Track allocation method and system for multi-aircraft formation inspection missions
By using weighted Voronoi diagrams to divide regions and employing a hierarchical resolution strategy, the problems of flight safety risks and uneven load distribution in multi-aircraft inspection missions are solved, achieving efficient and safe multi-aircraft inspection track allocation that adapts to complex scenarios and dynamic operating conditions.
Patent Information
- Application Number
- CN202611325089.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2026-08-28
- Publication Date
- 2026-11-17
AI Technical Summary
Existing methods for allocating tracks in multi-aircraft inspection missions do not perform unified spatiotemporal conflict verification on the tracks of multiple aircraft, which can easily lead to flight safety risks. The regional segmentation does not take into account the performance of the inspection aircraft to achieve balanced load distribution, resulting in insufficient inspection coverage efficiency and uniformity. The conflict resolution methods are limited and cannot flexibly adapt to complex inspection scenarios and dynamic operating conditions.
A weighted Voronoi diagram is used for balanced regional division, generating a full-coverage bow-shaped inspection track. Spatiotemporal conflict detection is performed through pairwise discrete sampling, and conflicts are resolved through a hierarchical resolution strategy that prioritizes time and supplements space. The track and regional boundaries are dynamically adjusted to output a conflict-free multi-aircraft inspection track allocation scheme.
It achieves the elimination of multi-aircraft spatiotemporal flight conflicts while ensuring full regional coverage, significantly improving the safety and execution efficiency of inspection tasks, resulting in more balanced load distribution, flexible and diverse conflict resolution methods, adaptability to different types of conflict scenarios, and the ability to intelligently match conflict resolution strategies and dynamically adapt to operational status.
Smart Images

Figure CN123113918A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of unmanned aerial vehicle (UAV) inspection trajectory planning technology, and in particular to a trajectory allocation method and system for multi-UAV formation inspection tasks. Background Technology
[0002] Existing multi-aircraft inspection missions often use fixed area splitting and single-aircraft independent trajectory planning for track allocation. They do not conduct unified spatiotemporal conflict verification for multi-aircraft tracks, which can easily lead to flight safety risks. Furthermore, the area segmentation does not take into account the performance of the inspection aircraft to achieve balanced load distribution, resulting in insufficient inspection coverage efficiency and uniformity. At the same time, the conflict resolution methods are limited and cannot flexibly adapt to complex inspection scenarios and dynamic operating conditions. Summary of the Invention
[0003] This application provides a method and system for track allocation in multi-aircraft formation inspection missions, aiming to solve the problems of existing multi-aircraft inspection mission track allocation methods that mostly adopt fixed area splitting and single-aircraft independent track planning, without unified spatiotemporal conflict verification of multi-aircraft tracks, which can easily lead to flight safety risks. In addition, the area segmentation does not take into account the performance of the inspection aircraft to achieve balanced load distribution, resulting in insufficient inspection coverage efficiency and uniformity. Furthermore, the conflict resolution methods are limited and cannot flexibly adapt to complex inspection scenarios and dynamic operating conditions.
[0004] In a first aspect, embodiments of this application provide a method for track allocation in a multi-aircraft formation inspection mission, the method comprising: Obtain the polygonal boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Divide the area to be inspected into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. For each inspection aircraft, an initial full-coverage inspection track corresponding to the sub-inspection area is generated. Spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. Perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output a multi-aircraft inspection track allocation scheme with no conflicts after resolution.
[0005] In some embodiments, obtaining polygon boundary information of the area to be inspected and inspection performance parameters of each inspection unit includes: obtaining polygon boundary vertex information of the area to be inspected, and inspection field of view width, endurance and cruising speed parameters of each inspection unit.
[0006] In some embodiments, the area to be inspected is divided into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. This includes: calculating the expected inspection area weight corresponding to each inspection machine based on its inspection coverage capability; initializing multiple seed points in the area to be inspected, matching the number of inspection machines; generating a weighted segmentation graphic based on the various seed points and cropping it with the boundary of the area to be inspected to obtain initial sub-regions corresponding to the various seed points; calculating the actual area of each initial sub-region; adjusting the position of the corresponding seed points based on the deviation between the actual area and the expected area of each sub-region; and repeating the region segmentation calculation and area deviation verification until the area deviation of each sub-region meets a preset threshold to obtain multiple sub-inspection areas.
[0007] In some embodiments, an initial full-coverage inspection track is generated for each inspection aircraft corresponding to a sub-inspection area, including: traversing each sub-inspection area and its assigned inspection aircraft, determining the main scanning direction of the corresponding sub-inspection area, calculating the interval distance between adjacent routes based on the inspection field of view width of the corresponding inspection aircraft, generating a continuous bow-shaped coverage waypoint sequence along the main scanning direction, inserting a smooth turning path at the turning point of the waypoint sequence, and generating the initial full-coverage inspection track corresponding to each inspection aircraft by combining the preset cruise altitude and cruise speed.
[0008] In some embodiments, spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. This includes: pairing all inspection aircraft into multiple inspection aircraft combinations, discretely sampling the two initial full-coverage inspection tracks of each inspection aircraft combination at a preset time interval, calculating the three-dimensional spatial distance between the corresponding points of the two tracks at each sampling time, determining the sampling time where the three-dimensional spatial distance is less than a preset safety interval as a conflict event, recording the corresponding inspection aircraft, conflict time, and conflict segment of all conflict events, and generating a conflict list.
[0009] In some embodiments, track resolution processing is performed on each conflict event in the conflict list, and the track of the corresponding inspection aircraft and the boundary of the sub-inspection area are updated. This includes: traversing each conflict event in the conflict list, assigning resolution priorities to the two inspection aircraft involved in the conflict, performing time dimension resolution first on the inspection aircraft with lower priority, adjusting the passage time and operating speed of the corresponding flight segment, performing spatial dimension resolution if the speed parameter exceeds the allowable range after time dimension resolution, adjusting the flight altitude or horizontal waypoint position of the corresponding flight segment, verifying whether the resolved track meets the inspection constraints and does not introduce new conflict events, updating the track data of the corresponding inspection aircraft, and adjusting the boundary of the corresponding sub-inspection area if the spatial resolution exceeds the boundary of the sub-inspection area.
[0010] In some embodiments, the output of a multi-aircraft inspection track allocation scheme without conflict after resolution includes: after completing the resolution of all conflict events, verifying that there are no spatiotemporal conflicts in the tracks of all inspection aircraft, summarizing the final inspection tracks of each inspection aircraft and the corresponding sub-inspection area boundaries, forming a complete multi-aircraft inspection track allocation scheme and outputting it.
[0011] In some embodiments, the method further includes: recording the processing method and resolution effect data for each conflict resolution, generating a conflict resolution strategy sample library, and when a new conflict event is detected, matching the historical resolution strategy with the highest similarity to the current conflict scenario from the sample library, directly generating candidate resolution schemes and performing feasibility verification.
[0012] In some embodiments, the method further includes: acquiring the remaining endurance data and actual flight deviation data of each inspection aircraft in real time; when the remaining endurance of the inspection aircraft is lower than a preset threshold or the flight deviation exceeds a preset range, re-dividing the range of the corresponding sub-inspection area, allocating the area exceeding the carrying capacity to other inspection aircraft in normal condition, synchronously updating the flight tracks of each inspection aircraft and performing conflict verification.
[0013] Secondly, this application provides a track allocation system for multi-aircraft formation inspection missions, the system comprising: The parameter acquisition unit is used to acquire the polygon boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Based on the inspection coverage capability of each inspection machine, the area to be inspected is divided into multiple sub-inspection areas. The list generation unit is used to generate the initial full-coverage inspection track for each inspection aircraft corresponding to the sub-inspection area, perform spatiotemporal conflict detection on the initial full-coverage inspection tracks of all inspection aircraft, and generate a conflict list containing all conflict events. The scheme output unit is used to perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output a multi-aircraft inspection track allocation scheme without conflict after resolution.
[0014] The method provided in this application has the following beneficial effects: 1. A complete processing chain was constructed, which includes regional balanced segmentation, initial track generation, spatiotemporal conflict detection, and hierarchical conflict resolution. This enables the integrated allocation of multi-aircraft inspection tracks, eliminates spatiotemporal flight conflicts of multiple aircraft while ensuring full regional coverage inspection, and significantly improves the safety and execution efficiency of inspection missions.
[0015] 2. By adopting an iterative weighted regional segmentation method, the area of the sub-inspection area is more matched with the performance of the inspection machine, and the load distribution of multi-machine inspection is more balanced, which can give full play to the operating capabilities of each inspection machine.
[0016] 3. It adopts a time-prioritized and space-supplemented hierarchical conflict resolution mechanism, which offers flexible and diverse resolution methods that can be adapted to different types of conflict scenarios. The resolution process takes into account both inspection constraints and boundary limitations, making the solution more feasible.
[0017] 4. It has the ability to intelligently resolve conflict strategies and dynamically adapt to operating status, enabling it to quickly respond to conflict scenarios and changes in equipment status, significantly improving the robustness and adaptability of the solution.
[0018] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description
[0019] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0020] Figure 1 This is a schematic flowchart illustrating the steps of a multi-aircraft formation inspection mission track allocation method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the overall process of track allocation for a multi-aircraft formation inspection mission provided in an embodiment of this application; Figure 3 This is a schematic diagram of a weighted Voronoi inspection area balancing process provided in an embodiment of this application; Figure 4 This is a schematic diagram of a sub-region full-coverage inspection track generation process provided in an embodiment of this application; Figure 5 This is a schematic diagram of a multi-aircraft flight path spatiotemporal conflict detection process provided in an embodiment of this application; Figure 6 This is a schematic diagram of a flight path conflict classification and resolution process provided in an embodiment of this application; Figure 7 This is a schematic block diagram of the structure of a track allocation system for a multi-aircraft formation inspection mission provided in one embodiment of this application; Figure 8 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application.
[0021] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Detailed Implementation
[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.
[0023] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content and operations / steps, nor does it necessarily have to be performed in the order described. For example, some operations / steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.
[0024] It should be understood that, in order to clearly describe 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 identical 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, and the terms "first" and "second" are not necessarily different.
[0025] It should 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 scope of the application. 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.
[0026] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.
[0027] In multi-aircraft formation inspection scenarios, trajectory planning and allocation are core elements for ensuring inspection coverage efficiency, flight safety, and mission balance. Existing multi-aircraft inspection trajectory allocation methods often employ fixed-area segmentation and independent planning for individual aircraft, which have several technical shortcomings: First, they lack unified spatiotemporal conflict verification for multi-aircraft trajectories, making scenarios with overlapping flight segments and altitudes prone to flight safety risks. Second, area segmentation does not consider the performance of the inspection aircraft to achieve balanced load distribution, resulting in some inspection aircraft being overloaded while others are unloaded, leading to insufficient inspection coverage efficiency and uniformity. Third, conflict resolution methods are simplistic, relying solely on adjustments based on altitude or time, which cannot flexibly adapt to complex inspection scenarios and dynamic operating conditions, failing to meet the safety and efficiency requirements of multi-aircraft collaborative inspections.
[0028] To address at least one of the aforementioned technical problems, embodiments of this application provide a method for track allocation in multi-aircraft formation inspection missions. This method first achieves balanced regional division based on the performance of each inspection aircraft using a weighted Voronoi diagram, matching load and capacity. Second, it generates a full-coverage, bow-shaped inspection track, and performs full-time and spatiotemporal conflict detection through pairwise discrete sampling to identify all conflict events. Finally, it handles conflicts using a time-priority, spatially supplementary hierarchical resolution strategy, dynamically adjusting the track and regional boundaries, ultimately outputting a conflict-free multi-aircraft track allocation scheme. This method balances regional load balancing, flight safety, and coverage efficiency, and can automatically adapt to inspection scenarios involving multiple aircraft types and multiple missions, significantly improving the safety and operational efficiency of multi-aircraft formation inspections.
[0029] Please refer to Figure 1 The multi-aircraft formation inspection mission trajectory allocation method provided in this application is applied to computer equipment, which performs the entire process of inspection area division, trajectory generation, conflict detection and resolution scheduling. The computer equipment can be deployed on a single server or server cluster, or on ground command stations, handheld control terminals, laptops, wearable devices, or airborne edge computing devices to achieve functions such as area division, trajectory planning, conflict detection, and scheduling optimization. It should also be noted that all inspection area data, equipment performance parameters, trajectory planning data, and other information involved in the method provided in this application are collected and used under the authorization of relevant users and in accordance with relevant data security and management regulations, and will not infringe on user privacy or flight safety.
[0030] Please refer to Figure 1 This application provides a method for track allocation in multi-aircraft formation inspection missions, applied to computer equipment. The computer equipment can be deployed on a single server or server cluster. It can also be deployed on handheld terminals, laptops, wearable devices, or robots, etc. It should be noted that all information involved in the method provided in this application is extracted with the authorization of the relevant user and in accordance with relevant regulations, and will not infringe on user privacy.
[0031] The provided method for track allocation in multi-aircraft formation inspection missions includes steps S101 to S103. Details are as follows: Step S101. Obtain the polygonal boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Divide the area to be inspected into multiple sub-inspection areas according to the inspection coverage capability of each inspection machine.
[0032] Specifically, the core objective of this step is to evenly divide the inspection area based on the performance differences of each inspection aircraft, ensuring that the workload of each inspection aircraft matches its coverage capacity. This avoids efficiency losses caused by uneven workloads and provides independent sub-areas for subsequent single-aircraft trajectory planning. The specific implementation process is as follows: In the basic parameter acquisition phase, the coordinates of the polygonal boundary vertices of the area to be inspected are obtained using standard latitude and longitude or a planar projected coordinate system. The boundary vertices are arranged in sequence to form a closed inspection area. At the same time, the inspection performance parameters of each inspection aircraft are collected, including the inspection field of view (effective scanning width), cruising speed, maximum range, and task priority of a single inspection aircraft, reflecting the coverage and operational capabilities of each inspection aircraft.
[0033] In the area partitioning phase, a weighted Voronoi diagram algorithm is used to achieve balanced area partitioning. First, the expected inspection area weight is calculated based on the coverage capability of each inspection unit. Inspection units with stronger coverage capabilities and longer battery life have larger weights and are allocated larger areas. Seed points, consistent with the number of inspection units, are initialized within the area to be inspected. The initial seed points can be evenly distributed across the area or arranged according to the density of key areas.
[0034] Based on the locations and corresponding weights of various sub-points, a weighted Voronoi diagram is generated. Each seed point corresponds to a sub-region, and the weighted distance from any point within the region to its own seed point is less than the weighted distance to other seed points. The generated Voronoi partitions are then cropped from the polygonal boundaries of the region to be inspected, removing the portions outside the boundaries to obtain the initial sub-inspection regions corresponding to various sub-points.
[0035] Calculate the actual area of each initial sub-region and compare it with the corresponding expected area to calculate the area deviation rate. If the deviation exceeds a preset threshold, adjust the position of the corresponding seed point according to the deviation direction: if the area is too large, move the seed point towards the center of the region; if the area is too small, move it towards the edge. Repeat the Voronoi generation, trimming, area calculation, and seed point adjustment iterations until the area deviation rate of all sub-regions is lower than the preset threshold, ultimately obtaining multiple load-balanced sub-inspection regions, each corresponding to one inspection machine.
[0036] By using weighted balancing partitioning, the workload of each inspection aircraft can be matched with its performance, avoiding the problem of underloaded high-performance aircraft and overloaded low-performance aircraft, thereby improving the overall inspection efficiency.
[0037] Step S102. Generate an initial full-coverage inspection track for each inspection aircraft corresponding to the sub-inspection area, perform spatiotemporal conflict detection on the initial full-coverage inspection tracks of all inspection aircraft, and generate a conflict list containing all conflict events.
[0038] Specifically, the core objective of this step is to generate a comprehensive, unobstructed inspection track for each sub-region, while simultaneously performing three-dimensional spatiotemporal conflict detection on all tracks to identify all conflict events posing a security risk, thus providing targets for subsequent resolution. The specific implementation process is as follows: In the initial full-coverage track generation phase, each sub-inspection area and its assigned inspection aircraft are traversed to generate the corresponding full-coverage track. First, the main scanning direction is determined, prioritizing the direction parallel to the longest side of the smallest bounding rectangle of the sub-area as the main scanning direction to reduce the number of turns and improve inspection efficiency.
[0039] Based on the inspection field of view of the corresponding inspection aircraft, the interval distance between adjacent routes is calculated. The interval distance is less than or equal to 90% of the field of view width, and a certain amount of overlap is retained to avoid missed detections at the boundary. A continuous bow-shaped waypoint sequence is generated along the main scanning direction, and the entire sub-region is covered by round-trip scanning. Smooth turning paths are inserted at the turning points of the waypoint sequence, and the turning radius conforms to the maneuverability constraints of the inspection aircraft to avoid sharp turns.
[0040] By combining preset cruising altitude and speed, each waypoint is assigned a timestamp and altitude value, generating a three-dimensional initial full-coverage inspection track that includes position, time, altitude, and speed information. The track of each inspection aircraft completely covers the corresponding sub-inspection area, with no blind spots or omissions.
[0041] In the spatiotemporal conflict detection phase, a pairwise discrete sampling method is used to detect spatiotemporal conflicts in all tracks. All inspection aircraft are paired up to form all inspection aircraft combinations. For the two tracks of each group, discrete sampling is performed at preset time intervals to obtain the position points of the two inspection aircraft at each sampling time.
[0042] Calculate the three-dimensional spatial distance between two locations at each sampling time, including horizontal distance and altitude difference. When the three-dimensional spatial distance is less than a preset safety interval threshold, that moment is determined to be a conflict event. Record information for all conflict events, including the numbers of the two inspection aircraft involved, the time of the conflict, the location of the conflict segment, and the type of conflict (horizontal conflict, altitude conflict, mixed conflict). All conflict events are summarized to form a conflict list.
[0043] Through all-weather and all-space conflict detection, all potential flight conflict risks can be identified, providing precise targets for subsequent resolution and ensuring the safety of multi-aircraft flights.
[0044] Step S103. Perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output the multi-aircraft inspection track allocation scheme without conflict after resolution.
[0045] Specifically, the core objective of this step is to handle all conflict events through a tiered resolution strategy, eliminating flight conflicts while minimizing impact on inspection coverage, and dynamically adjusting flight paths and area boundaries to ultimately output a safe, conflict-free, and fully covered multi-aircraft flight path scheme. The specific implementation process is as follows: In the conflict resolution phase, each conflict event in the conflict list is traversed, and a resolution priority is assigned to the two inspection aircraft involved in the conflict. The priority is determined based on mission importance, remaining range, and the importance of the flight segment: inspection aircraft with higher mission priority, less remaining range, and those in critical inspection segments have higher priority and are given priority in preserving their flight paths.
[0046] For lower-priority inspection aircraft, prioritize time-based resolution: adjust the passage times of the corresponding conflict segments by adjusting cruise speed or circling waiting time at turns to stagger the passage times of the two aircraft. After adjustment, verify that the speed and time are within the allowable range and that no new conflicts arise after resolution.
[0047] If the speed exceeds the allowable range after time-dimensional resolution, or if conflicts cannot be avoided, then spatial-dimensional resolution is performed: adjust the flight altitude of the corresponding flight segment to avoid collisions within the allowable altitude stratification range; or horizontally adjust the waypoint positions and fine-tune the route positions. After adjustment, verify whether the inspection coverage requirements are still met and whether any areas are missed.
[0048] If spatial dissolution causes the flight path to exceed the boundary of the sub-inspection area, the boundaries of the two sub-inspection areas will be adjusted accordingly to compensate for each other and ensure full coverage of the overall area.
[0049] After each resolution is completed, the conflict between the flight segment and other tracks is re-verified to ensure that the resolution does not introduce new conflicts. The track data of the corresponding inspection aircraft and the sub-area boundaries are updated.
[0050] In the solution output phase, after resolving all conflict events, a global conflict check is performed to confirm that there are no spatiotemporal conflicts in the flight paths of all inspection aircraft. The final inspection flight paths of each inspection aircraft, the corresponding sub-inspection area boundaries, and mission parameters are then summarized to form a complete multi-aircraft inspection flight path allocation solution. The solution includes the 3D flight path, time series, and coverage area of each aircraft and can be directly imported into the flight control system for execution.
[0051] By tiered resolution and dynamic boundary adjustment, all flight conflicts can be eliminated while ensuring coverage, balancing safety and efficiency.
[0052] In some embodiments, obtaining polygon boundary information of the area to be inspected and inspection performance parameters of each inspection unit includes: obtaining polygon boundary vertex information of the area to be inspected, and inspection field of view width, endurance and cruising speed parameters of each inspection unit.
[0053] By acquiring the vertex information of the polygonal boundary of the area to be inspected, with the vertices arranged in a clockwise or counterclockwise order using a planar projected coordinate system, a closed polygonal region is formed. This supports inspection areas of arbitrarily complex shapes, including complex boundaries containing islands and recesses. Simultaneously, the elevation information of no-fly zones and obstacles within the region is acquired as constraints for subsequent trajectory planning.
[0054] Collect inspection performance parameters for each inspection aircraft, including: inspection field of view width, i.e., the effective scanning coverage width of the airborne sensors, which is related to flight altitude; cruise speed, i.e. the flight speed for normal inspection operations; maximum range, which determines the maximum inspectable range; maneuverability parameters, including minimum turning radius and maximum climb and descent rate; and identification information such as mission priority and equipment number.
[0055] All parameters are standardized and validated, outliers are removed, and missing default values are added to provide an accurate parameter basis for subsequent area division and track generation.
[0056] In some embodiments, the area to be inspected is divided into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. This includes: calculating the expected inspection area weight corresponding to each inspection machine based on its inspection coverage capability; initializing multiple seed points in the area to be inspected, matching the number of inspection machines; generating a weighted segmentation graphic based on the various seed points and cropping it with the boundary of the area to be inspected to obtain initial sub-regions corresponding to the various seed points; calculating the actual area of each initial sub-region; adjusting the position of the corresponding seed points based on the deviation between the actual area and the expected area of each sub-region; and repeating the region segmentation calculation and area deviation verification until the area deviation of each sub-region meets a preset threshold to obtain multiple sub-inspection areas.
[0057] The expected inspection area weight for each inspection aircraft is calculated based on its inspection coverage capability. This weight is positively correlated with the field of view, cruising speed, and range. A comprehensive coverage capability coefficient is then calculated, and the weight is proportional to the coverage capability coefficient. The stronger the coverage capability, the larger the allocated area, ensuring a balanced load.
[0058] Initialize N seed points within the area to be inspected, where N equals the number of inspection machines. The initial seed points can be evenly distributed using a grid, or adaptively arranged according to the density of key areas, with denser seed points in key areas.
[0059] Based on the location and corresponding weight of various sub-points, a weighted Voronoi diagram partition is generated: for any point in the region, its seed point is the seed point with the smallest weighted distance, and the weighted distance is equal to the Euclidean distance divided by the weight of the corresponding seed point.
[0060] The generated Voronoi partitions are trimmed from the outer boundary of the area to be inspected, and the internal no-fly zones are also trimmed to obtain the initial sub-inspection areas corresponding to various sub-points.
[0061] Calculate the actual area of each sub-region and compare it with the corresponding expected area (total area × weight percentage) to calculate the area deviation rate. If the deviation rate exceeds a preset threshold (e.g., 5%), adjust the seed point position: if the area is too large, move the seed point towards the region's centroid; if the area is too small, move it away from the centroid. Repeat the iterative process of Voronoi generation, trimming, area calculation, and seed point adjustment until the area deviation rate of all sub-regions is below the threshold, ultimately obtaining N load-balanced sub-inspection regions.
[0062] By using weighted Voronoi iterative partitioning, balanced partitioning that matches the capabilities of each machine can be achieved, avoiding the uneven load problem of manual partitioning and improving overall inspection efficiency.
[0063] In some embodiments, an initial full-coverage inspection track is generated for each inspection aircraft corresponding to a sub-inspection area, including: traversing each sub-inspection area and its assigned inspection aircraft, determining the main scanning direction of the corresponding sub-inspection area, calculating the interval distance between adjacent routes based on the inspection field of view width of the corresponding inspection aircraft, generating a continuous bow-shaped coverage waypoint sequence along the main scanning direction, inserting a smooth turning path at the turning point of the waypoint sequence, and generating the initial full-coverage inspection track corresponding to each inspection aircraft by combining the preset cruise altitude and cruise speed.
[0064] By traversing each sub-inspection area and its assigned inspection aircraft, a corresponding full-coverage flight path is generated. First, the main scanning direction is determined: the minimum bounding rectangle of the sub-area is calculated, and the direction parallel to the long side of the rectangle is selected as the main scanning direction to maximize the length of a single flight path, reduce the number of turns, and improve operational efficiency.
[0065] Based on the field of view of the inspection machine and the preset overlap coefficient (default 10%), the interval distance between adjacent routes is calculated. The interval = field of view × (1 - overlap coefficient) to ensure that adjacent routes have sufficient overlap and avoid missed inspections at the boundary.
[0066] Along the main scanning direction, starting from one boundary of the sub-region, equally spaced parallel flight paths are generated, and the round-trip scans cover the entire sub-region, forming a bow-shaped waypoint sequence. At the two ends of the flight path, smooth turning segments are generated based on the minimum turning radius of the inspection aircraft, connecting adjacent flight paths to ensure continuous flight path continuity.
[0067] Assign preset cruising altitude and speed to all waypoints, calculate the timestamp of each waypoint sequentially, and generate a three-dimensional initial full-coverage inspection track containing position, altitude, time, and speed. The track completely covers the corresponding sub-inspection area, with no blind spots or exceeding boundaries.
[0068] By generating a bow-shaped full-coverage flight path, it is possible to ensure that no inspection is missed, while the path is smooth and conforms to flight constraints, making it feasible for engineering.
[0069] In some embodiments, spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. This includes: pairing all inspection aircraft into multiple inspection aircraft combinations, discretely sampling the two initial full-coverage inspection tracks of each inspection aircraft combination at a preset time interval, calculating the three-dimensional spatial distance between the corresponding points of the two tracks at each sampling time, determining the sampling time where the three-dimensional spatial distance is less than a preset safety interval as a conflict event, recording the corresponding inspection aircraft, conflict time, and conflict segment of all conflict events, and generating a conflict list.
[0070] Conflict detection is performed by pairing up all the aircraft in pairs. The N inspection aircraft are paired up to generate a total of N×(N-1) / 2 inspection aircraft pairs, ensuring that all aircraft pairs are inspected.
[0071] For each group of two flight paths, discrete sampling is performed according to a preset time sampling interval (e.g., 1 second) to obtain the three-dimensional coordinates (longitude, latitude, and altitude) of the two aircraft at each sampling time.
[0072] Calculate the three-dimensional spatial distance between two points at each sampling time, considering both horizontal and vertical intervals. Set a safety interval threshold, including horizontal and vertical safety distances. When the three-dimensional spatial distance is less than the safety interval threshold, that moment is determined to be a collision event.
[0073] For each conflict event, record the conflict type: insufficient horizontal distance alone constitutes a horizontal conflict, insufficient height alone constitutes a height conflict, and insufficient height for either is a mixed conflict. Also record the involved inspection machine number, the start and end times of the conflict, the conflict location, and the conflict severity.
[0074] All conflict events are compiled into a conflict list, sorted by conflict severity. Through pairwise discrete sampling detection, all spatiotemporal conflicts can be comprehensively identified without omission, providing precise targets for subsequent resolution.
[0075] In some embodiments, track resolution processing is performed on each conflict event in the conflict list, and the track of the corresponding inspection aircraft and the boundary of the sub-inspection area are updated. This includes: traversing each conflict event in the conflict list, assigning resolution priorities to the two inspection aircraft involved in the conflict, performing time dimension resolution first on the inspection aircraft with lower priority, adjusting the passage time and operating speed of the corresponding flight segment, performing spatial dimension resolution if the speed parameter exceeds the allowable range after time dimension resolution, adjusting the flight altitude or horizontal waypoint position of the corresponding flight segment, verifying whether the resolved track meets the inspection constraints and does not introduce new conflict events, updating the track data of the corresponding inspection aircraft, and adjusting the boundary of the corresponding sub-inspection area if the spatial resolution exceeds the boundary of the sub-inspection area.
[0076] The conflict list is traversed, and conflicts are handled in descending order of severity. For each conflict involving two inspection aircraft, the resolution priority is determined based on a comprehensive assessment of mission priority, remaining range, flight segment importance, and adjustment cost. Inspection aircraft with higher mission priority, less remaining range, located in core inspection segments, and higher adjustment costs have higher priority and are given priority in maintaining their flight paths while lower-priority aircraft are adjusted.
[0077] Prioritize time-based resolution: In conflict segments, adjust the speed of low-priority aircraft or add circling waiting at the upcoming turn to stagger the timing of the two aircraft passing the conflict point. After adjustment, verify that the speed is within the allowable range, the time offset meets the mission requirements, and that the resolution does not create new conflicts between this segment and other segments. Time-based resolution is prioritized because it has the least impact on coverage.
[0078] If the time dimension cannot be resolved (e.g., speed exceeding limits, excessive time offset affecting the mission), then spatial dimension resolution is performed. Altitude is adjusted first, within the allowed altitude layer range, adjusting the flight altitude of low-priority aircraft to stagger altitude layers; if altitude cannot be adjusted, then the horizontal flight path position is finely adjusted, shifting the flight segment inward or outward.
[0079] If spatial adjustments cause the flight path to exceed the boundary of the sub-inspection area, the boundaries of the two sub-areas will be adjusted accordingly to compensate for each other, ensuring full coverage of the entire area and no missed inspections.
[0080] After each conflict resolution is completed, the conflict status of the area is re-verified to confirm that no new conflicts have occurred, and the flight path data of the corresponding aircraft and the boundary of the sub-area are updated.
[0081] By employing a tiered conflict resolution strategy, conflicts can be eliminated at minimal cost, maximizing inspection efficiency and coverage.
[0082] In some embodiments, the output of a multi-aircraft inspection track allocation scheme without conflict after resolution includes: after completing the resolution of all conflict events, verifying that there are no spatiotemporal conflicts in the tracks of all inspection aircraft, summarizing the final inspection tracks of each inspection aircraft and the corresponding sub-inspection area boundaries, forming a complete multi-aircraft inspection track allocation scheme and outputting it.
[0083] After all conflict events are resolved, a global secondary conflict check is performed, traversing all inspection pairs and re-performing the sampling conflict detection to confirm that no conflict events have been missed, thus ensuring the security of the solution.
[0084] Summarize the final data from each inspection aircraft, including the three-dimensional track point sequence (including timestamps, latitude and longitude, altitude, and speed), the polygonal boundaries of the corresponding sub-inspection areas, the coverage area, the estimated inspection time, and the mission completion assessment.
[0085] All data is organized into a standardized multi-aircraft inspection track allocation scheme, and the output is in a format that can be directly imported into the flight control system. At the same time, a visual track map and zoning map are output for the command personnel to view.
[0086] The solution also includes conflict resolution records, including the number of conflicts, resolution methods, and adjustments, for subsequent effectiveness evaluation. The complete solution output allows for direct integration with the execution system and provides traceability.
[0087] In some embodiments, the method further includes: recording the processing method and resolution effect data for each conflict resolution, generating a conflict resolution strategy sample library, and when a new conflict event is detected, matching the historical resolution strategy with the highest similarity to the current conflict scenario from the sample library, directly generating candidate resolution schemes and performing feasibility verification.
[0088] A conflict resolution sample library is constructed to record the scenario characteristics, resolution strategies, resolution effects, and cost scores for each conflict event. Scenario characteristics include conflict type, conflict segment characteristics, priority and performance parameters of the two aircraft; resolution strategies include time adjustment, altitude adjustment, and horizontal offset; effect indicators include conflict resolution degree, coverage impact rate, time cost, and efficiency loss.
[0089] When a new conflict event is detected, the scene feature vector of the conflict is extracted and matched with the historical samples in the sample library to find the top 3 historical resolution solutions with the highest similarity.
[0090] The feasibility of candidate solutions is verified, and the cost and effect of each solution are calculated. The solution with the lowest cost and best effect is selected as the candidate resolution solution. If there are no matching samples in the sample library, the default hierarchical resolution process is executed.
[0091] After each resolution process, the conflict scenario, resolution strategy, and effectiveness evaluation are stored in the sample database to continuously enrich the database. As the sample size increases, the accuracy of intelligent matching gradually improves, and the resolution efficiency continues to increase.
[0092] Intelligent matching through a sample library can improve the efficiency of conflict resolution, avoid calculating from scratch each time, and accumulate historical best strategies to continuously optimize the resolution effect.
[0093] In some embodiments, the method further includes: acquiring the remaining endurance data and actual flight deviation data of each inspection aircraft in real time; when the remaining endurance of the inspection aircraft is lower than a preset threshold or the flight deviation exceeds a preset range, re-dividing the range of the corresponding sub-inspection area, allocating the area exceeding the carrying capacity to other inspection aircraft in normal condition, synchronously updating the flight tracks of each inspection aircraft and performing conflict verification.
[0094] During the inspection process, the remaining range, actual flight position deviation, and environmental wind resistance data of each inspection aircraft are acquired in real time. When the remaining range of an inspection aircraft falls below a preset threshold or the flight deviation exceeds a preset range, causing it to be unable to complete the inspection task in its originally assigned area, a dynamic area reallocation is triggered.
[0095] Assess the remaining coverage capacity of the inspection machine and calculate the area that can be reduced. Allocate any edge areas exceeding its capacity to neighboring inspection machines that are in good working order and have remaining capacity.
[0096] The boundaries of the corresponding sub-inspection areas are readjusted, the affected inspection tracks are adjusted simultaneously, and conflict detection and resolution are re-executed on the adjusted segments to ensure no conflicts occur.
[0097] The flight paths and task assignments of each aircraft are updated and simultaneously distributed to all inspection aircraft. Through dynamic reallocation, it is possible to cope with endurance deviations and environmental changes during flight, ensuring the overall completion rate of inspection tasks and improving robustness.
[0098] In some embodiments, please refer to Figure 2 The overall process from start to finish is as follows: input the region boundary and aircraft group parameters, perform region slicing, generate initial tracks, perform multi-aircraft spatiotemporal conflict detection, determine whether there is a conflict, if there is no conflict, directly output the solution, if there is a conflict, generate a conflict list, perform conflict resolution, update tracks and regions, and then repeat the detection until there is no conflict and output the final solution, forming a complete closed loop.
[0099] Please refer to Figure 3The weighted Voronoi region partitioning process is as follows: Input the region boundary vertices, the number of inspection machines, and the coverage weight of each machine; calculate the area weight; initialize N seed points; generate a weighted Voronoi map and clip it to the inspection region; calculate the actual area of each sub-region; determine whether the deviation is less than the threshold; if not, adjust the seed points and repeat the iteration; if it is, output a set of N sub-region polygons.
[0100] Please refer to Figure 4 The full-coverage trajectory generation process is as follows: Input N sub-region polygon sets, traverse each region and its assigned inspection aircraft, determine the main scanning direction, calculate the route spacing based on the inspection field of view width, generate a bow-shaped coverage waypoint sequence along the main direction, insert smooth turning paths at turning points, and generate a four-dimensional spatiotemporal trajectory by combining preset cruise altitude and speed. After all regions are processed, output the initial spatiotemporal trajectory set of all inspection aircraft.
[0101] Please refer to Figure 5 The spatiotemporal conflict detection process is as follows: Input the initial spatiotemporal tracks of all inspection aircraft, pair them up to form inspection aircraft combinations, sample each set of tracks at equal time intervals, calculate the three-dimensional spatial distance at each sampling time, determine whether the distance is less than the safety interval threshold, if so, record the relevant information of the conflict event, and output the conflict list after all pairings are detected.
[0102] Please refer to Figure 6 The conflict resolution process is as follows: Input a conflict list, iterate through each conflict event in the list, assign resolution priorities to both conflicting parties, prioritize adjusting the time offset for lower priority aircraft, and determine if the adjusted parameters are within the allowable range. If so, perform time resolution; otherwise, adjust the flight altitude or horizontal waypoint position, and determine if the adjustment exceeds the sub-region boundary. If so, adjust the corresponding sub-region boundary. Verify if resolution introduces new conflicts; if so, re-execute resolution; otherwise, update the corresponding track and region boundary. Determine if the number of resolution attempts exceeds the preset limit; if so, proceed to manual intervention; otherwise, complete the current resolution. After all conflicts are resolved, return to the main process and output the final solution.
[0103] The complete execution process is as follows: The first step is to input the boundary of the area to be inspected and the performance parameters of each inspection machine, and then obtain multiple sub-inspection areas with load balancing through weighted Voronoi iteration.
[0104] The second step is to generate a bow-shaped, fully covered inspection track for each sub-region, which includes spatiotemporal four-dimensional information.
[0105] The third step involves pairing up individuals to perform full-time and space-time conflict detection and generating a list of conflict events.
[0106] The fourth step is to resolve conflicts according to priority levels, prioritizing time adjustments and supplementing them with spatial adjustments, and dynamically adjusting regional boundaries to ensure coverage.
[0107] The fifth step is to output the final multi-aircraft inspection track allocation scheme after global verification confirms no conflicts.
[0108] In some embodiments, the method further includes a real-time optimization process for dynamic trajectories based on deep reinforcement learning, which solves the technical problem that static pre-planned trajectories cannot adapt to dynamic scenarios such as dynamic weather and sudden no-fly zones, resulting in low inspection efficiency. It is suitable for real-time inspection and scheduling scenarios in complex environments. By constructing a deep reinforcement learning scheduling agent, the current position status of each aircraft, remaining range, weather and wind field distribution, sudden no-fly zones, and overall task completion rate are used as the state space input, the trajectory adjustment amount of each aircraft and the area redistribution strategy are used as the action space output, and the overall inspection completion rate, conflict risk value, and total task time are used as the reward function.
[0109] During the pre-training phase, the agent is trained on a large scale in a simulation environment, covering various typical scenarios such as wind field disturbances, no-fly zone detours, and mission takeover by a malfunctioning aircraft, learning optimal adjustment strategies for different scenarios. After training, it is deployed to the ground command system and runs in inference mode.
[0110] During real-time inspections, the intelligent agent receives environmental perception data and fleet status data in real time, dynamically optimizing the flight paths and area allocation of each aircraft. This maximizes inspection efficiency and minimizes time loss while ensuring no conflicts occur. In case of emergencies, it quickly outputs adjustment plans, with a response speed far faster than traditional global replanning methods.
[0111] Simultaneously, the agent is continuously trained incrementally using actual execution data to continuously optimize scheduling performance. Through reinforcement learning and dynamic optimization, it can respond to dynamic scene changes in real time, significantly improving inspection efficiency and robustness in complex environments.
[0112] In some embodiments, the method further includes a digital twin-based inspection trajectory simulation and rehearsal process to address the technical problems of inability to verify the execution effect of trajectory planning in advance and inability to predict potential risks. It is applicable to rehearsals and risk assessment scenarios for important inspection tasks. By constructing a digital twin model of the inspection task, including a terrain model of the inspection area, a meteorological environment dynamics model, a flight dynamics model of the inspection aircraft, and a coverage effectiveness model of airborne sensors, the method inputs a pre-planned multi-aircraft trajectory scheme and simulates the entire inspection execution process in the twin environment.
[0113] During the simulation, potential risks such as flight path conflicts, coverage blind spots, insufficient endurance, and weather impacts were addressed. The feasibility, coverage, completion time, and safety redundancy of the proposed solutions were quantitatively evaluated. For identified risks, flight path plans were optimized in advance to mitigate potential problems.
[0114] Before formal implementation, the feasibility of the plan is verified through a twin simulation, process parameters are optimized, and the risks of actual implementation are reduced. During implementation, real-time flight data is synchronously injected into the twin model to dynamically predict subsequent risk trends and provide adjustment suggestions in advance.
[0115] By using digital twin simulations, we can verify the effectiveness of flight path plans in advance, predict risks, optimize plans, improve mission success rates, and reduce safety risks in actual execution.
[0116] In some embodiments, the method further includes a multi-task priority-driven track resource scheduling process to address the technical problems of uneven resource allocation and insufficient support for high-priority tasks when multiple tasks are running in parallel. This approach is suitable for complex inspection scenarios with overlapping tasks. By constructing a multi-task priority system, inspection tasks are divided into Level 1, Level 2, and Level 3 tasks according to their importance, with different levels corresponding to different resource priorities and support levels. Level 1 tasks prioritize the allocation of optimal areas and prioritize right-of-way in the event of track conflicts.
[0117] When multiple tasks are executed simultaneously, inspection aircraft and airspace resources are allocated according to task priority. Higher priority tasks are assigned inspection aircraft with better performance and optimal flight path altitudes. In the event of a conflict, priority is given to ensuring that the flight paths of higher priority tasks remain unchanged.
[0118] A resource optimization algorithm is employed to allocate track resources, altitude layer resources, and time-of-day resources with the goal of maximizing overall mission benefits. Low-priority missions can be executed during off-peak hours or utilize the airspace gaps between high-priority missions.
[0119] Priority-driven resource scheduling can prioritize important tasks when multiple tasks are running in parallel, maximizing the overall task value and avoiding insufficient support for important tasks due to average resource allocation.
[0120] In some embodiments, the method further includes a cross-regional collaborative scheduling optimization process using federated learning, addressing technical issues such as data silos in multi-regional inspections, the inability to share and optimize scheduling strategies, and data security risks. It is applicable to cross-regional multi-fleet collaborative inspection scenarios. By constructing a flight path scheduling model under a federated learning framework, each inspection region acts as a local node, storing its own local inspection historical data. The original data does not leave the local node, ensuring data security and privacy. A federated coordination node is set up to be responsible for the aggregation, distribution, and iterative management of the global model, without ever accessing the original business data.
[0121] Each local node trains its local trajectory scheduling model based on its historical inspection data. After training, it only encrypts and uploads the model parameter gradients to the coordinating node. The coordinating node performs weighted aggregation of the gradients from all nodes, with the weights being positively correlated with the amount of data at each node, to generate an updated global baseline model, which is then encrypted and distributed to each local node.
[0122] After receiving the global model, each local node fine-tunes it based on local scenarios and device characteristics to obtain a locally optimized scheduling model. Through multiple rounds of federated iterations, the global model integrates scheduling experience from all regions, resulting in superior generalization capabilities. Meanwhile, all original data remains locally, complying with data security and compliance requirements.
[0123] Through federated learning and collaborative optimization, scheduling experience from multiple regions can be aggregated to continuously improve the level of flight path scheduling while protecting data privacy, thereby achieving cross-regional capability sharing and joint improvement.
[0124] Please see Figure 7 As shown, Figure 7 This is a schematic diagram of the structure of a multi-aircraft formation inspection task track allocation system 200 provided in this application embodiment. The multi-aircraft formation inspection task track allocation system 200 is used to execute the steps of the track allocation method for multi-aircraft formation inspection tasks shown in the above embodiments. The multi-aircraft formation inspection task track allocation system 200 can be a single server or a server cluster, or it can be a terminal, such as a handheld terminal, laptop computer, wearable device, or robot.
[0125] like Figure 7 As shown, the track allocation system 200 for multi-aircraft formation patrol missions includes: The parameter acquisition unit 201 is used to acquire the polygon boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Based on the inspection coverage capability of each inspection machine, the area to be inspected is divided into multiple sub-inspection areas. The list generation unit 202 is used to generate an initial full-coverage inspection track for each inspection aircraft corresponding to a sub-inspection area, perform spatiotemporal conflict detection on the initial full-coverage inspection tracks of all inspection aircraft, and generate a conflict list containing all conflict events. The scheme output unit 203 is used to perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output a multi-aircraft inspection track allocation scheme without conflict after resolution.
[0126] In some embodiments, obtaining polygon boundary information of the area to be inspected and inspection performance parameters of each inspection unit includes: obtaining polygon boundary vertex information of the area to be inspected, and inspection field of view width, endurance and cruising speed parameters of each inspection unit.
[0127] In some embodiments, the area to be inspected is divided into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. This includes: calculating the expected inspection area weight corresponding to each inspection machine based on its inspection coverage capability; initializing multiple seed points in the area to be inspected, matching the number of inspection machines; generating a weighted segmentation graphic based on the various seed points and cropping it with the boundary of the area to be inspected to obtain initial sub-regions corresponding to the various seed points; calculating the actual area of each initial sub-region; adjusting the position of the corresponding seed points based on the deviation between the actual area and the expected area of each sub-region; and repeating the region segmentation calculation and area deviation verification until the area deviation of each sub-region meets a preset threshold to obtain multiple sub-inspection areas.
[0128] In some embodiments, an initial full-coverage inspection track is generated for each inspection aircraft corresponding to a sub-inspection area, including: traversing each sub-inspection area and its assigned inspection aircraft, determining the main scanning direction of the corresponding sub-inspection area, calculating the interval distance between adjacent routes based on the inspection field of view width of the corresponding inspection aircraft, generating a continuous bow-shaped coverage waypoint sequence along the main scanning direction, inserting a smooth turning path at the turning point of the waypoint sequence, and generating the initial full-coverage inspection track corresponding to each inspection aircraft by combining the preset cruise altitude and cruise speed.
[0129] In some embodiments, spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. This includes: pairing all inspection aircraft into multiple inspection aircraft combinations, discretely sampling the two initial full-coverage inspection tracks of each inspection aircraft combination at a preset time interval, calculating the three-dimensional spatial distance between the corresponding points of the two tracks at each sampling time, determining the sampling time where the three-dimensional spatial distance is less than a preset safety interval as a conflict event, recording the corresponding inspection aircraft, conflict time, and conflict segment of all conflict events, and generating a conflict list.
[0130] In some embodiments, track resolution processing is performed on each conflict event in the conflict list, and the track of the corresponding inspection aircraft and the boundary of the sub-inspection area are updated. This includes: traversing each conflict event in the conflict list, assigning resolution priorities to the two inspection aircraft involved in the conflict, performing time dimension resolution first on the inspection aircraft with lower priority, adjusting the passage time and operating speed of the corresponding flight segment, performing spatial dimension resolution if the speed parameter exceeds the allowable range after time dimension resolution, adjusting the flight altitude or horizontal waypoint position of the corresponding flight segment, verifying whether the resolved track meets the inspection constraints and does not introduce new conflict events, updating the track data of the corresponding inspection aircraft, and adjusting the boundary of the corresponding sub-inspection area if the spatial resolution exceeds the boundary of the sub-inspection area.
[0131] In some embodiments, the output of a multi-aircraft inspection track allocation scheme without conflict after resolution includes: after completing the resolution of all conflict events, verifying that there are no spatiotemporal conflicts in the tracks of all inspection aircraft, summarizing the final inspection tracks of each inspection aircraft and the corresponding sub-inspection area boundaries, forming a complete multi-aircraft inspection track allocation scheme and outputting it.
[0132] In some embodiments, the method further includes: recording the processing method and resolution effect data for each conflict resolution, generating a conflict resolution strategy sample library, and when a new conflict event is detected, matching the historical resolution strategy with the highest similarity to the current conflict scenario from the sample library, directly generating candidate resolution schemes and performing feasibility verification.
[0133] In some embodiments, the method further includes: acquiring the remaining endurance data and actual flight deviation data of each inspection aircraft in real time; when the remaining endurance of the inspection aircraft is lower than a preset threshold or the flight deviation exceeds a preset range, re-dividing the range of the corresponding sub-inspection area, allocating the area exceeding the carrying capacity to other inspection aircraft in normal condition, synchronously updating the flight tracks of each inspection aircraft and performing conflict verification.
[0134] It should be noted that those skilled in the art will understand that, for the sake of convenience and brevity, the specific working process of the track allocation system and each module of the multi-aircraft formation inspection mission described above can be referred to the corresponding content in the various embodiments of the track allocation method for the multi-aircraft formation inspection mission, and will not be repeated here.
[0135] The aforementioned method for track allocation in multi-aircraft formation patrol missions can be implemented as a computer program, which can be used in various ways, such as... Figure 7 It runs on the system shown.
[0136] Please see Figure 8 , Figure 8 This is a schematic block diagram of the structure of a computer device provided in an embodiment of this application. The computer device includes a processor, a memory, and a network interface connected via a device bus, wherein the memory may include a storage medium and internal memory.
[0137] The storage medium may store operating devices and computer programs. The computer program includes program instructions that, when executed, cause the processor to perform any method of track allocation for a multi-aircraft formation patrol mission.
[0138] The processor provides computing and control capabilities, supporting the operation of the entire computer device.
[0139] Internal memory provides an environment for the execution of computer programs in non-volatile storage media. When the computer program is executed by the processor, it enables the processor to perform any method of track allocation for multi-aircraft formation inspection missions.
[0140] This network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the terminal to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.
[0141] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.
[0142] In one embodiment, the processor is configured to run a computer program stored in memory to perform the following steps: Obtain the polygonal boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Divide the area to be inspected into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. For each inspection aircraft, an initial full-coverage inspection track corresponding to the sub-inspection area is generated. Spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. Perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output a multi-aircraft inspection track allocation scheme with no conflicts after resolution.
[0143] In some embodiments, obtaining polygon boundary information of the area to be inspected and inspection performance parameters of each inspection unit includes: obtaining polygon boundary vertex information of the area to be inspected, and inspection field of view width, endurance and cruising speed parameters of each inspection unit.
[0144] In some embodiments, the area to be inspected is divided into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. This includes: calculating the expected inspection area weight corresponding to each inspection machine based on its inspection coverage capability; initializing multiple seed points in the area to be inspected, matching the number of inspection machines; generating a weighted segmentation graphic based on the various seed points and cropping it with the boundary of the area to be inspected to obtain initial sub-regions corresponding to the various seed points; calculating the actual area of each initial sub-region; adjusting the position of the corresponding seed points based on the deviation between the actual area and the expected area of each sub-region; and repeating the region segmentation calculation and area deviation verification until the area deviation of each sub-region meets a preset threshold to obtain multiple sub-inspection areas.
[0145] In some embodiments, an initial full-coverage inspection track is generated for each inspection aircraft corresponding to a sub-inspection area, including: traversing each sub-inspection area and its assigned inspection aircraft, determining the main scanning direction of the corresponding sub-inspection area, calculating the interval distance between adjacent routes based on the inspection field of view width of the corresponding inspection aircraft, generating a continuous bow-shaped coverage waypoint sequence along the main scanning direction, inserting a smooth turning path at the turning point of the waypoint sequence, and generating the initial full-coverage inspection track corresponding to each inspection aircraft by combining the preset cruise altitude and cruise speed.
[0146] In some embodiments, spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. This includes: pairing all inspection aircraft into multiple inspection aircraft combinations, discretely sampling the two initial full-coverage inspection tracks of each inspection aircraft combination at a preset time interval, calculating the three-dimensional spatial distance between the corresponding points of the two tracks at each sampling time, determining the sampling time where the three-dimensional spatial distance is less than a preset safety interval as a conflict event, recording the corresponding inspection aircraft, conflict time, and conflict segment of all conflict events, and generating a conflict list.
[0147] In some embodiments, track resolution processing is performed on each conflict event in the conflict list, and the track of the corresponding inspection aircraft and the boundary of the sub-inspection area are updated. This includes: traversing each conflict event in the conflict list, assigning resolution priorities to the two inspection aircraft involved in the conflict, performing time dimension resolution first on the inspection aircraft with lower priority, adjusting the passage time and operating speed of the corresponding flight segment, performing spatial dimension resolution if the speed parameter exceeds the allowable range after time dimension resolution, adjusting the flight altitude or horizontal waypoint position of the corresponding flight segment, verifying whether the resolved track meets the inspection constraints and does not introduce new conflict events, updating the track data of the corresponding inspection aircraft, and adjusting the boundary of the corresponding sub-inspection area if the spatial resolution exceeds the boundary of the sub-inspection area.
[0148] In some embodiments, the output of a multi-aircraft inspection track allocation scheme without conflict after resolution includes: after completing the resolution of all conflict events, verifying that there are no spatiotemporal conflicts in the tracks of all inspection aircraft, summarizing the final inspection tracks of each inspection aircraft and the corresponding sub-inspection area boundaries, forming a complete multi-aircraft inspection track allocation scheme and outputting it.
[0149] In some embodiments, the method further includes: recording the processing method and resolution effect data for each conflict resolution, generating a conflict resolution strategy sample library, and when a new conflict event is detected, matching the historical resolution strategy with the highest similarity to the current conflict scenario from the sample library, directly generating candidate resolution schemes and performing feasibility verification.
[0150] In some embodiments, the method further includes: acquiring the remaining endurance data and actual flight deviation data of each inspection aircraft in real time; when the remaining endurance of the inspection aircraft is lower than a preset threshold or the flight deviation exceeds a preset range, re-dividing the range of the corresponding sub-inspection area, allocating the area exceeding the carrying capacity to other inspection aircraft in normal condition, synchronously updating the flight tracks of each inspection aircraft and performing conflict verification.
[0151] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, causes the processor to implement the steps of the track allocation method for a multi-aircraft formation inspection mission as provided in any embodiment of this application.
[0152] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.
[0153] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.
Claims
1. A method for track allocation in a multi-aircraft formation inspection mission, characterized in that, include: Obtain the polygonal boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Divide the area to be inspected into multiple sub-inspection areas based on the inspection coverage capability of each inspection machine. For each inspection aircraft, an initial full-coverage inspection track corresponding to the sub-inspection area is generated. Spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events. Perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output a multi-aircraft inspection track allocation scheme with no conflicts after resolution.
2. The method according to claim 1, characterized in that, Obtain the polygonal boundary information of the area to be inspected and the inspection performance parameters of each inspection machine, including: Acquire information on the polygonal boundary vertices of the area to be inspected, as well as the inspection field of view, endurance, and cruising speed parameters of each inspection aircraft.
3. The method according to claim 2, characterized in that, Based on the inspection coverage capability of each inspection machine, the area to be inspected is divided into multiple sub-inspection areas, including: Calculate the expected inspection area weight of each inspection machine based on its inspection coverage capability, and initialize multiple seed points in the area to be inspected, with the same number of inspection machines as the number of inspection machines. A weighted segmentation graphic is generated based on various sub-points and clipped with the boundary of the area to be inspected to obtain the initial sub-regions corresponding to various sub-points, and the actual area of each initial sub-region is calculated. Adjust the position of the corresponding seed point according to the deviation between the actual area and the expected area of each sub-region, and repeat the region segmentation calculation and area deviation verification until the area deviation of each sub-region meets the preset threshold to obtain multiple sub-inspection areas.
4. The method according to claim 1, characterized in that, For each inspection aircraft, an initial full-coverage inspection track is generated for the corresponding sub-inspection area, including: Traverse each sub-inspection area and its assigned inspection machine to determine the main scanning direction of the corresponding sub-inspection area; The interval distance between adjacent routes is calculated based on the inspection field of view width of the corresponding inspection aircraft. A continuous bow-shaped coverage waypoint sequence is generated along the main scanning direction. A smooth turning path is inserted at the turning point of the waypoint sequence. The initial full coverage inspection track corresponding to each inspection aircraft is generated by combining the preset cruise altitude and cruise speed.
5. The method according to claim 4, characterized in that, Spatiotemporal conflict detection is performed on the initial full-coverage inspection tracks of all inspection aircraft to generate a conflict list containing all conflict events, including: All inspection aircraft are paired up to form multiple inspection aircraft combinations. The two initial full-coverage inspection tracks of each inspection aircraft combination are discretely sampled at preset time intervals, and the three-dimensional spatial distance between the corresponding points of the two tracks at each sampling time is calculated. The sampling time when the three-dimensional spatial distance is less than the preset safety interval is identified as a conflict event. The corresponding inspection aircraft, conflict time and conflict flight segment of all conflict events are recorded to generate a conflict list.
6. The method according to claim 1, characterized in that, For each conflict event in the conflict list, track resolution is performed, and the track of the corresponding inspection aircraft and the boundary of the sub-inspection area are updated, including: Iterate through each conflict event in the conflict list, assign a resolution priority to the two inspection machines involved in the conflict, and perform time-dimensional resolution first for the inspection machine with lower priority; Adjust the transit time and speed of the corresponding flight segment. If the speed parameter exceeds the allowable range after time dimension resolution, perform spatial dimension resolution and adjust the flight altitude or horizontal waypoint position of the corresponding flight segment. Verify whether the resolved track meets the inspection constraints and does not introduce new conflict events, update the track data of the corresponding inspection aircraft, and adjust the boundary of the corresponding sub-inspection area if the spatial resolution exceeds the boundary of the sub-inspection area.
7. The method according to claim 6, characterized in that, Output a conflict-free multi-aircraft inspection track allocation scheme after the resolution is completed, including: After resolving all conflict events, the flight paths of all inspection aircraft were verified to be free of spatiotemporal conflicts. The final inspection tracks of each inspection aircraft and the corresponding sub-inspection area boundaries are summarized to form a complete multi-aircraft inspection track allocation scheme and output it.
8. The method according to claim 1, characterized in that, The method further includes: Record the processing methods and resolution effect data for each conflict resolution, and generate a sample library of conflict resolution strategies; When a new conflict event is detected, the historical resolution strategy with the highest similarity to the current conflict scenario is matched from the sample library, and a candidate resolution scheme is directly generated and its feasibility is verified.
9. The method according to claim 1, characterized in that, The method further includes: Real-time acquisition of remaining range data and actual flight deviation data of each inspection aircraft; when the remaining range of an inspection aircraft is lower than a preset threshold or the flight deviation exceeds a preset range, the range of the corresponding sub-inspection area is redefined. Areas exceeding the carrying capacity are allocated to other inspection aircraft in normal condition, and the flight paths of each inspection aircraft are updated synchronously and conflict verification is performed.
10. A track allocation system for multi-aircraft formation inspection missions, used to implement the method as described in any one of claims 1-9, characterized in that, include: The parameter acquisition unit is used to acquire the polygon boundary information of the area to be inspected and the inspection performance parameters of each inspection machine. Based on the inspection coverage capability of each inspection machine, the area to be inspected is divided into multiple sub-inspection areas. The list generation unit is used to generate the initial full-coverage inspection track for each inspection aircraft corresponding to the sub-inspection area, perform spatiotemporal conflict detection on the initial full-coverage inspection tracks of all inspection aircraft, and generate a conflict list containing all conflict events. The scheme output unit is used to perform track resolution processing on each conflict event in the conflict list, update the track of the corresponding inspection aircraft and the boundary of the sub-inspection area, and output a multi-aircraft inspection track allocation scheme without conflict after resolution.
