An Optimization Method for Autonomous Inspection Task Allocation of Low-Altitude Unmanned Aerial Vehicles

Abstract

This invention discloses an optimization method for autonomous inspection task allocation of low-altitude unmanned aerial vehicles (UAVs), belonging to the field of UAV intelligent control technology. The method includes: acquiring task attributes, UAV status, geographical environment, and real-time meteorological data through a data acquisition module; constructing a three-dimensional dynamic environment model by integrating geographical and meteorological data through an environment modeling module; and using a dynamic allocation module to minimize the number of UAV flights, combined with constraints on the UAV's maximum single flight distance and path safety threshold, employing an improved cost-saving algorithm for task grouping, optimizing the task sequence based on a vehicle path problem model with time windows, and generating a task allocation scheme. The control terminal sends the task allocation scheme to the UAV, which executes the scheme and adjusts its path according to real-time weather changes. After the task is completed, a multi-dimensional inspection report is generated. This invention improves task allocation efficiency and flight safety in complex environments while reducing inspection costs.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) intelligent control technology, and specifically discloses an optimization method for autonomous inspection task allocation of low-altitude flying UAVs. Background Technology

[0002] Drones, with their flexibility, efficiency, and intelligence, have been widely used in various fields, significantly improving operational efficiency and reducing costs; however, current methods for allocating drone inspection tasks have the following limitations:

[0003] Insufficient environmental adaptability: Traditional methods are mostly based on static geographic data for route planning, without incorporating real-time meteorological data, such as the dynamic impact of wind speed and turbulence on flight safety and energy consumption, resulting in a high risk of planned routes failing in actual flight.

[0004] Allocation efficiency needs improvement: Task grouping relies heavily on manual experience or simple distance clustering, without taking into account task priority, time window constraints, and drone endurance limitations, which can easily lead to redundant flight sorties or mission timeouts.

[0005] Insufficient quantification of safety: Risk factors such as no-fly zones and obstacles are usually judged in binary form, lacking a refined safety assessment of complex low-altitude environments, such as wind fields around building complexes and sudden weather events.

[0006] Lack of dynamic response: Flight path adjustments rely on manual intervention and cannot autonomously avoid meteorological threats such as sudden strong winds and sharp drops in visibility, affecting mission success rate.

[0007] Therefore, it is essential to invent an optimized method for autonomous inspection task allocation of low-altitude flying UAVs to solve the above problems. Summary of the Invention

[0008] To overcome the aforementioned shortcomings of existing technologies, this invention provides an optimization method for autonomous inspection task allocation of low-altitude unmanned aerial vehicles (UAVs). The method involves: a data acquisition module to obtain task attributes, UAV status, geographical environment, and real-time meteorological data; an environment modeling module to integrate geographical and meteorological data to construct a three-dimensional dynamic environment model; a dynamic allocation module to minimize the number of UAV flights, combining the maximum single flight distance and path safety threshold constraints, employing an improved cost-saving algorithm for task grouping, optimizing the task sequence based on a vehicle path problem model with time windows, and generating a task allocation scheme; a control terminal to issue the task allocation scheme to the UAV, which executes the scheme and adjusts its path according to real-time weather changes; and a multi-dimensional inspection report generated upon task completion, effectively solving the problems mentioned in the background technology.

[0009] To achieve the above objectives, the present invention provides the following technical solution: an optimization method for autonomous inspection task allocation of a low-altitude flying unmanned aerial vehicle (UAV), characterized by comprising a data acquisition module, an environment modeling module, a dynamic allocation module, a UAV, and a control terminal, specifically including the following steps:

[0010] S1. Collect task attribute data, UAV status data, geographic environment data and real-time meteorological data through the data acquisition module;

[0011] S2, the environmental modeling module integrates geographic environmental data and real-time meteorological data to construct a three-dimensional dynamic environmental model;

[0012] S3. The dynamic allocation module generates a task allocation scheme based on the constraints of the maximum flight distance and minimum path safety threshold of the UAV in a single run, with the goal of minimizing the number of runs.

[0013] S4. The control terminal issues tasks to the UAV according to the task allocation plan;

[0014] S5. The drone performs the mission and adjusts its flight path according to real-time weather data. The control terminal generates an inspection report after the mission is completed.

[0015] The specific analysis method for the generated task allocation scheme is as follows:

[0016] Based on task priority and task time window, all tasks are sorted to generate an initial task sequence;

[0017] Using the maximum single flight distance of the UAV as a constraint, an improved saving algorithm is adopted to cluster the tasks in the initial task sequence into several groups of task subsets that can be completed in a single flight. The goal is to minimize the total number of UAV flights required.

[0018] For each task subset, a vehicle routing problem model with a time window is constructed based on the current position of the UAV, the coordinates of the task position, the estimated flight time of the inspection path, and the time window constraint. The genetic algorithm is used to solve the model to optimize the execution order of tasks within the group. The goal is to minimize the total flight distance and time of the sortie and ensure that all tasks are completed within their time windows.

[0019] The mission safety index is calculated based on the safety level of the flyable area, and the optimized mission sequence is checked for time window conflicts, mission safety index below the threshold or exceeding the single maximum flight distance constraint. If there are conflicts, the mission grouping or sequence order is adjusted until all constraints are met.

[0020] The output includes the number of drone sorties, the mission sequence for each sortie, the estimated takeoff time for each sortie, the total flight distance, and the estimated execution time for each mission, as well as the mission allocation scheme.

[0021] The specific analysis method for adjusting the flight path is as follows:

[0022] If any of the following conditions are detected, dynamic path adjustment will be triggered:

[0023] The turbulence intensity index of the current path segment exceeds the turbulence intensity threshold;

[0024] The crosswind speed exceeded 70% of the drone's wind resistance limit;

[0025] Decreased atmospheric visibility resulted in target observation clarity falling below the preset value;

[0026] The adjustment strategies include:

[0027] Local paths are replanned based on updated environmental models to avoid areas of high turbulence and strong winds;

[0028] The flight altitude is dynamically adjusted based on real-time visibility to ensure the effectiveness of observations;

[0029] If the energy consumption of the adjusted route exceeds the remaining driving range, a mission abort or return command will be requested from the control terminal.

[0030] Based on the above embodiments, the task attribute data includes: task location coordinates, task priority, and window time; the UAV status data includes: remaining UAV range; the geographic environment data includes: digital elevation model, obstacle distribution data, no-fly zone boundary coordinates, and land cover type data; the real-time meteorological data includes: wind speed, wind direction, temperature, precipitation probability, atmospheric visibility, and turbulence intensity index.

[0031] Based on the above embodiments, the construction process of the three-dimensional dynamic environment model includes:

[0032] A static terrain skeleton is generated by overlaying digital elevation models with obstacle distribution data.

[0033] Real-time meteorological data is interpolated using finite element meshes to generate spatial distribution heat maps of wind speed and turbulence intensity.

[0034] By integrating the boundary coordinates of no-fly zones with land cover type data, the safety level of flyable areas is marked.

[0035] Based on the above embodiments, the security level calculation formula is: S=w1·exp(-k·V)+w2·(1-T) i )+w3·C t In the formula, S represents the safety level score, V represents the real-time wind speed, and T represents the wind speed. i C is the turbulence intensity index. t is the land cover type coefficient, w1, w2, w3 are weighting coefficients, and k is the wind speed attenuation factor.

[0036] Based on the above embodiments, the task safety index is calculated as follows: In the formula, I is the task safety index, n is the number of paths covered in the task subset, and S... i To score the security level of the i-th path segment, l i Let L be the length of the i-th path segment, L be the total length of the n paths, P be the task priority, β be the priority weight coefficient, and ΔT be the path length. i denoted as the rate of change of turbulence intensity, γ as the meteorological sudden change penalty coefficient, and δ(t) as the time urgency factor.

[0037] Based on the above embodiments, the control terminal generates an inspection report after the task is completed, specifically including:

[0038] Task execution sequence log;

[0039] Deviation analysis between actual flight path and preset path;

[0040] Statistics on the impact of meteorological data on flight energy consumption;

[0041] Number of times the path was dynamically adjusted and the classification of the reasons;

[0042] Task completion status marker.

[0043] The technical effects and advantages of this invention are as follows:

[0044] 1. By integrating digital elevation models, obstacle distribution data, and real-time meteorological data, a three-dimensional dynamic environment model is constructed, which includes wind speed field, turbulence intensity heat map, and safety level, providing real-time risk quantification basis for path planning;

[0045] 2. With the goal of minimizing the number of flights, we improve the saving algorithm to generate task subsets by clustering, and combine the genetic algorithm to optimize the task sequence within the group, so as to ensure the efficient execution of high-priority tasks under the constraints of time window and range.

[0046] 3. Automatically detect turbulence exceeding the threshold, crosswind exceeding the limit, or insufficient visibility during flight, triggering local path replanning, altitude adjustment, or return-to-home requests to improve mission robustness under sudden weather conditions;

[0047] 4. The control terminal generates inspection reports that include deviation analysis, meteorological impact statistics, and adjustment reason classification, supporting task review and algorithm iteration optimization. Attached Figure Description

[0048] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0049] Figure 1 This is a schematic diagram of the overall structure of the present invention.

[0050] Figure 2 This is a flowchart illustrating the overall steps of the present invention. Detailed Implementation

[0051] 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 embodiments of the present invention, and not all embodiments. 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.

[0052] This invention provides, for example Figure 1 The method shown is an optimization method for autonomous inspection task allocation of a low-altitude flying UAV, and its structure is as follows: Figure 1 As shown, it includes a data acquisition module, an environment modeling module, a dynamic allocation module, a drone, and a control terminal;

[0053] like Figure 2 As shown, the autonomous inspection task allocation optimization method for a low-altitude flying UAV specifically includes the following steps:

[0054] S1. Collect task attribute data, UAV status data, geographic environment data and real-time meteorological data through the data acquisition module;

[0055] Furthermore, in the above technical solution, the task attribute data includes: task location coordinates, task priority, and window time; the UAV status data includes: the remaining flight range of the UAV; the geographic environment data includes: digital elevation model, obstacle distribution data, no-fly zone boundary coordinates, and land cover type data; the real-time meteorological data includes: wind speed, wind direction, temperature, precipitation probability, atmospheric visibility, and turbulence intensity index.

[0056] S2, the environmental modeling module integrates geographic environmental data and real-time meteorological data to construct a three-dimensional dynamic environmental model;

[0057] Furthermore, in the above technical solution, the construction process of the three-dimensional dynamic environment model includes:

[0058] A static terrain skeleton is generated by overlaying digital elevation models with obstacle distribution data.

[0059] Real-time meteorological data is interpolated using finite element meshes to generate spatial distribution heat maps of wind speed and turbulence intensity.

[0060] By integrating the boundary coordinates of no-fly zones with land cover type data, the safety level of flyable areas is marked.

[0061] Furthermore, in the above technical solution, the formula for calculating the security level is: S = w1·exp(-k·V) + w2·(1-T) i )+w3·C t In the formula, S represents the safety level score, V represents the real-time wind speed, and T represents the wind speed. i C is the turbulence intensity index. t is the land cover type coefficient, w1, w2, w3 are weighting coefficients, and k is the wind speed attenuation factor.

[0062] It should be further noted that the safety level score ranges from S to [0, 1], with a larger value indicating greater safety; the land cover type coefficient C... t Depending on the type of inspection area, in the optimal technical solution, when the inspection area is a no-fly zone, C... t =0, when C is a building zone t =0.2, when it is a water area C t =0.5, which is the C value in the vegetated area. t =0.8, when C is in open space t =1.0; the weighting coefficients satisfy w1+w2+w3=1, with default values ​​of w1=0.4, w2=0.3, w3=0.3, and the default value of the wind speed attenuation factor is k=0.2;

[0063] Example of safety score calculation:

[0064] Scenario description: In a certain area, the real-time wind speed V = 8 m / s, and the turbulence intensity index T i =0.7, the land cover type is a mixed area, including 30% built-up area and 70% water area, the weighting coefficients w1=0.4, w2=0.3, w3=0.3, and the wind speed attenuation factor k=0.2;

[0065] Calculation process: C t = (0.3 × 0.2) + (0.7 × 0.5) = 0.06 + 0.35 = 0.41;

[0066] S=w1·exp(-k·V)+w2·(1-T i )+w3·C t

[0067] S = 0.4 × e (-0.2×8) +0.3×(1-0.7)+0.3×0.41≈0.29;

[0068] Conclusion: The safety score for this area is 0.29.

[0069] S3. The dynamic allocation module generates a task allocation scheme based on the constraints of the maximum flight distance and minimum path safety threshold of the UAV in a single run, with the goal of minimizing the number of runs.

[0070] Furthermore, in the above technical solution, the specific analysis method for the generated task allocation scheme is as follows:

[0071] Based on task priority and task time window, all tasks are sorted to generate an initial task sequence;

[0072] It should be further explained that the specific sorting method is as follows: first, tasks are sorted from high to low according to their priority; then, tasks with the same priority are sorted according to their time window, with tasks that are more urgent being sorted first.

[0073] Using the maximum single flight distance of the UAV as a constraint, an improved saving algorithm is adopted to cluster the tasks in the initial task sequence into several groups of task subsets that can be completed in a single flight. The goal is to minimize the total number of UAV flights required.

[0074] It should be further noted that the maximum single flight distance D of the aforementioned UAV max This represents 90% of the drone's remaining flight range.

[0075] The specific implementation method for clustering and grouping tasks in the initial task sequence is as follows:

[0076] For each mission's target location, within the flyable area of ​​the 3D dynamic environment model, the shortest feasible path from the preset takeoff point to the target location is searched based on the A* algorithm. When calculating the path, wind speed, wind direction, and turbulence intensity are incorporated as dynamic cost factors into the path cost function, prioritizing paths with lower wind speeds, weaker turbulence, and higher safety levels. Simultaneously, the path altitude is adjusted based on atmospheric visibility data to ensure the target is within the effective observation range. Finally, the optimal path for each mission is obtained.

[0077] Calculate the optimal path length L for each task i And calculate the combined savings value S for any two tasks. ij The improvement savings value S is calculated based on the average safety level score of the optimal task path and the time window compatibility coefficient. en ;

[0078] The task will be performed according to S en Values ​​are sorted in descending order, starting from the highest S. en Initially, attempt to merge two paths, i.e., perform constraint checks on the merge result. If the constraints are met, merge the paths and update the task group.

[0079] Stop when no valid merge is found, and output each task subset.

[0080] It should be further explained that the formula for calculating the combined savings value is: S ij =dist(D0,T i )+dist(D0,T j )-dist(T i ,T j In the formula, D0 represents the initial coordinates of the UAV, dist(A, B) represents the optimal path length from point A to point B, and T... x This represents the coordinates of the task point for the x-th task;

[0081] The S en The calculation formula is: In the formula, S x Assess the security level of the area where the mission is located, α ij The time window compatibility coefficient is calculated using the following formula: In the formula, t x Let t be the time window length for task x. ij This indicates the length of the overlapping portion of the time windows for task i and task j;

[0082] The constraint check includes: the merged path length L new <D max Furthermore, the merged task sequence can be completed within the respective time windows of all tasks.

[0083] For each task subset, a vehicle routing problem model with a time window is constructed based on the current position of the UAV, the coordinates of the task position, the estimated flight time of the inspection path, and the time window constraint. The genetic algorithm is used to solve the model to optimize the execution order of tasks within the group. The goal is to minimize the total flight distance and time of the sortie and ensure that all tasks are completed within their time windows.

[0084] The mission safety index is calculated based on the safety level of the flyable area, and the optimized mission sequence is checked for time window conflicts, mission safety index below the threshold or exceeding the single maximum flight distance constraint. If there are conflicts, the mission grouping or sequence order is adjusted until all constraints are met.

[0085] Furthermore, in the above technical solution, the task safety index is calculated as follows: In the formula, I is the task safety index, n is the number of paths covered in the task subset, and S... i The average security level score for the i-th path segment is given by l. i Let L be the length of the i-th path segment, L be the total length of the n paths, P be the task priority, β be the priority weight coefficient, and ΔT be the path length. iδ(t) represents the rate of change of turbulence intensity, γ represents the meteorological abrupt change penalty coefficient, δ(t) represents the time urgency factor, and t represents the remaining time before the mission time window ends.

[0086] It should be further explained that the value range of the task safety index I is I∈[0,201]. When I<100, it is determined to be below the threshold, triggering the adjustment of task grouping or sequence order. The priority weight coefficient and the meteorological change penalty coefficient are obtained through the mapping set of historical data and corresponding coefficients established in the database. The default value of the priority weight coefficient is β=0.7, and the default value of the meteorological change penalty coefficient is γ=0.4.

[0087] The formula for calculating the time urgency factor δ(t) is as follows:

[0088] The output includes the number of drone sorties, the mission sequence for each sortie, the estimated takeoff time for each sortie, the total flight distance, and the estimated execution time for each mission, as well as the mission allocation scheme.

[0089] Example of calculating mission safety index:

[0090] Scenario 1: The average safety scores of the task paths are S1 = 0.8, l1 = 200m, S2 = 0.6, l2 = 300m, the task priority is P = 0.9, and the turbulence rate of change is ΔT. i =0.4, t=90min, priority weight coefficient β=0.7, meteorological change penalty coefficient γ=0.4;

[0091] δ(t)=1-0.5tanh(0.05×30)=0.548;

[0092] I=100×(0.8×200+0.6×300) / (200+300)×e (0.7×0.9) ×(1-0.4×1 / 7)×0.548≈38.2;

[0093] Conclusion: I < 100, triggering adjustment of task grouping or sequence order.

[0094] Scenario 2: The average safety scores for the mission paths are S1 = 0.95, l1 = 150m, S2 = 0.90, l2 = 250m, mission priority P = 0.7, and turbulence rate of change ΔT. i =0.25, t=180min, priority weight coefficient β=0.7, meteorological change penalty coefficient γ=0.4;

[0095] Calculation process:

[0096] δ(t) = 1;

[0097]

[0098] I=100×(0.95×150+0.9×250) / (150+250)×e (0.7×0.7) ×(1-0.4×0)×1≈150;

[0099] Conclusion: I > 100, this subset of tasks is executable.

[0100] S4. The control terminal issues tasks to the UAV according to the task allocation plan;

[0101] S5. The drone performs the mission and adjusts its flight path based on real-time weather data. The control terminal generates an inspection report after the mission is completed.

[0102] Furthermore, in the above technical solution, the specific analysis method for adjusting the flight path is as follows:

[0103] If any of the following conditions are detected, dynamic path adjustment will be triggered:

[0104] The turbulence intensity index of the current path segment exceeds the turbulence intensity threshold;

[0105] The crosswind speed exceeded 70% of the drone's wind resistance limit;

[0106] Decreased atmospheric visibility resulted in target observation clarity falling below the preset value;

[0107] It should be further noted that the default value of the turbulence intensity threshold is 0.6.

[0108] The adjustment strategies include:

[0109] Local paths are replanned based on updated environmental models to avoid areas of high turbulence and strong winds;

[0110] The flight altitude is dynamically adjusted based on real-time visibility to ensure the effectiveness of observations;

[0111] If the energy consumption of the adjusted route exceeds the remaining driving range, a mission abort or return command will be requested from the control terminal.

[0112] Furthermore, in the above technical solution, the control terminal generates an inspection report after the task is completed, specifically including:

[0113] The mission execution timeline includes takeoff time, arrival time, departure time, and return time for each mission.

[0114] Deviation analysis between actual flight path and preset path;

[0115] Statistics on the impact of meteorological data on flight energy consumption;

[0116] Number of times the path was dynamically adjusted and the classification of the reasons;

[0117] Task completion status markers, including success, partial success, and failure.

[0118] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An autonomous inspection task allocation optimization method for low-altitude flying unmanned aerial vehicles, characterized in that, The utility model relates to a kind of unmanned aerial vehicle task allocation method and system, including data acquisition module, environment modeling module, dynamic allocation module, unmanned aerial vehicle and control terminal, specifically including following steps: S1, task attribute data, unmanned aerial vehicle state data, geographic environment data and real-time weather data are collected by data acquisition module; S2, environment modeling module fuses geographic environment data and real-time weather data, and constructs three-dimensional dynamic environment model; S3, dynamic allocation module generates task allocation scheme based on unmanned aerial vehicle single maximum flight distance and minimum path safety threshold constraint, with the goal of minimizing operation times; S4, control terminal issues task to unmanned aerial vehicle according to task allocation scheme; S5, unmanned aerial vehicle executes task and adjusts flight path according to real-time weather data, and control terminal generates inspection report after task completion; The specific analysis method for generating task allocation scheme is as follows: Sort all tasks based on task priority and task time window, and generate initial task sequence; Cluster tasks in initial task sequence into groups using improved saving algorithm, with the constraint of unmanned aerial vehicle single maximum flight distance, to form several task subsets that can be completed in a single flight, with the goal of minimizing the total flight times of required unmanned aerial vehicles; For each task subset, construct a vehicle routing problem model with time window based on unmanned aerial vehicle current location, task location coordinates, estimated flight time of inspection path and time window constraint, and solve the model using genetic algorithm to optimize the execution order of tasks in the group, with the goal of minimizing the total flight distance and time of this flight and ensuring that all tasks are completed within their time windows; Calculate task safety index according to the safety level of flyable area, and check whether there is a time window conflict, task safety index below threshold or exceeding single maximum flight distance constraint in the optimized task sequence, and if there is a conflict, adjust the task grouping or sequence order until all constraints are met; Output task allocation scheme containing unmanned aerial vehicle times, task sequence executed by each flight, estimated takeoff time of each flight, total flight distance and estimated execution time of each task. The specific analysis method for adjusting flight path is as follows: Trigger path dynamic adjustment if any of the following conditions is detected: Current path segment turbulence intensity index exceeds turbulence intensity threshold; Crosswind speed exceeds 70% of the upper limit of unmanned aerial vehicle wind resistance capacity; Atmospheric visibility decreases to cause target observation clarity below preset value; Adjustment strategies include: Replan local path based on updated environment model to avoid high turbulence area and strong wind area; Dynamically adjust flight altitude according to real-time visibility to ensure observation effectiveness; If the energy consumption of adjusted path exceeds remaining endurance mileage, request task termination or return instruction from control terminal; The construction process of three-dimensional dynamic environment model includes: Generate static terrain skeleton by superimposing digital elevation model and obstacle distribution data; Generate wind speed and turbulence intensity spatial distribution heat map by finite element grid interpolation of real-time weather data; Mark the safety level of flyable area by fusing no-fly zone boundary coordinates and land cover type data. The safety level calculation formula is: , wherein S is a safety level score, V is a real-time wind speed, T i is a turbulence intensity index, C t is a surface cover type coefficient, w1, w2, and w3 are weight coefficients, and k is a wind speed attenuation factor; The task safety index is calculated in the following manner: ; in the formula, I is a task safety index, n is a number of paths covered in a task subset, S i is a safety level score of an i-th path, l i is a length of the i-th path, L is a total length of n paths, P is a task priority, β is a priority weight coefficient, △T i is a turbulence intensity change rate, γ is a meteorological mutation penalty coefficient, and δ(t) is a time urgency factor. 2.The method of claim 1, wherein: The task attribute data includes task position coordinates, task priority and window time; the UAV state data includes UAV remaining endurance mileage; the geographic environment data includes digital elevation model, obstacle distribution data, no-fly zone boundary coordinates and ground cover type data; and the real-time weather data includes wind speed, wind direction, temperature, precipitation probability, atmospheric visibility and turbulence intensity index. 3.The method of claim 1, wherein: The control terminal generates an inspection report after completion of the task, and specifically includes: a task execution timing log; deviation analysis of an actual flight path from a preset path; influence statistics of weather data on flight energy consumption; path dynamic adjustment times and reason classification; a task completion status marker.

Images