current path of each individual drone in the drone cluster using a predetermined path.

[0014] The path simulation module is used to acquire situational information data of the UAV swarm after deviation correction, and to perform path simulation using the situational information data to obtain path simulation results. The path simulation results include the simulated path, UAV flight parameters, and UAV performance parameters. Among them, cluster analysis is performed on the situational information data, and the various types of situational data obtained from the cluster analysis are used to simulate future paths.

[0015] The deviation analysis module is used to perform deviation analysis on the simulated path using a deviation analysis model and output the deviation analysis results. The deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path. The deviation analysis results include whether the simulated path is qualified.

[0016] The task replanning module is used to generate task data for the UAV swarm and target mission based on the path simulation results when the simulated path is qualified; and to replan the future missions of the UAV swarm based on the task data.

[0017] This invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the above-mentioned replanning method for unmanned aerial vehicle (UAV) swarm operation tasks.

[0018] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned replanning method for unmanned aerial vehicle (UAV) swarm operations.

[0019] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-mentioned replanning method for UAV swarm operation tasks.

[0020] In this embodiment of the invention, the current task path of the UAV swarm is obtained; deviation correction is performed on the current path of each individual UAV in the swarm using a predetermined path; the situational information data of the UAV swarm after deviation correction is obtained, and path simulation is performed using the situational information data to obtain path simulation results; the path simulation results include simulated path, UAV flight parameters, and UAV performance parameters; wherein, cluster analysis is performed on the situational information data, and future path simulation is performed using various types of situational data obtained from the cluster analysis; deviation analysis is performed on the simulated path using a deviation analysis model, and deviation analysis results are output; the deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path; the deviation analysis results include whether the simulated path is qualified; when the simulated path is qualified, task data of the UAV swarm and the target task is generated using the path simulation results; the future tasks of the UAV swarm are replanned using the task data. In this embodiment of the invention, deviation correction is performed on the UAV swarm. The situational information data of the UAV swarm after deviation correction is used to simulate the path. Then, path simulation is performed on the corrected path, deviation analysis is performed on the simulated path, and task data of the UAV swarm and the target task is generated based on the deviation analysis results. Finally, the future tasks of the UAV swarm are replanned. Through the overall framework of deviation correction-simulation-deviation analysis-replanning, the efficiency and accuracy of UAV swarm task replanning are effectively improved. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the 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. In the drawings:

[0022] Figure 1 This is a flowchart illustrating the replanning method for unmanned aerial vehicle (UAV) swarm operation tasks in an embodiment of the present invention.

[0023] Figure 2 This is a specific example diagram of the replanning method for UAV swarm operation tasks in an embodiment of the present invention;

[0024] Figure 3 This is another specific example of the replanning method for drone swarm operations in this invention.

[0025] Figure 4 This is a schematic diagram of the replanning device for drone swarm operation tasks in an embodiment of the present invention;

[0026] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention. Detailed Implementation

[0027] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the embodiments of the present invention will be further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0028] To facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order.

[0029] The acquisition, transmission, storage, use, and processing of data in this application all comply with the relevant provisions of national laws and regulations.

[0030] First, the technical terms involved in the embodiments of the present invention will be explained.

[0031] Drone swarm technology: a technology in which multiple drones work together to perform tasks through self-organization and collaboration.

[0032] Cluster optimization: Improve cluster performance by adjusting and improving cluster configuration.

[0033] Path planning: In a given environment, the process of calculating one or more safe and efficient paths for a moving entity based on its origin and destination locations. This process typically involves steps such as environment modeling, obstacle detection, path search, and path optimization.

[0034] Task replanning: During task execution, due to changes in the external environment, changes in the internal system state, or the emergence of new task requirements, the process of adjusting the execution order, resource allocation, or behavior patterns of existing tasks that are no longer applicable or inefficient is carried out.

[0035] The inventors discovered through research that path planning is crucial for UAVs to perform tasks and a major challenge for autonomous UAVs in engineering applications. Existing UAV path planning algorithms are mainly divided into classical algorithms and metaheuristic algorithms, but these algorithms suffer from low search efficiency, slow convergence, and inaccuracy when facing complex environments. Therefore, the inventors proposed a replanning method for UAV swarm operations.

[0036] Figure 1 This is a flowchart illustrating the replanning method for UAV swarm operations in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes:

[0037] Step 101: Obtain the current task path of the drone cluster;

[0038] Step 102: Perform deviation correction on the current path of each individual drone in the drone swarm using a predetermined path;

[0039] Step 103: Obtain the situation information data of the UAV cluster after deviation correction, and use the situation information data to perform path simulation to obtain the path simulation results; the path simulation results include the simulated path, UAV flight parameters, and UAV performance parameters; among them, cluster analysis is performed on the situation information data, and the various types of situation data obtained from the cluster analysis are used to simulate future paths;

[0040] Step 104: Using the deviation analysis model, perform deviation analysis on the simulated path and output the deviation analysis results; the deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path; the deviation analysis results include whether the simulated path is qualified;

[0041] Step 105: When the simulated path is qualified, use the path simulation results to generate task data for the UAV cluster and the target mission;

[0042] Step 106: Use mission data to replan the future missions of the drone swarm.

[0043] from Figure 1 As can be seen from the flowchart, the method of the present invention can effectively improve the efficiency and accuracy of UAV swarm task replanning by focusing on the logic of correction, simulation of correction results, and re-execution of planning based on simulation results.

[0044] In step 101, the current job path of the drone cluster is obtained.

[0045] For example, the drone's own positioning system can be used to obtain the current task path of the drone swarm, or the drone can transmit its position, attitude and other information to the control center in real time via a wireless communication link.

[0046] In step 102, deviation correction is performed on the current path of each individual drone in the drone cluster using a predetermined path.

[0047] During implementation, the drone swarm sets a predetermined path and target mission before takeoff. The control center monitors each individual drone in the swarm and performs deviation correction when an individual drone deviates from its designated path.

[0048] Figure 2 This is a specific example diagram of the replanning method for UAV swarm operation tasks in an embodiment of the present invention, as shown below. Figure 2 As shown, deviation correction is performed on the current path of each individual drone in the drone swarm using a predetermined path, including:

[0049] Step 201: Compare the predetermined path with the current task path of each drone in the drone swarm;

[0050] Step 202: When the current task path of any UAV deviates from the predetermined path, obtain the deviation time, deviation angle, and deviation distance of the UAV.

[0051] Step 203: Monitor the actual position of the drone, and continuously adjust the drone's flight direction and speed using the predetermined path and the drone's deviation time, deviation angle, and deviation distance until the deviation distance between the drone's actual position and the predetermined path is less than the first preset deviation value.

[0052] For example, a predetermined path comparison is performed on the current operation path of the target drone cluster. When the comparison shows a deviation from the predetermined path, the deviation time and angle are recorded. Based on the recorded data and the predetermined flight speed of the drone cluster, the deviation distance is determined. The deviation distance is reported to the drone cluster control center. The control center then performs deviation correction.

[0053] Deviation distance refers to the straight-line distance between the actual position of a drone during flight and its corresponding position on the predetermined path. For example, suppose the predetermined position of the drone at time t is... The actual location is Then the deviation distance Deviation can be manifested in three ways: lateral deviation, the offset perpendicular to the predetermined path direction (e.g., left or right deviation from the flight path); longitudinal deviation, the lead or lag along the predetermined path direction (e.g., caused by abnormal speed); and comprehensive deviation, determined by a deviation analysis model (e.g., formula). ) Quantify the total deviation impact.

[0054] Specifically, when the comparison shows a deviation from the predetermined path, the deviation time and angle are statistically analyzed in a timely manner. After obtaining the corresponding data, the deviation distance is determined based on the predetermined flight speed. The determination is based on the product of speed and time, which is the distance. Alternatively, it can be calculated directly by obtaining the UAV's positioning coordinates in real time.

[0055] The correction process stops when the actual position of the drone deviates from the predetermined path by a distance less than or equal to the first preset deviation value.

[0056] After deviation correction, step 103 continues to acquire situational information data of the UAV cluster after deviation correction.

[0057] Since the current deviation correction still leaves two possible scenarios for the subsequent route situation: acceptable or unacceptable, it is necessary to continue monitoring the drone swarm to obtain situational information data after deviation correction. This situational information data will then be used to perform path simulation, yielding simulation results. The simulation results include the simulated path, drone flight parameters, and drone performance parameters. Specifically, cluster analysis will be performed on the situational information data, and the various types of situational data obtained from this cluster analysis will be used to simulate future paths, resulting in further path simulation results.

[0058] During implementation, situational information data of the UAV swarm after deviation correction is acquired. Cluster analysis is performed on the situational information data to obtain at least two types of situational information data. Future path simulation is then performed on the two types of situational information data, which can be: situational information data of a qualified predetermined route and situational information data of a predetermined route with reasonable deviation. It is understood that cluster analysis includes classifying and categorizing the data information. In this method, the preferred classification criterion is the overlap of predetermined routes.

[0059] Various path planning algorithms can be used for path simulation, such as the A algorithm and Dijkstra's algorithm. Considering environmental factors and the uncertainty of UAV flight, Monte Carlo simulation algorithm can be introduced to randomly generate a large number of sample paths for simulation calculation.

[0060] In step 104, a deviation analysis model is used to perform deviation analysis on the simulated path and output the deviation analysis results. The deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path. The deviation analysis results include whether the simulated path is qualified.

[0061] Deviation analysis models are used to analyze the difference between the UAV's planned path and the simulated path in order to evaluate the accuracy of path planning and the UAV's flight performance.

[0062] In one embodiment, based on error analysis in control theory, fault-tolerant mechanisms in robot path planning, and engineering practice data, the deviation analysis model can be expressed as follows:

[0063] ;

[0064] in, Indicates the deviation value. Indicates the deviation distance in the simulated path. Indicates the allowable deviation distance. This indicates the rated deviation value in the predetermined path.

[0065] In the formula, the first term is a normalization process, which normalizes the deviation distance ( ) and allowable deviation distance ( The difference is converted into a dimensionless relative value to avoid analytical bias caused by different units or dimensions; the second term is to introduce inherent system biases such as hardware errors and environmental noise to ensure that the model is on the ideal path ( The output value under condition 0 can still reflect the actual fault tolerance capability.

[0066] Furthermore, using a deviation analysis model, deviation analysis is performed on the simulated path, and the output deviation analysis results may include:

[0067] When the deviation value is within the set allowable deviation range, the simulation path is deemed qualified;

[0068] When the deviation value is outside the set allowable deviation range, the simulation path is determined to be unqualified.

[0069] During implementation, when the future paths of the two types of situational information data deviate from the predetermined route, the deviation data is input into the deviation analysis model for analysis. When the deviation value is within the set allowable deviation range, it means that the simulated path of the corrected UAV cluster is qualified and can be input into the control center for execution. When the deviation value is not within the set allowable deviation range, it means that the simulated path of the corrected UAV cluster is unqualified and execution in the control center is suspended.

[0070] For example, it is understandable that when It is 3m. The default value is 1m. When it is 2.5m, The value is approximately 3.9m. At this point, the ∑ value is compared with the preset ideal deviation distance of the control center or terminal. When the difference is less than 1m, it can be input into the control center to control the drone cluster to execute.

[0071] In step 105, if the simulated path is qualified, the path simulation results are used to generate task data for the UAV cluster and the target mission.

[0072] For example, if the deviation analysis result is satisfactory, the drone swarm collaborative task execution is triggered. The drone swarm receives the collaborative task instruction again. After receiving the collaborative task, the drone swarm responds by obtaining the status information of the drone swarm and the target task to obtain task data. The task data refers to various information data related to the drone's task execution; different tasks involve different data types and contents.

[0073] In step 106, the future missions of the drone swarm are replanned using mission data.

[0074] Finally, in response to mission data, the future mission planning of the drone swarm is re-planned.

[0075] Figure 3This is another specific example diagram of the replanning method for UAV swarm operation tasks in this embodiment of the invention, as shown in the figure. Figure 3 As shown, replanning future missions of a drone swarm using mission data can include:

[0076] Step 301: Perform cluster analysis on the task data to obtain task data in different groups; the task data in different groups include emergency search tasks, routine inspection tasks, and may also include classification tasks and attack tasks;

[0077] Step 302: Input the task data of different groups into the pre-built collaborative task processing model and output the UAV swarm replanning scheme; the UAV swarm replanning scheme includes the task sequence, path, and resource allocation information of each UAV; the collaborative task processing model takes minimizing the total task completion time, maximizing resource utilization and balancing the load as the objective function, and UAV endurance and communication range as constraints to perform path planning.

[0078] For example, firstly, task data clustering analysis is performed. Using UAV status, task objectives, and environmental information as input data, the task data is clustered into different groups (emergency search tasks, routine inspection tasks) based on preset classification rules (task priority). Secondly, a collaborative task processing model is constructed, including three objective functions: minimizing total task completion time, maximizing resource utilization, and balancing load, along with constraints such as UAV endurance and communication range. Finally, a replanning output is performed, providing the task sequence, path, and resource allocation scheme for each UAV.

[0079] This invention also provides a replanning device for UAV swarm operation tasks, as described in the following embodiments. Since the principle behind this device is similar to the replanning method for UAV swarm operation tasks, its implementation can refer to the implementation of the replanning method for UAV swarm operation tasks; repeated details will not be elaborated further.

[0080] Figure 4 This is a schematic diagram of a replanning device for drone swarm operations in an embodiment of the present invention, as shown below. Figure 4 As shown, the device 400 includes:

[0081] Deviation correction module 401 is used to obtain the current task path of the UAV cluster; and to perform deviation correction on the current path of each UAV in the UAV cluster using a predetermined path.

[0082] The path simulation module 402 is used to acquire situational information data of the UAV cluster after deviation correction, and to perform path simulation using the situational information data to obtain path simulation results. The path simulation results include the simulated path, UAV flight parameters, and UAV performance parameters. Among them, cluster analysis is performed on the situational information data, and the various types of situational data obtained from the cluster analysis are used to simulate future paths.

[0083] The deviation analysis module 403 is used to perform deviation analysis on the simulated path using a deviation analysis model and output the deviation analysis results; the deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path; the deviation analysis results include whether the simulated path is qualified;

[0084] The task replanning module 404 is used to generate task data for the UAV swarm and the target task using the path simulation results when the simulated path is qualified; and to replan the future tasks of the UAV swarm using the task data.

[0085] In one embodiment, the deviation correction module 401 is specifically used for:

[0086] Compare the predetermined path with the current task path of each drone in the drone swarm;

[0087] When the current task path of any UAV deviates from the predetermined path, obtain the deviation time, deviation angle, and deviation distance of the UAV;

[0088] Monitor the actual position of the drone, and continuously adjust the drone's flight direction and speed using a predetermined path and the drone's deviation time, deviation angle, and deviation distance until the deviation distance between the drone's actual position and the predetermined path is less than a first preset deviation value.

[0089] In one embodiment, the various types of situational data include qualified predetermined route situational data and reasonable deviation predetermined route situational data.

[0090] In one embodiment, the deviation analysis model is represented as follows:

[0091] ;

[0092] in, Indicates the deviation value. Indicates the deviation distance in the simulated path. Indicates the allowable deviation distance. This indicates the rated deviation value in the predetermined path;

[0093] Deviation analysis module 403 is specifically used for:

[0094] When the deviation value is within the set allowable deviation range, the simulation path is deemed qualified;

[0095] When the deviation value is outside the set allowable deviation range, the simulation path is determined to be unqualified.

[0096] In one embodiment, the task replanning module 404 is specifically used for:

[0097] Cluster analysis of the task data yielded task data in different groups; these groups included emergency search tasks and routine inspection tasks.

[0098] Different task data groups are input into a pre-built collaborative task processing model, which outputs a drone swarm replanning scheme. The drone swarm replanning scheme includes the task sequence, path, and resource allocation information of each drone. The collaborative task processing model uses minimizing the total task completion time, maximizing resource utilization, and balancing the load as objective functions, and drone endurance and communication range as constraints to perform path planning.

[0099] Figure 5 This is a schematic diagram of a computer device in an embodiment of the present invention, such as... Figure 5 As shown, this embodiment of the invention also provides a computer device 500, including a processor 501, a memory 502, and a computer program 503 stored in the memory 502 and executable on the processor 501. When the processor 501 executes the computer program 503, it implements the above-mentioned replanning method for UAV swarm operation tasks.

[0100] This invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the aforementioned replanning method for unmanned aerial vehicle (UAV) swarm operations.

[0101] This invention also provides a computer program product, which includes a computer program that, when executed by a processor, implements the above-mentioned replanning method for UAV swarm operation tasks.

[0102] In this embodiment of the invention, the current task path of the UAV swarm is obtained; deviation correction is performed on the current path of each individual UAV in the swarm using a predetermined path; the situational information data of the UAV swarm after deviation correction is obtained, and path simulation is performed using the situational information data to obtain path simulation results; the path simulation results include simulated path, UAV flight parameters, and UAV performance parameters; wherein, cluster analysis is performed on the situational information data, and future path simulation is performed using various types of situational data obtained from the cluster analysis; deviation analysis is performed on the simulated path using a deviation analysis model, and deviation analysis results are output; the deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path; the deviation analysis results include whether the simulated path is qualified; when the simulated path is qualified, task data of the UAV swarm and the target task is generated using the path simulation results; the future tasks of the UAV swarm are replanned using the task data. In this embodiment of the invention, deviation correction is performed on the UAV swarm. The situational information data of the UAV swarm after deviation correction is used to simulate the path. Then, path simulation is performed on the corrected path, deviation analysis is performed on the simulated path, and task data of the UAV swarm and the target task is generated based on the deviation analysis results. Finally, the future tasks of the UAV swarm are replanned. Through the overall framework of deviation correction-simulation-deviation analysis-replanning, the efficiency and accuracy of UAV swarm task replanning are effectively improved.

[0103] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0104] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0105] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0106] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0107] The specific embodiments described above further illustrate the purpose, technical solution, and beneficial effects of the present invention. It should be understood that the above descriptions are merely specific embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A replanning method for unmanned aerial vehicle (UAV) swarm operations, characterized in that, include: Obtain the current task path of the drone cluster; Deviation correction is performed on the current path of each individual drone in the drone swarm using a predetermined path; The system acquires situational information data of the UAV swarm after deviation correction, uses the situational information data to perform path simulation, and obtains path simulation results. The path simulation results include the simulated path, UAV flight parameters, and UAV performance parameters. In particular, the situational information data is subjected to cluster analysis, and the various types of situational data obtained from the cluster analysis are used to simulate future paths. A deviation analysis model is used to perform deviation analysis on the simulated path and output the deviation analysis results. The deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path. The deviation analysis results include whether the simulated path is qualified. If the simulated path is satisfactory, the path simulation results are used to generate task data for the drone cluster and the target mission. Re-planning future missions of drone swarms using mission data; The deviation analysis model is represented as follows: ； in, Indicates the deviation value. Indicates the deviation distance in the simulated path. Indicates the allowable deviation distance. This indicates the rated deviation value in the predetermined path; Using a deviation analysis model, deviation analysis is performed on the simulated path, and the deviation analysis results are output, including: When the deviation value is within the set allowable deviation range, the simulation path is deemed qualified; When the deviation value is outside the set allowable deviation range, the simulation path is determined to be unqualified.

2. The method as described in claim 1, characterized in that, Deviation correction is performed on the current path of each individual drone in the drone swarm using a predetermined path, including: Compare the predetermined path with the current task path of each drone in the drone swarm; When the current task path of any UAV deviates from the predetermined path, obtain the deviation time, deviation angle, and deviation distance of the UAV; Monitor the actual position of the drone, and continuously adjust the drone's flight direction and speed using a predetermined path and the drone's deviation time, deviation angle, and deviation distance until the deviation distance between the drone's actual position and the predetermined path is less than a first preset deviation value.

3. The method as described in claim 1, characterized in that, The various types of situational data include situational data for qualified predetermined routes and situational data for predetermined routes with reasonable deviations.

4. The method as described in claim 1, characterized in that, Using mission data to replan the future missions of the drone swarm, including: Cluster analysis of the task data yielded task data in different groups; these groups included emergency search tasks and routine inspection tasks. Different task data groups are input into a pre-built collaborative task processing model, which outputs a drone swarm replanning scheme. The drone swarm replanning scheme includes the task sequence, path, and resource allocation information of each drone. The collaborative task processing model uses minimizing the total task completion time, maximizing resource utilization, and balancing the load as objective functions, and drone endurance and communication range as constraints to perform path planning.

5. A replanning device for unmanned aerial vehicle (UAV) swarm operations, characterized in that, include: The deviation correction module is used to obtain the current task path of the drone cluster; Deviation correction is performed on the current path of each individual drone in the drone swarm using a predetermined path; The path simulation module is used to acquire situational information data of the UAV cluster after deviation correction, and to perform path simulation using the situational information data to obtain path simulation results. The path simulation results include simulated path, UAV flight parameters, and UAV performance parameters. Among them, cluster analysis is performed on the situational information data, and the various types of situational data obtained from the cluster analysis are used to simulate future paths. The deviation analysis module is used to perform deviation analysis on the simulated path using a deviation analysis model and output the deviation analysis results. The deviation analysis model is used to analyze the path planning effect and UAV flight performance based on the difference between the simulated path and the predetermined path. The deviation analysis results include whether the simulated path is qualified. The task replanning module is used to generate task data for the UAV swarm and the target task based on the path simulation results when the simulated path is qualified; and to replan the future tasks of the UAV swarm based on the task data. The deviation analysis model is represented as follows: ； in, Indicates the deviation value. Indicates the deviation distance in the simulated path. Indicates the allowable deviation distance. This indicates the rated deviation value in the predetermined path; The deviation analysis module is specifically used for: When the deviation value is within the set allowable deviation range, the simulation path is deemed qualified; When the deviation value is outside the set allowable deviation range, the simulation path is determined to be unqualified.

6. The apparatus as claimed in claim 5, characterized in that, The deviation correction module is specifically used for: Compare the predetermined path with the current task path of each drone in the drone swarm; When the current task path of any UAV deviates from the predetermined path, obtain the deviation time, deviation angle, and deviation distance of the UAV; Monitor the actual position of the drone, and continuously adjust the drone's flight direction and speed using a predetermined path and the drone's deviation time, deviation angle, and deviation distance until the deviation distance between the drone's actual position and the predetermined path is less than a first preset deviation value.

7. The apparatus as claimed in claim 5, characterized in that, The various types of situational data include situational data for qualified predetermined routes and situational data for predetermined routes with reasonable deviations.

8. The apparatus as claimed in claim 5, characterized in that, The task replanning module is specifically used for: Cluster analysis of the task data yielded task data in different groups; these groups included emergency search tasks and routine inspection tasks. Input task data from different groups into a pre-built collaborative task processing model to output a drone swarm replanning scheme; The drone swarm replanning scheme includes the task sequence, path, and resource allocation information for each drone. The collaborative task processing model uses minimizing the total task completion time, maximizing resource utilization, and balancing the load as objective functions, and takes the UAV's endurance and communication range as constraints to perform path planning.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 4.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the method of any one of claims 1 to 4.

Images