Unmanned aerial vehicle cluster task management method and device, computer device and storage medium
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-01-29
- Publication Date
- 2026-05-12
Smart Images
Figure CN121613947B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of unmanned aerial vehicle (UAV) technology, and in particular to UAV swarm mission management methods, devices, computer equipment, and storage media. Background Technology
[0002] With the development of drone swarm technology, drone swarms have been widely applied in many fields due to their advantages such as distributed collaboration, wide coverage, and strong fault tolerance. In actual complex tasks, the formation needs to execute multiple stages of tasks in a continuous manner, and the smoothness of the connection between each stage directly determines the overall efficiency and accuracy.
[0003] From a technical perspective, a complete drone swarm mission can be viewed as a stitch-together sequence of multiple discrete animation clips. Here, "animation" refers to the concrete representation of core information such as the motion state, attitude trajectory, position changes, and collaborative logic of each mission stage of the swarm, carrying the behavioral data and control commands for the corresponding stage. Due to the characteristics of the mission, the animations at different stages have inherent discontinuities in parameters, timing, and other aspects.
[0004] In task execution, efficient matching and seamless integration of animation information is crucial for improving efficiency. Inaccurate matching can easily lead to problems such as posture disorder and positional deviation, and may even cause cluster collisions and task interruptions. Therefore, quickly aligning the core information of each animation through matching algorithms to achieve seamless splicing is an inevitable way to improve the efficiency and stability of cluster tasks. However, this field still faces many challenges: First, animation data is complex, heterogeneous, and massive, increasing the computational complexity of algorithms; second, external disturbances can easily cause information distortion, requiring higher robustness from the algorithms. Existing methods are mostly adapted to single scenarios, making it difficult to balance speed, accuracy, and anti-interference capabilities, and thus unable to meet the needs of complex tasks. Summary of the Invention
[0005] This invention provides a method, apparatus, computer device, and storage medium for managing unmanned aerial vehicle (UAV) swarm tasks, aiming to improve the task execution efficiency of UAV swarms.
[0006] In a first aspect, embodiments of the present invention provide a method for managing unmanned aerial vehicle (UAV) swarm tasks, including:
[0007] Obtain the target task to be executed by the drone swarm; wherein the target task includes multiple consecutive animation processes, and each animation process contains waypoint information of multiple drones;
[0008] Based on the waypoint information, obtain the set of aircraft coordinates for the first frame and the set of aircraft coordinates for the last frame in each animation process;
[0009] Based on the set of aircraft coordinates in the first frame and the set of aircraft coordinates in the last frame, a waypoint mapping table between two adjacent animation processes is calculated using an optimal matching algorithm.
[0010] Based on the waypoint mapping table, a cumulative mapping relationship is generated, and the waypoints of the UAVs in each animation process are exchanged and optimized as a whole to obtain the optimized waypoints for each animation process.
[0011] Path planning is performed on the optimized waypoints to obtain the waypoint planning results for the target task, and the UAV cluster is controlled to execute the target task according to the waypoint planning results.
[0012] Secondly, embodiments of the present invention provide a drone swarm task management device, comprising:
[0013] The task acquisition unit is used to acquire the target tasks to be executed by the UAV cluster; wherein, the target tasks include multiple continuous animation processes, and each animation process contains waypoint information of multiple UAVs;
[0014] The set acquisition unit is used to acquire the set of aircraft coordinates for the first frame and the set of aircraft coordinates for the last frame in each animation process based on the waypoint information.
[0015] The mapping calculation unit is used to calculate the waypoint mapping table between two adjacent animation processes based on the first frame aircraft coordinate set and the last frame aircraft coordinate set using an optimal matching algorithm.
[0016] The waypoint optimization unit is used to generate a cumulative mapping relationship based on the waypoint mapping table, and to perform overall exchange optimization of the UAV waypoints in each animation process to obtain the optimized waypoints for each animation process.
[0017] The planning and control unit is used to perform path planning on the optimized waypoints, obtain the waypoint planning results for the target task, and control the UAV cluster to execute the target task according to the waypoint planning results.
[0018] Thirdly, embodiments of the present invention provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the UAV swarm task management method as described in the first aspect.
[0019] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the UAV swarm task management method as described in the first aspect.
[0020] This invention provides a method, apparatus, computer device, and storage medium for managing unmanned aerial vehicle (UAV) swarm tasks. The method includes: acquiring a target task to be executed by the UAV swarm; wherein the target task includes multiple consecutive animation processes, and each animation process contains waypoint information for multiple UAVs; acquiring the first frame's aircraft coordinate set and the last frame's aircraft coordinate set for each animation process based on the waypoint information; calculating a waypoint mapping table between adjacent animation processes using an optimal matching algorithm based on the first frame's and last frame's aircraft coordinate sets; generating a cumulative mapping relationship based on the waypoint mapping table, and performing overall exchange optimization on the UAV waypoints in each animation process to obtain optimized waypoints for each animation process; performing path planning on the optimized waypoints to obtain the waypoint planning result for the target task, and controlling the UAV swarm to execute the target task according to the waypoint planning result. This invention uses an optimal matching algorithm to accurately calculate the waypoint mapping table, effectively solving the connection problem between different animation processes and avoiding attitude disorder, position deviation, swarm collisions, and task interruptions caused by inaccurate matching in traditional methods. Meanwhile, by optimizing waypoints through overall exchange, the coherence between various animation processes can be further improved, making the transition between stages of the drone swarm more natural and smooth when performing tasks, thereby improving the task execution efficiency and accuracy of the drone swarm. Attached Figure Description
[0021] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0022] Figure 1 A flowchart illustrating a drone swarm task management method provided in an embodiment of the present invention;
[0023] Figure 2 A schematic block diagram of a drone swarm task management device provided in an embodiment of the present invention;
[0024] Figure 3 This is a first example diagram of a drone swarm task management method provided in an embodiment of the present invention;
[0025] Figure 4 This is a second example diagram of a drone swarm task management method provided in an embodiment of the present invention;
[0026] Figure 5 This is a third example diagram of a drone swarm task management method provided in an embodiment of the present invention. Detailed Implementation
[0027] 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. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0028] It should be understood that, when used in this specification and the appended claims, the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.
[0029] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.
[0030] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0031] Please see below. Figure 1 The present invention provides a method for managing unmanned aerial vehicle (UAV) swarm tasks, which specifically includes steps S101 to S105.
[0032] Step S101: Obtain the target task to be executed by the drone cluster; wherein, the target task includes multiple consecutive animation processes, and each animation process contains waypoint information of multiple drones;
[0033] Step S102: Obtain the set of aircraft coordinates for the first frame and the set of aircraft coordinates for the last frame in each animation process based on the waypoint information;
[0034] Step S103: Based on the set of aircraft coordinates in the first frame and the set of aircraft coordinates in the last frame, calculate the waypoint mapping table between two adjacent animation processes using the optimal matching algorithm;
[0035] Step S104: Generate a cumulative mapping relationship based on the waypoint mapping table, and perform overall exchange optimization on the UAV waypoints in each animation process to obtain the optimized waypoints for each animation process;
[0036] Step S105: Perform path planning on the optimized waypoints to obtain the waypoint planning results for the target task, and control the UAV cluster to execute the target task according to the waypoint planning results.
[0037] In this embodiment, the target task, which includes multiple consecutive animation processes (each animation process contains waypoint information of multiple UAVs), is first obtained. Then, the aircraft coordinate sets of the first and last frames of each animation process are extracted based on the waypoint information. Then, based on these coordinate sets, a waypoint mapping table between adjacent animation processes is calculated using an optimal matching algorithm. Then, a cumulative mapping relationship is generated based on the mapping table, and the UAV waypoints of each animation process are exchanged and optimized as a whole to obtain optimized waypoints. Finally, path planning is performed on the optimized waypoints to generate waypoint planning results, thereby controlling the UAV cluster to execute the target task.
[0038] This embodiment uses an optimal matching algorithm to accurately calculate the waypoint mapping table, effectively solving the connection problem between different animation processes and avoiding attitude disorder, position deviation, swarm collision, and mission interruption caused by inaccurate matching in traditional methods. Furthermore, by optimizing waypoints through overall exchange, the coherence between animation processes is further improved, making the transitions between stages more natural and smooth during UAV swarm mission execution, thereby improving the mission execution efficiency and accuracy of the UAV swarm.
[0039] This embodiment addresses the optimal matching requirements between multiple animations, optimizing the process for new application scenarios and achieving significant technical results: by expanding the processing scope from single-frame matching to global matching of continuous animation sequences, more comprehensive task coverage is achieved; the optimization strategy of hierarchical matching and cumulative mapping significantly improves matching quality and computational efficiency; it directly addresses practical multi-animation splicing application scenarios, accurately adapting to the real-world needs of UAV swarms executing multiple tasks consecutively, making it more practical; it also offers outstanding convenience, as when a segment of the flight mission changes, only that segment and subsequent matching content need to be updated, without replanning the entire mission, saving computation time and effectively ensuring the timeliness of mission execution. Furthermore, this embodiment fills the technical gap in continuous animation sequence matching, effectively solving the path planning problem of UAV swarms in multi-animation splicing scenarios in practical applications. Algorithm optimization further improves computational efficiency, ultimately making efficient matching of large-scale animation sequences possible, providing strong technical support for the stable and efficient execution of continuous tasks by UAV swarms.
[0040] In one embodiment, step S101 includes:
[0041] Let A denote each animation process in the target task as A. i And each animation process A i The drone in the middle is denoted as A.ij Where i = 1, 2...k, j = 1, 2...w, k represents the total number of animation processes, and w represents each animation process A. i The total number of drone sorties;
[0042] Determine if there is an animation process where the number of drone sorties is not w;
[0043] If an animation process is determined to have a drone sortie count that is not w, then the corresponding animation process is marked as invalid and removed.
[0044] In this embodiment, each animation process in the target task is labeled A. i Each drone in the animation process is labeled A. ij By checking the number of drone sorties during the animation process, the standardization and consistency of each animation process involved in the task can be ensured. If there is an animation process where the number of drone sorties does not meet the set number w, it is marked as invalid and removed, which can avoid task execution errors caused by abnormal animation processes.
[0045] After removing invalid animation processes, a set of valid animation processes is obtained for the target task. Each valid animation process in this set can then be further analyzed and processed. For each valid animation process A... i Its internal drone A ij Each has a clear identifier and corresponding waypoint information. This waypoint information is the basis for subsequent coordinate set extraction and waypoint mapping table calculation.
[0046] In one embodiment, step S102 includes:
[0047] Obtain each drone A in each animation process ij The first frame coordinates A ijS And according to each drone A ij The first frame coordinates A ijS Construct the first frame's aircraft coordinate set A iS ;
[0048] Obtain each drone A in each animation process ij The coordinates of the last frame A ijE And according to each drone A ij The coordinates of the last frame A ijE Construct the tail frame aircraft coordinate set A iE .
[0049] This embodiment uses waypoint information from the animation process to obtain the coordinates of each UAV in the first and last frames, thereby constructing the first-frame and last-frame UAV coordinate sets respectively. These two sets are key data for subsequent calculation of the waypoint mapping table between adjacent animation processes. The first-frame UAV coordinate set reflects the position distribution of the UAVs at the beginning of each animation process, while the last-frame UAV coordinate set reflects the position state of the UAVs at the end of that animation process. By analyzing and processing these two sets, we can clearly understand the positional changes of the UAVs in different animation processes, providing strong data support for subsequent mission planning.
[0050] like Figure 3 As shown, it includes three consecutive animation processes, namely animation process 1, animation process 2 and animation process 3. Each of the three animation processes includes 3 drones. Taking animation process 1 as the reference, the drone coordinate set of the first frame in animation process 1 is distributed according to ①, ② and ③. The drone coordinate set of the first frame in animation process 2 is distributed according to ③, ① and ②. The drone coordinate set of the first frame in animation process 3 is distributed according to ②, ③ and ①.
[0051] In one embodiment, step S103 includes:
[0052] The coordinates of the last frame of the preceding animation process and the coordinates of the first frame of the following animation process are input into the KM algorithm, which then outputs a waypoint mapping table T that minimizes the total travel distance of all UAVs. (i,i+1) Where i = 1, 2, ..., k-1.
[0053] This embodiment uses the KM algorithm to calculate the waypoint mapping table between two adjacent animation processes.
[0054] The KM algorithm is an efficient algorithm for finding the maximum weight matching in a weighted bipartite graph. In this scenario, it can find an optimal matching method based on the coordinate sets of the last and first frames of two adjacent animation processes, so that the total movement distance of all drones when transitioning from one animation process to the next is minimized.
[0055] Specifically, for two adjacent animation processes, the coordinate set of the last frame of the preceding animation process and the coordinate set of the first frame of the following animation process are provided as input to the KM algorithm. The KM algorithm calculates the movement distance corresponding to each possible pair of drone matches and uses these distances as edge weights to construct a weighted bipartite graph. Then, through a series of calculations and adjustments, a maximum-weighted matching is found, which is the matching scheme that minimizes the total movement distance of all drones. This matching scheme is based on the waypoint mapping table T. (i,i+1) Output in the form of optimal mapping table T (i,i+1) =KM(A iE A(i+1)S ), where i = 1, 2, ..., k-1, i represents the number of the previous animation process, and i+1 represents the number of the next animation process.
[0056] like Figure 4 As shown, in T 1,2 In this diagram, 1=>3 means that drone 1 in animation process A1 should go to the position of drone 3 in animation process A2; 2=>1 means that drone 2 in A1 should go to the position of drone 1 in A2; 3=>2 means that drone 3 in A1 should go to the position of drone 2 in A2, and so on. The waypoint mapping tables between other adjacent animation processes are calculated in the same way. This yields a waypoint mapping table for all adjacent animation processes, laying the foundation for subsequent generation of cumulative mapping relationships and waypoint optimization.
[0057] This embodiment uses the KM algorithm to calculate the waypoint mapping table, ensuring more reasonable and efficient transitions between different animation processes for the UAV. Because the shortest total travel distance means less energy consumed and less flight time during flight, it reduces mission execution costs and time. Simultaneously, it also reduces the risk of collisions between UAVs, improving mission safety.
[0058] In practical applications, to ensure the accuracy and efficiency of the KM algorithm, preprocessing of the input coordinate set is necessary. For example, coordinate normalization can be performed to compare coordinates from different animation processes at the same scale; or coordinate filtering can be applied to remove potential noise and outliers. Furthermore, the KM algorithm can be optimized based on specific needs, such as employing parallel computing to accelerate its execution and adapt to the requirements of large-scale UAV swarm tasks.
[0059] In one embodiment, step S104 includes:
[0060] Based on the waypoint mapping table, taking the first animation process as a reference, the waypoint information of the UAV in the previous animation process in the next animation process is obtained in two adjacent animation processes, so as to generate a cumulative mapping relationship from the first animation process to each subsequent animation process.
[0061] Based on the cumulative mapping relationship, the waypoints of the UAVs in each animation process are exchanged as a whole to obtain an animation process that includes optimized waypoints.
[0062] This embodiment uses the obtained waypoint mapping table to deduce the correspondence between UAV waypoints in adjacent animation processes, starting from the first animation process, forming a cumulative mapping relationship. This cumulative mapping relationship can comprehensively and clearly show the position changes and correspondences of each UAV in subsequent animation processes, starting from the first animation process. When exchanging UAV waypoints in each animation process based on the cumulative mapping relationship, the distribution of all UAVs in each animation process is considered holistically, avoiding the overall inconsistency that may be caused by local adjustments, and ensuring a tighter and more natural connection between each animation process.
[0063] The animation process, including optimized waypoints, obtained after the overall exchange, exhibits significantly improved coherence and smoothness. In actual drone swarm missions, optimized waypoints enable drones to follow more rational flight paths, reducing unnecessary flight distances and turns, thereby lowering energy consumption and extending flight time. Furthermore, optimized waypoints further reduce the risk of collisions between drones, enhancing mission safety and stability.
[0064] like Figure 5 As shown, based on T (1,2) ~T (i,i+1) Taking UAV No. 1 as an example, in T 1,2 In the equation, 1=>3, therefore in A2, the location of drone number 3 should be where drone number 1 should be. Therefore, F... 1,2 In the middle, there is 1=>3; continue looking at T. 2,3 In the equation, 3=>2, therefore, in A3, the position of drone 2 should be where drone 3 should be. (The last part, "T", appears to be a typo and can be omitted.) 1,2 With T 2,3 Accumulation shows that UAV 1 is located at position 1 in A1, therefore F 1,1 Since 1=>1; Drone 1 is located at position 3 in A2, therefore F 1,2 Since 1 => 3; Drone 1 should be in position 2 in A3, therefore F 1,3 There is 1=>2. F i,j Essentially, it involves determining the correct position of each numbered drone in the j-th frame, using drone number i as a reference. This process is repeated sequentially to generate a mapping F from the first animation to the current frame. (1,1) ~F (1,i+1) and A i A is obtained by exchanging all the waypoints of each drone in the process. i '(like Figure 5 The animation process of optimizing waypoints (A1', A2', A3') is included to avoid detours caused by unreasonable path settings when the drone is performing continuous tasks.
[0065] In a specific embodiment, based on the waypoint mapping table and taking the first animation process as a reference, the waypoint information of the UAV in the previous animation process in the subsequent animation process is obtained in two adjacent animation processes, thereby generating a cumulative mapping relationship from the first animation process to each subsequent animation process, including:
[0066] When any animation process other than the first animation process is updated, waypoint mapping is performed based on the updated animation process, and a new cumulative mapping relationship is generated.
[0067] This embodiment takes into account the possibility that the animation process may change in practical applications. For example, when other animation processes besides the first one are updated, the entire task may need to be replanned and mapped in the conventional way, which would consume a lot of time and computing resources. This embodiment, however, performs waypoint mapping based on the updated animation process and generates new cumulative mapping relationships, thereby avoiding such unnecessary repetitive operations and further improving task execution efficiency.
[0068] For example, in a large-scale drone performance, multiple consecutive animation sequences were originally planned. However, before the performance, due to certain reasons, some of these sequences need to be modified. Using traditional methods, the entire performance would need to be replanned, which would not only increase computation time but also potentially affect the performance's timeliness. This embodiment, however, only requires updating waypoint mappings and cumulative mapping relationships for the updated animation sequences and their subsequent sequences, without needing to replan the entire task.
[0069] Specifically, when an animation process is updated, a new waypoint mapping table is first calculated using the aircraft coordinates of the first and last frames of the updated animation process, employing an optimal matching algorithm. Then, based on this new waypoint mapping table and the previously generated cumulative mapping relationships, the cumulative mapping relationships from the first animation process to each subsequent animation process are updated. This allows for quick and efficient task adjustments, saving computation time while ensuring the timeliness of UAV swarm task execution.
[0070] In practice, to further improve efficiency, parallel computing can be used to process the generation of updated waypoint mappings and cumulative mapping relationships. For example, by utilizing multi-core processors or distributed computing systems to process multiple animation processes simultaneously, update time can be significantly shortened and system real-time performance improved.
[0071] In one embodiment, step S105 includes:
[0072] According to the execution order of the animation process of the target task, pairwise path planning is performed on two adjacent animation processes to obtain the waypoint planning result.
[0073] This embodiment, after obtaining optimized waypoints, performs pairwise path planning for adjacent animation processes, fully considering the transition between different animation processes to ensure the rationality and continuity of the UAV's flight path. For each pair of adjacent animation processes, the optimal path for the UAV to transition from one animation process to the next can be determined based on its optimized waypoints. For example, advanced path planning algorithms, such as A* algorithm and Dijkstra's algorithm, can be used to find the shortest or optimal path. Simultaneously, collision avoidance between UAVs needs to be considered to prevent collisions during path planning. During path planning, the path can also be adjusted and optimized according to actual conditions. For example, if a path is found to have areas with high flight difficulty, such as areas with strong winds or many obstacles, the path can be appropriately adjusted to ensure the UAV can fly safely and stably.
[0074] Once the waypoint planning results are obtained, the drone swarm can be precisely controlled to execute the target mission. During execution, the flight status of the drones can be monitored in real time, allowing for timely detection and handling of potential problems, such as drones deviating from their flight path or exhibiting abnormal flight speeds. Precise control of the drone swarm ensures smoother transitions between different stages of mission execution, further improving the mission execution efficiency and accuracy of the drone swarm and providing strong support for its application in various complex mission scenarios.
[0075] Figure 2 This is a schematic block diagram of a drone swarm task management device 200 provided in an embodiment of the present invention. The device 200 includes:
[0076] The task acquisition unit 201 is used to acquire the target task to be executed by the UAV cluster; wherein, the target task includes multiple continuous animation processes, and each animation process contains waypoint information of multiple UAVs;
[0077] The set acquisition unit 202 is used to acquire the set of aircraft coordinates of the first frame and the set of aircraft coordinates of the last frame in each animation process based on the waypoint information.
[0078] The mapping calculation unit 203 is used to calculate the waypoint mapping table between two adjacent animation processes based on the first frame aircraft coordinate set and the last frame aircraft coordinate set using an optimal matching algorithm.
[0079] The waypoint optimization unit 204 is used to generate a cumulative mapping relationship based on the waypoint mapping table, and to perform overall exchange optimization of the UAV waypoints in each animation process to obtain the optimized waypoints for each animation process.
[0080] The planning and control unit 205 is used to perform path planning on the optimized waypoints, obtain the waypoint planning results for the target task, and control the UAV cluster to execute the target task according to the waypoint planning results.
[0081] In one embodiment, the task acquisition unit 201 includes:
[0082] Task marking unit, used to record each animation process in the target task as A i And each animation process A i The drone in the middle is denoted as A. ij Where i = 1, 2...k, j = 1, 2...w, k represents the total number of animation processes, and w represents each animation process A. i The total number of drone sorties;
[0083] The sortie count determination unit is used to determine whether there is an animation process where the number of drone sorties is not w;
[0084] The valid marking unit is used to mark and remove an animation process that is invalid if it is determined that there is an animation process where the number of drone sorties is not w.
[0085] In one embodiment, the set acquisition unit 202 includes:
[0086] The first frame set construction unit is used to obtain each drone A in each animation process. ij The first frame coordinates A ijS And according to each drone A ij The first frame coordinates A ijS Construct the first frame's aircraft coordinate set A iS ;
[0087] The tail frame set construction unit is used to acquire each drone A in each animation process. ij The coordinates of the last frame A ijE And according to each drone A ij The coordinates of the last frame A ijE Construct the tail frame aircraft coordinate set A iE .
[0088] In one embodiment, the mapping calculation unit 203 includes:
[0089] The set input unit is used to input the coordinate set of the last frame of the previous animation process and the coordinate set of the first frame of the next animation process into the KM algorithm, and the KM algorithm outputs a waypoint mapping table T that minimizes the total movement distance of all UAVs. (i,i+1) Where i = 1, 2, ..., k-1.
[0090] In one embodiment, the waypoint optimization unit 204 includes:
[0091] The mapping generation unit is used to obtain the waypoint information of the UAV in the previous animation process in the next animation process based on the waypoint mapping table and with the first animation process as the reference, so as to generate a cumulative mapping relationship from the first animation process to each subsequent animation process.
[0092] The waypoint exchange unit is used to perform overall exchange of UAV waypoints in each animation process according to the cumulative mapping relationship, so as to obtain an animation process containing optimized waypoints.
[0093] In one embodiment, the mapping generation unit includes:
[0094] The update mapping unit is used to perform waypoint mapping based on the updated animation process and generate a new cumulative mapping relationship when other animation processes besides the first animation process are updated.
[0095] In one embodiment, the planning control unit 205 includes:
[0096] The sequence planning unit is used to perform pairwise path planning on two adjacent animation processes according to the execution order of the animation process of the target task, so as to obtain the waypoint planning result.
[0097] Since the embodiments of the apparatus and the embodiments of the method correspond to each other, please refer to the description of the embodiments of the method for the embodiments of the apparatus, which will not be repeated here.
[0098] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed, can perform the steps provided in the above embodiments. The storage medium may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.
[0099] This invention also provides a computer device, which may include a memory and a processor. The memory stores a computer program, and when the processor calls the computer program in the memory, it can implement the steps provided in the above embodiments. Of course, the computer device may also include various network interfaces, power supplies, and other components.
[0100] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant parts can be referred to in the method section. It should be noted that those skilled in the art can make various improvements and modifications to this application without departing from the principles of this application, and these improvements and modifications also fall within the protection scope of the claims of this application.
[0101] It should also be noted that, in this specification, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.
Claims
1. A method for managing unmanned aerial vehicle (UAV) swarm tasks, characterized in that, include: Obtain the target task to be executed by the drone swarm; wherein the target task includes multiple consecutive animation processes, and each animation process contains waypoint information of multiple drones; Based on the waypoint information, obtain the set of aircraft coordinates for the first frame and the set of aircraft coordinates for the last frame in each animation process; Based on the set of aircraft coordinates in the first frame and the set of aircraft coordinates in the last frame, a waypoint mapping table between two adjacent animation processes is calculated using an optimal matching algorithm. Based on the waypoint mapping table, a cumulative mapping relationship is generated, and the waypoints of the UAVs in each animation process are exchanged and optimized as a whole to obtain the optimized waypoints for each animation process. Path planning is performed on the optimized waypoints to obtain the waypoint planning results for the target task, and the UAV cluster is controlled to execute the target task according to the waypoint planning results; The process involves generating a cumulative mapping relationship based on the waypoint mapping table and performing overall exchange and optimization of UAV waypoints in each animation process to obtain optimized waypoints for each animation process, including: Based on the waypoint mapping table, taking the first animation process as a reference, the waypoint information of the UAV in the previous animation process in the next animation process is obtained in two adjacent animation processes, so as to generate a cumulative mapping relationship from the first animation process to each subsequent animation process. Based on the cumulative mapping relationship, the waypoints of the UAVs in each animation process are exchanged as a whole to obtain an animation process that includes optimized waypoints.
2. The UAV swarm task management method according to claim 1, characterized in that, The process of acquiring the target task to be executed by the drone swarm includes: Let A be the animation process in the target task. i And each animation process A i The drone in the middle is denoted as A. ij Where i = 1, 2...k, j = 1, 2...w, k represents the total number of animation processes, and w represents each animation process A. i The total number of drone sorties; Determine if there is an animation process where the number of drone sorties is not w; If an animation process is determined to have a drone sortie count that is not w, then the corresponding animation process is marked as invalid and removed.
3. The UAV swarm task management method according to claim 2, characterized in that, The step of obtaining the set of aircraft coordinates for the first frame and the set of aircraft coordinates for the last frame in each animation process based on the waypoint information includes: Obtain each drone A in each animation process ij The first frame coordinates A ijS And according to each drone A ij The first frame coordinates A ijS Construct the first frame aircraft coordinate set A iS ; Obtain each drone A in each animation process ij Tail frame coordinates A ijE And according to each drone A ij Tail frame coordinates A ijE Construct the tail frame aircraft coordinate set A iE .
4. The UAV swarm task management method according to claim 2, characterized in that, The step of calculating the waypoint mapping table between two adjacent animation processes based on the first frame aircraft coordinate set and the last frame aircraft coordinate set using an optimal matching algorithm includes: The coordinates of the last frame of the preceding animation process and the coordinates of the first frame of the following animation process are input into the KM algorithm, which then outputs a waypoint mapping table T that minimizes the total travel distance of all UAVs. (i,i+1) Where i = 1, 2, ..., k-1.
5. The UAV swarm task management method according to claim 1, characterized in that, Based on the waypoint mapping table, and taking the first animation process as a reference, the waypoint information of the UAV in the previous animation process in the subsequent animation process is obtained in two adjacent animation processes. This generates a cumulative mapping relationship from the first animation process to each subsequent animation process, including: When any animation process other than the first animation process is updated, waypoint mapping is performed based on the updated animation process, and a new cumulative mapping relationship is generated.
6. The UAV swarm task management method according to claim 1, characterized in that, The step of performing path planning on the optimized waypoints to obtain the waypoint planning result for the target task, and controlling the UAV cluster to execute the target task according to the waypoint planning result, includes: According to the execution order of the animation process in the target task, pairwise path planning is performed on two adjacent animation processes to obtain the waypoint planning result.
7. A drone swarm task management device, characterized in that, include: The task acquisition unit is used to acquire the target tasks to be executed by the UAV cluster; wherein, the target tasks include multiple continuous animation processes, and each animation process contains waypoint information of multiple UAVs; The set acquisition unit is used to acquire the set of aircraft coordinates for the first frame and the set of aircraft coordinates for the last frame in each animation process based on the waypoint information. The mapping calculation unit is used to calculate the waypoint mapping table between two adjacent animation processes based on the first frame aircraft coordinate set and the last frame aircraft coordinate set using an optimal matching algorithm. The waypoint optimization unit is used to generate a cumulative mapping relationship based on the waypoint mapping table, and to perform overall exchange optimization of the UAV waypoints in each animation process to obtain the optimized waypoints for each animation process. The planning and control unit is used to perform path planning on the optimized waypoints, obtain the waypoint planning results for the target task, and control the UAV cluster to execute the target task according to the waypoint planning results; The waypoint optimization unit includes: The mapping generation unit is used to obtain the waypoint information of the UAV in the previous animation process in the next animation process based on the waypoint mapping table and the first animation process as a reference, so as to generate a cumulative mapping relationship from the first animation process to each subsequent animation process. The waypoint exchange unit is used to perform overall exchange of UAV waypoints in each animation process according to the cumulative mapping relationship, so as to obtain an animation process containing optimized waypoints.
8. A computer device, characterized in that, The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the unmanned aerial vehicle (UAV) swarm task management method as described in any one of claims 1 to 6.
9. 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 UAV swarm task management method as described in any one of claims 1 to 6.