Multi-unmanned aerial vehicle navigation path planning method and system based on multi-task parameters

Abstract

The invention relates to the technical field of path planning, in particular to a multi-unmanned aerial vehicle navigation path planning method and system based on multi-task parameters, and the method comprises the steps: obtaining a three-dimensional mapping space, determining a current wind speed, a current gust vector, a current rainfall capacity and an unmanned aerial vehicle task sequence, obtaining a plurality of historical fault groups, performing negative pheromone marking on the three-dimensional mapping space based on a preset initial pheromone concentration and a plurality of historical fault groups to obtain a negative marking space, and on the basis of the current wind speed, the current gust vector, the current rainfall, a pre-constructed optimized heuristic function, a pre-constructed path coordinate group sequence set and a negative marking space, carrying out optimized ant colony simulation on the jth task coordinate group to obtain an updated coordinate group sequence set, and generating a plurality of optimal paths by utilizing the updated coordinate group sequence set, and completing multi-unmanned aerial vehicle navigation path planning based on the plurality of optimal paths. According to the invention, the accuracy and reliability of path planning can be improved, and the safety when multiple unmanned aerial vehicles execute tasks at the same time is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and particularly to a multi-UAV navigation path planning method and system based on multi-task parameters. Background Art

[0002] With the continuous improvement of the demand for intelligent operations, UAV systems have been widely used in complex environment tasks such as urban security, intelligent warehousing, and disaster emergency. Compared with single-UAV operations, the collaborative execution of tasks by multiple UAVs can significantly improve the response speed and coverage. However, in the actual application process, when multiple UAVs execute multiple tasks in the same airspace simultaneously, they may face challenges such as path conflicts and environmental interference, which pose higher requirements for the accuracy, reliability, and safety of path planning.

[0003] Currently, common UAV path planning methods include Dijkstra, RRT, and ant colony algorithms, etc. These methods mainly search for feasible paths in space based on grid maps. Some methods introduce obstacle avoidance strategies to adapt to complex tasks, but they still mainly focus on static scenarios and single tasks.

[0004] Although the existing technologies can achieve the planning of UAV navigation paths, the existing ant colony algorithms generally lack the consideration of environmental factors such as wind speed and rainfall, and fail to effectively use historical fault data for pheromone marking to avoid high-risk areas. Moreover, there is a lack of interference analysis mechanism between multi-UAV paths, which is prone to path conflicts. Therefore, there is an urgent need for a navigation path planning method for multi-tasks and multi-UAVs to improve the accuracy and reliability of path planning and enhance the safety when multiple UAVs execute tasks simultaneously. Summary of the Invention

[0005] The present invention provides a multi-UAV navigation path planning method and a computer-readable storage medium based on multi-task parameters, and its main purpose is to improve the accuracy and reliability of path planning and enhance the safety when multiple UAVs execute tasks simultaneously.

[0006] To achieve the above object, a multi-UAV navigation path planning method based on multi-task parameters provided by the present invention includes: Obtain a three-dimensional mapping space, wherein the three-dimensional mapping space is in the shape of a cube, and the three-dimensional mapping space includes: a space rectangular coordinate system and a plurality of cells, wherein the cells are in the shape of a cube, the unit length of the space rectangular coordinate system is the side length of the cell, each cell in the plurality of cells has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system, and the plurality of cells are composed of a plurality of blank cells and a plurality of obstacle cells; The current wind speed, the current gust vector, the current rainfall amount, and the UAV mission sequence are confirmed, where the UAV mission sequence includes: K task coordinate groups, and each task coordinate group includes: a starting coordinate and an ending coordinate; Multiple historical fault groups are obtained, where each historical fault group includes: a historical fault coordinate and a historical fault count; Based on a preset initial pheromone concentration and multiple historical fault groups, negative pheromone marking is performed on the three-dimensional mapping space to obtain a negative marking space; The j-th task coordinate group is extracted from the UAV mission sequence, where the initial value of j is 1; Based on the current wind speed, the current gust vector, the current rainfall amount, a pre-constructed optimization heuristic function, a pre-constructed sequence set of path coordinate groups, and the negative marking space, an optimized ant colony simulation is performed on the j-th task coordinate group to obtain an updated sequence set of coordinate groups, where the updated sequence set of coordinate groups includes: multiple optimal path sequences; The updated sequence set of coordinate groups is used as the sequence set of path coordinate groups, let J = j + 1, take J as j, and return to the step of extracting the j-th task coordinate group from the UAV mission sequence until j = K, and multiple optimal paths are generated using the updated sequence set of coordinate groups, where the optimal paths correspond one-to-one with the task coordinate groups; Based on multiple optimal paths, multi-UAV navigation path planning is completed.

[0007] Optionally, the negative pheromone marking is performed on the three-dimensional mapping space based on a preset initial pheromone concentration and multiple historical fault groups to obtain a negative marking space, including: The following operations are performed on each historical fault group in the multiple historical fault groups: Based on the historical fault coordinate in the historical fault group, a fault cell is confirmed in the three-dimensional mapping space; Based on the fault cell, multiple dangerous cells are confirmed in the three-dimensional mapping space, where the dangerous cells are adjacent to the fault cell in the three-dimensional mapping space; Based on the initial pheromone concentration and the historical fault count in the historical fault group, a dangerous pheromone concentration is calculated; Based on the dangerous pheromone concentration, an obstacle pheromone concentration is calculated, where the obstacle pheromone concentration is half of the dangerous pheromone concentration; Based on the obstacle pheromone concentration, the fault cell is marked to obtain an obstacle marked cell, and based on the dangerous pheromone concentration, each of the multiple dangerous cells is marked to obtain multiple dangerous marked cells; The obstacle marked cell and the multiple dangerous marked cells are summarized to obtain multiple repulsive cells, where the repulsive cells are obstacle marked cells or dangerous marked cells; Exclude multiple rejection cells from multiple cells in the three-dimensional mapping space to obtain multiple basic cells; Mark each of the multiple basic cells based on the initial pheromone concentration to obtain multiple initially marked cells; Summarize the multiple rejection cells and the multiple initially marked cells to obtain multiple initial cells, where the initial cells are rejection cells or initially marked cells; Identify the negative marking space based on the multiple initial cells and the three-dimensional mapping space.

[0008] Optionally, the optimizing ant colony simulation for the j-th task coordinate group based on the current wind speed, the current gust vector, the current rainfall, the pre-constructed optimization heuristic function, the pre-constructed sequence set of path coordinate groups, and the negative marking space to obtain the updated sequence set of coordinate groups includes: Identify the starting cell in the negative marking space according to the starting coordinate in the j-th task coordinate group, and denote the ending coordinate in the j-th task coordinate group as the termination coordinate; Generate multiple virtual ants, and perform the following operations on each of the multiple virtual ants: Place the virtual ant in the starting cell to obtain the starting point cell; Identify multiple neighboring cells of the starting point cell in the negative marking space; Perform the following operations on each of the multiple neighboring cells: Analyze the transfer strategy for the neighboring cell and the starting point cell according to the current wind speed, the current gust vector, the current rainfall, the optimization heuristic function, the termination coordinate, the preset number of loops, the pre-constructed sequence of memory coordinate groups, the preset starting time, and the sequence set of path coordinate groups to obtain the transfer comprehensive index and the update time; Summarize the transfer comprehensive index and the update time respectively to obtain multiple transfer comprehensive indexes and multiple update times, where the transfer comprehensive index and the update time correspond to the neighboring cells one by one; Perform probability transfer on the multiple neighboring cells based on the multiple transfer comprehensive indexes and the multiple update times to obtain the transfer cell and the landing time; Move the virtual ant to the transfer cell to obtain the landing point cell, and identify the landing point coordinate of the landing point cell in the negative marking space; Combine the landing point coordinate and the landing time to obtain the landing point coordinate group; Update the sequence of memory coordinate groups using the landing point coordinate group to obtain the updated sequence of memory groups; Determine whether the landing point coordinate is equal to the termination coordinate; If the landing coordinates are not equal to the termination coordinates, then use the landing cell as the starting cell, use the updated memory group sequence as the memory coordinate group sequence, use the landing time as the starting time, and return the step of identifying multiple adjacent cells of the starting cell in the negative marking space until the landing coordinates are equal to the termination coordinates; If the landing coordinates are equal to the termination coordinates, then use the updated memory group sequence as the target path sequence; Aggregate the target path sequences to obtain multiple target path sequences, where a target path sequence includes: multiple target coordinate groups, and a target coordinate group includes: a target coordinate and a target time; Perform path analysis on the multiple target path sequences to obtain the path coincidence degree and multiple total path times; Judge the path coincidence degree and compare the loop count with the preset loop threshold; If the path coincidence degree is less than the path threshold and the loop count is less than the loop threshold, then optimize the pheromone in the negative marking space according to the multiple total path times and the multiple target path sequences to obtain a path marking space, calculate the update count according to the loop count, use the path marking space as the negative marking space, use the update count as the loop count, and return the step of generating multiple virtual ants until the path coincidence degree is greater than or equal to the path threshold or the loop count is greater than or equal to the loop threshold; If the path coincidence degree is greater than or equal to the path threshold or the loop count is greater than or equal to the loop threshold, then confirm the optimal path sequence based on the multiple total path times and the multiple target path sequences, and update the path coordinate group sequence set according to the optimal path sequence to obtain an updated coordinate group sequence set.

[0009] Optionally, the analyzing the transfer strategy for adjacent cells and the starting cell according to the current wind speed, the current gust vector, the current rainfall, the optimization heuristic function, the termination coordinates, the preset number of loops, the pre-constructed memory coordinate group sequence, the preset starting time, and the path coordinate group sequence set to obtain the transfer comprehensive index and the update time includes: Identify the adjacent coordinates and the starting coordinates of the adjacent cells and the starting cell in the negative marking space respectively; Calculate the far distance according to the adjacent coordinates and the termination coordinates; Obtain the near distance based on the adjacent coordinates and the starting coordinates; Calculate the movement time according to the preset resolution conversion rate, the near distance, and the preset average speed; Calculate the update time according to the movement time and the starting time, where the update time is the sum of the movement time and the starting time; Judge whether the adjacent cell is the obstacle cell. If the adjacent cell is the obstacle cell, then use the preset zeroing probability as the transfer comprehensive index; Otherwise, confirm the movement vector based on the adjacent coordinates and the starting coordinates; Identify the last coordinate group in the memory coordinate group sequence, where the last coordinate group is the last memory coordinate group in the memory coordinate group sequence; Based on the last coordinate group, identify the advance coordinate group in the memory coordinate group sequence, where the last coordinate group is adjacent to the advance coordinate group and lags behind the advance coordinate group in the memory coordinate group sequence; Extract the advance coordinates from the advance coordinate group, extract the last coordinates from the last coordinate group, obtain the memory vector based on the advance coordinates and the last coordinates, and calculate the corner energy consumption index according to the memory vector and the movement vector; Calculate the environmental impact index according to the movement vector, the current wind speed, the current gust vector and the current rainfall, and the calculation formula is as follows: Wherein, is the environmental impact index, and are the current rainfall and the current wind speed respectively, and are the current gust vector and the preset rising vector respectively, is the movement vector, is the modulus of the movement vector, and are the preset rising resistance coefficient and the preset wind speed resistance coefficient respectively, and are the modulus of the rising vector and the modulus of the current gust vector respectively; Identify the adjacent pheromone concentration of the adjacent cell; Perform interference characteristic analysis on the path coordinate group sequence set based on the update time and the adjacent coordinates to obtain the mutual interference index; Substitute the number of cycles, the adjacent pheromone concentration, the near distance, the far distance, the mutual interference index, the corner energy consumption index and the environmental impact index into the optimization heuristic function to obtain the transfer comprehensive index.

[0010] Optionally, the performing interference characteristic analysis on the path coordinate group sequence set based on the update time and the adjacent coordinates to obtain the mutual interference index includes: Judge whether the path coordinate group sequence set is an empty set. If the path coordinate group sequence set is an empty set, use the preset initial interference index as the mutual interference index. Otherwise, perform the following operations on each path coordinate group sequence in the path coordinate group sequence set: Identify the close coordinate group in the path coordinate group sequence based on the update time; Extract the close coordinates and the close time from the close coordinate group; Calculate the mutual interference factor according to the update time, adjacent coordinates, close coordinates, and close time; Summarize the mutual interference factors to obtain multiple mutual interference factors, and calculate the mutual interference index according to the multiple mutual interference factors, where the mutual interference index is the sum of the multiple mutual interference factors.

[0011] Optionally, the optimization heuristic function is as follows: Wherein, is the optimization heuristic function, is the corner energy consumption index, is the mutual interference index, is the adjacent pheromone concentration, is the number of cycles, is the cycle threshold, is the far distance, is the near distance.

[0012] Optionally, the probability transfer of multiple adjacent cells based on multiple transfer comprehensive indices and multiple update times to obtain transfer cells and landing times includes: [[ID=зо]]Perform the following operations on each adjacent cell among the multiple adjacent cells: Calculate the transfer probability according to the transfer comprehensive index corresponding to the adjacent cell; Perform probability selection according to the transfer probability corresponding to each adjacent cell among the multiple adjacent cells to obtain transfer cells; Use the update time corresponding to the transfer cell among the multiple update times as the landing time.

[0013] Optionally, the path parsing of multiple target path sequences to obtain the path coincidence degree and multiple total path times includes: Confirm the number of paths of multiple target path sequences; Perform the following operations on each target path sequence among the multiple target path sequences: Extract the a-th target coordinate group from the target path sequence, where the initial value of a is 1; Extract the a-th coordinate from the a-th target coordinate group, where the a-th coordinate is the target coordinate in the a-th target coordinate group; >mSummarize the a-th coordinates to obtain multiple a-th coordinates, and extract multiple reference abscissas, multiple reference ordinates, and multiple reference vertical coordinates from the multiple a-th coordinates; Calculate the abscissa variance according to the multiple reference abscissas, where the abscissa variance is the variance of the multiple reference abscissas; Obtain the ordinate variance and the vertical coordinate variance respectively based on the multiple reference ordinates and the multiple reference vertical coordinates; Calculate the average coordinate variance based on the abscissa variance, ordinate variance, and vertical coordinate variance, where the average coordinate variance is the average of the abscissa variance, ordinate variance, and vertical coordinate variance; Let A = a + 1, take A as a, and return to the step of confirming the number of paths of multiple target path sequences until A = M, where M is the number of paths; Summarize the average coordinate variances to obtain multiple average coordinate variances, and calculate the path overlap degree based on the multiple average coordinate variances; Perform the following operations on each of the multiple target path sequences: Extract multiple target times from multiple target coordinate groups in the target path sequence; Calculate the total path time based on the multiple target times, where the total path time is the sum of the multiple target times; Summarize the total path times to obtain multiple total path times.

[0014] Optionally, the information pheromone of the negative marking space is optimized according to the multiple total path times and the multiple target path sequences to obtain a path marking space, including: Sequentially extract target path sequences from the multiple target path sequences, and perform the following operations on the extracted target path sequences: Calculate the target pheromone increment based on the initial pheromone concentration and the total path time corresponding to the target path sequence in the multiple total path times; Extract multiple target coordinates from multiple target coordinate groups in the target path sequence; Perform the following operations on each of the multiple target coordinates: Confirm a target cell based on the target coordinate in the negative marking space; Identify the target pheromone concentration of the target cell, and calculate the replacement pheromone concentration according to the target pheromone concentration and the target pheromone increment; Update the pheromone of the target cell based on the replacement pheromone concentration to obtain a supplementary cell; Summarize the supplementary cells to obtain multiple supplementary cells; Update the negative marking space based on the multiple supplementary cells to obtain a supplementary three-dimensional space; Take the supplementary three-dimensional space as the negative marking space, return to the step of sequentially extracting target path sequences from the multiple target path sequences until all the multiple target path sequences are extracted, and take the supplementary three-dimensional space as the path marking space.

[0015] To achieve the above object, the present invention also provides a multi-UAV navigation path planning system based on multi-task parameters, including: A mapping space construction module for obtaining a three-dimensional mapping space. The three-dimensional mapping space is in the shape of a cube and includes: a spatial rectangular coordinate system and multiple cells. The cells are in the shape of cubes, the unit length of the spatial rectangular coordinate system is the side length of the cell, each cell in the multiple cells has a unique corresponding three-dimensional coordinate in the spatial rectangular coordinate system, and the multiple cells are composed of multiple blank cells and multiple obstacle cells; An environmental data marking module for identifying the current wind speed, the current gust vector, the current rainfall, and the UAV mission sequence. The UAV mission sequence includes: K mission coordinate groups, and a mission coordinate group includes: a starting coordinate and an ending coordinate. Obtain multiple historical fault groups, where a historical fault group includes: a historical fault coordinate and the number of historical faults. Perform negative pheromone marking on the three-dimensional mapping space based on a preset initial pheromone concentration and multiple historical fault groups to obtain a negatively marked space; An ant colony algorithm optimization module for extracting the j-th mission coordinate group from the UAV mission sequence, where the initial value of j is 1. Perform an optimized ant colony simulation on the j-th mission coordinate group based on the current wind speed, the current gust vector, the current rainfall, a pre-constructed optimization heuristic function, a pre-constructed sequence set of path coordinate groups, and the negatively marked space to obtain an updated sequence set of coordinate groups, where the updated sequence set of coordinate groups includes: multiple optimal path sequences; An optimal path generation module for using the updated sequence set of coordinate groups as the sequence set of path coordinate groups, setting J = j + 1, using J as j, and returning to the step of extracting the j-th mission coordinate group from the UAV mission sequence until j = K. Generate multiple optimal paths using the updated sequence set of coordinate groups, where the optimal paths correspond one-to-one with the mission coordinate groups, and complete the multi-UAV navigation path planning based on the multiple optimal paths.

[0016] To solve the above problems, the present invention also provides an electronic device, which includes: A memory storing at least one instruction; A processor for executing the instructions stored in the memory to implement the above-mentioned multi-UAV navigation path planning method based on multi-task parameters.

[0017] To solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned multi-UAV navigation path planning method based on multi-task parameters.

[0018] To solve the problems described in the background art, the present invention obtains a three-dimensional mapping space. The shape of the three-dimensional mapping space is a cube, and the three-dimensional mapping space includes: a space rectangular coordinate system and a plurality of cells. The shape of the cells is a cube, the unit length of the space rectangular coordinate system is the side length of the cells, and each of the plurality of cells has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system. The plurality of cells are composed of a plurality of blank cells and a plurality of obstacle cells. It can be seen that in the embodiment of the present invention, the terrain features and spatial structure of the target task area in reality are mapped into a three-dimensional mapping space, so as to convert the real spatial environment information into a mathematical model that can be processed by a computer, providing a computable spatial structure basis for subsequent path planning, and then determining the current wind speed, the current gust vector, the current rainfall amount, and the UAV task sequence. The UAV task sequence includes: K task coordinate groups, and the task coordinate group includes: a starting coordinate and an ending coordinate. It can be seen that in the embodiment of the present invention, by obtaining the current wind speed, the current gust vector, and the current rainfall amount, real-time environmental parameters are provided for subsequent path planning, enhancing the reliability and safety of path planning. At the same time, by obtaining the UAV task sequence, it is convenient to perform path planning in sequence according to the priority of the tasks in the UAV task sequence. Obtain a plurality of historical failure groups, where the historical failure group includes: historical failure coordinates and the number of historical failures. Based on the preset initial pheromone concentration and a plurality of historical failure groups, negative pheromone marking is performed on the three-dimensional mapping space to obtain a negatively marked space. It can be seen that in the embodiment of the present invention, by introducing historical failure data and using the historical failure data to perform negative pheromone marking on the three-dimensional mapping space, the ant colony algorithm execution process automatically avoids high-risk areas, improving the reliability and safety of path planning. Extract the j-th task coordinate group from the UAV task sequence, where the initial value of j is 1. Based on the current wind speed, the current gust vector, the current rainfall amount, a pre-constructed optimization heuristic function, a pre-constructed path coordinate group sequence set, and the negatively marked space, an optimized ant colony simulation is performed on the j-th task coordinate group to obtain an updated coordinate group sequence set. The updated coordinate group sequence set includes: a plurality of optimal path sequences. It can be seen that in the embodiment of the present invention, through an improved ant colony algorithm, the search for the optimal path is realized on the basis of considering environmental factors and the mutual interference factors of multiple UAVs, improving the accuracy and reliability of path planning. Take the updated coordinate group sequence set as the path coordinate group sequence set, let J = j + 1, take J as j, and return to the step of extracting the j-th task coordinate group from the UAV task sequence until j = K. Generate a plurality of optimal paths by using the updated coordinate group sequence set. The optimal paths correspond one-to-one with the task coordinate groups. Based on the plurality of optimal paths, the multi-UAV navigation path planning is completed. It can be seen that in the embodiment of the present invention, by sequentially extracting task coordinate groups from the UAV task sequence through a loop process and generating optimal paths one by one, the situation of overlap or interference of the multi-UAV paths is avoided, improving the safety when multiple UAVs perform tasks simultaneously.Therefore, the present invention can improve the accuracy and reliability of path planning and enhance the safety when multiple UAVs perform tasks simultaneously. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 FIG. is a schematic flowchart of a multi-UAV navigation path planning method based on multi-task parameters provided by an embodiment of the present invention; Figure 2 FIG. is a functional module diagram of a multi-UAV navigation path planning system based on multi-task parameters provided by an embodiment of the present invention; Figure 3 FIG. is a schematic structural diagram of an electronic device for implementing the multi-UAV navigation path planning method based on multi-task parameters provided by an embodiment of the present invention.

[0020] DESCRIPTION OF THE REFERENCE NUMERALS: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0021] The implementation, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] An embodiment of the present application provides a multi-UAV navigation path planning method based on multi-task parameters. The execution subject of the multi-UAV navigation path planning method based on multi-task parameters includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the multi-UAV navigation path planning method based on multi-task parameters can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0024] Referring to Figure 1 FIG., which is a schematic flowchart of a multi-UAV navigation path planning method based on multi-task parameters provided by an embodiment of the present invention. In this embodiment, the multi-UAV navigation path planning method based on multi-task parameters includes: S1. Obtain a three-dimensional mapping space, where the three-dimensional mapping space is in the shape of a cube, and the three-dimensional mapping space includes: a space rectangular coordinate system and a plurality of cells, where the cells are in the shape of a cube, the unit length of the space rectangular coordinate system is the side length of the cell, each cell in the plurality of cells has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system, and the plurality of cells are composed of a plurality of blank cells and a plurality of obstacle cells.

[0025] It should be explained that the three-dimensional mapping space is a three-dimensional model used to reflect the terrain features and spatial structure of the target task area. By mapping the target task area into the three-dimensional mapping space, the real spatial environment information is converted into a mathematical model that can be processed by a computer. And the three-dimensional mapping space is pre-scanned by the staff of the UAV control center through a lidar point cloud scanning system for the target task area to obtain the three-dimensional point cloud data of the target task area, and the three-dimensional point cloud data is input into the three-dimensional mapping software of the computer (such as OctoMap, RTAB-Map, and Point Cloud Library) for modeling processing, and finally the three-dimensional mapping space is generated. The target task area is the largest spatial area where multiple UAVs are allowed to move when performing tasks in reality, and the shape of the target task area in reality is a cube. The UAV control center is a department responsible for controlling multiple UAVs. And the technology of scanning the target task area through the lidar point cloud scanning system to obtain the three-dimensional point cloud data of the target task area, inputting the three-dimensional point cloud data into the three-dimensional mapping software of the computer (such as OctoMap, RTAB-Map, and Point Cloud Library) for modeling processing, and finally generating the three-dimensional mapping space is a prior art, and it will not be elaborated in the embodiments of the present invention.

[0026] It can be understood that in order to reduce the data volume and computational complexity in the process of constructing the three-dimensional mapping space, when constructing the three-dimensional mapping space using the target task area, a resolution conversion rate for mapping the target task area to the three-dimensional mapping space is preset. Exemplarily, when the resolution conversion rate is 100, the corresponding distance between two points 1 meter apart in the target task area in the three-dimensional mapping space is 1 centimeter, that is, each 1 centimeter of mapping unit corresponds to a 1-meter distance in the real space.

[0027] It should be understood that when the three-dimensional mapping space is constructed, it has been divided into multiple cubes with equal volumes according to the principle of uniform division and the preset side length of the cell. The multiple cubes with equal volumes are the multiple cells. Exemplarily, if the preset side length of the cell is 1 centimeter and the total volume of the three-dimensional mapping space is 1 cubic meter, the three-dimensional mapping space includes a total of 1,000,000 cells.

[0028] It can be understood that a blank cell refers to a cell in the three-dimensional mapping space that is not occupied by any obstacles, representing the space where the UAV can freely pass, and an obstacle cell refers to a cell where there are obstacles, representing the space where the UAV cannot pass.

[0029] It should be understood that taking any vertex of the three-dimensional mapping space as the origin, and using the three adjacent edges of this vertex as the horizontal axis, vertical axis, and vertical axis respectively to construct the space rectangular coordinate system. The unit length of the space rectangular coordinate system is the side length of the cell, and the coordinates corresponding to the geometric center of each cell in the space rectangular coordinate system are used to indicate the position where the cell is located. Therefore, each cell in the three-dimensional mapping space has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system. For example, the coordinates of the cell closest to the origin are (0.5, 0.5, 0.5), and the coordinates of the cell adjacent to the cell closest to the origin and directly above it are (0.5, 0.5, 1.5).

[0030] S2. Confirm the current wind speed, current gust vector, current rainfall, and the UAV mission sequence. Among them, the UAV mission sequence includes: K mission coordinate groups, and each mission coordinate group includes: a starting coordinate and an ending coordinate.

[0031] It should be explained that the current wind speed refers to the wind speed in the target mission area at this time. Optionally, multiple wind speeds in the target mission area at this time are collected by multiple wind speed sensors, and the average value of the multiple wind speeds is calculated to obtain the current wind speed. The current rainfall refers to the precipitation in the target mission area at this time. The current gust vector is a unit vector in the three-dimensional mapping space used to reflect the wind direction in the target mission area at this time. Exemplarily, if the wind direction in the target mission area at this time is north wind, and the positive direction of the horizontal axis in the three-dimensional mapping space corresponds to the direction from south to north in reality, then the current gust vector is (-1, 0, 0); if the wind direction in the target mission area at this time is south wind, then the current gust vector is (1, 0, 0). Optionally, the wind direction and rainfall are obtained by querying the weather of the target mission area on the website of the China Meteorological Administration.

[0032] Exemplarily, if there are multiple UAVs about to execute tasks in the target mission area, the coordinates of the cell corresponding to the position of one of the UAVs in the three-dimensional mapping space at this time are the starting coordinates, and the coordinates of the cell corresponding to the position that this UAV needs to reach when executing the task in the three-dimensional mapping space are the ending coordinates. The starting coordinate and the ending coordinate form the mission coordinate group, and one UAV corresponds to one mission coordinate group. If there are K UAVs, there are a total of K mission coordinate groups. The K mission coordinate groups are sorted according to the priority of task execution to obtain the UAV mission sequence, and the priority of task execution is determined by the staff of the UAV control center.

[0033] S3. Obtain multiple historical fault groups. Among them, each historical fault group includes: historical fault coordinates and the number of historical faults.

[0034] It is understandable that the coordinates of the cell corresponding to the location where the drone malfunctioned in the target mission area in the three-dimensional mapping space are the historical failure coordinates, and the historical failure count refers to the number of times a failure occurred at the historical failure coordinates. For example, if the number of times a failure occurred at the location corresponding to the coordinates (12, 3, 9) is 1, then the historical failure group is {(12, 3, 9), 1}; if the number of times a failure occurred at the location corresponding to the coordinates (32, 1, 12) is 2, then the historical failure group is {(32, 1, 12), 2}. The records of multiple drone malfunctions in history are statistically analyzed to generate multiple historical failure groups.

[0035] S4. Perform negative pheromone marking on the three-dimensional mapping space based on the preset initial pheromone concentration and multiple historical failure groups to obtain a negatively marked space.

[0036] Specifically, the performing negative pheromone marking on the three-dimensional mapping space based on the preset initial pheromone concentration and multiple historical failure groups to obtain a negatively marked space includes: Perform the following operations on each historical failure group among the multiple historical failure groups: Identify the failed cell in the three-dimensional mapping space based on the historical failure coordinates in the historical failure group; Identify multiple dangerous cells in the three-dimensional mapping space based on the failed cell, where the dangerous cells are adjacent to the failed cell in the three-dimensional mapping space; Calculate the dangerous pheromone concentration based on the initial pheromone concentration and the historical failure count in the historical failure group. The calculation formula is as follows: Where, is the dangerous pheromone concentration, is the historical failure count, is the initial pheromone concentration, is the natural constant; Calculate the obstacle pheromone concentration based on the dangerous pheromone concentration, where the obstacle pheromone concentration is half of the dangerous pheromone concentration; Mark the failed cell based on the obstacle pheromone concentration to obtain an obstacle-marked cell, and mark each of the multiple dangerous cells based on the dangerous pheromone concentration to obtain multiple dangerous-marked cells; Summarize the obstacle-marked cell and the multiple dangerous-marked cells to obtain multiple repulsive cells, where the repulsive cells are either the obstacle-marked cell or the dangerous-marked cells; Exclude the multiple repulsive cells from the multiple cells in the three-dimensional mapping space to obtain multiple basic cells; Mark each of the multiple basic cells based on the initial pheromone concentration to obtain multiple initially marked cells; Aggregate multiple exclusion cells and multiple initially marked cells to obtain multiple initial cells, where the initial cells are either exclusion cells or initially marked cells; Based on the multiple initial cells and the three-dimensional mapping space, identify the negative marking space.

[0037] It should be explained that identifying the faulty cells based on the historical fault coordinates in the historical fault group in the three-dimensional mapping space means: regarding the cells in the multiple cells of the three-dimensional mapping space whose coordinates are the historical fault coordinates as the faulty cells.

[0038] It can be understood that marking the faulty cells based on the obstacle pheromone concentration to obtain the obstacle marked cells means: using the value of the obstacle pheromone concentration to identify the faulty cells, and the obstacle marked cells are the faulty cells after being identified. Marking each of the multiple dangerous cells based on the danger pheromone concentration to obtain multiple danger marked cells means: using the value of the danger pheromone concentration to identify each of the multiple dangerous cells, and the multiple danger marked cells are the multiple dangerous cells after being identified.

[0039] It should be understood that the method of marking each of the multiple basic cells based on the initial pheromone concentration to obtain multiple initially marked cells is the same as the method of marking each of the multiple dangerous cells based on the danger pheromone concentration to obtain multiple danger marked cells, and will not be elaborated here. The initial pheromone concentration is a value artificially set by the staff of the UAV control center. Optionally, the initial pheromone concentration is 1.

[0040] It can be understood that identifying the negative marking space based on the multiple initial cells and the three-dimensional mapping space means: when it is confirmed that all the cells in the three-dimensional mapping space are transformed into multiple initial cells, the three-dimensional mapping space at this time is the negative marking space.

[0041] S5. Extract the j-th task coordinate group from the UAV task sequence, where the initial value of j is 1. Based on the current wind speed, current gust vector, current rainfall, pre-constructed optimization heuristic function, pre-constructed path coordinate group sequence set, and the negative marking space, perform an optimized ant colony simulation on the j-th task coordinate group to obtain an updated coordinate group sequence set, where the updated coordinate group sequence set includes: multiple optimal path sequences.

[0042] It should be understood that in the embodiments of the present invention, by improving the ant colony algorithm and considering the situation of multiple UAVs running simultaneously, the relationship between the positions and times of multiple UAVs that have completed path planning is recorded through a path coordinate group sequence set, preventing the paths of subsequent UAVs from overlapping with those of other UAVs during path planning, and preventing mutual interference among multiple UAVs during task execution. At the same time, by introducing an optimized heuristic function to improve the ant colony algorithm again, the influence of real-time environmental factors on path planning is considered, improving the accuracy and reliability of path planning for multiple UAVs through the ant colony algorithm.

[0043] It should be explained that the pre-constructed path coordinate group sequence set is an empty set, and its main function is to save the updated memory group sequences of multiple UAVs that have completed path planning subsequently. For example: when the first task coordinate group is extracted, the path coordinate group sequence set is an empty set, but subsequently, the path coordinate group sequence set is updated according to the optimal path sequence to obtain an updated coordinate group sequence set, and the updated coordinate group sequence set is used as the path coordinate group sequence set, returning to the step of extracting the j-th task coordinate group from the UAV task sequence, that is, when extracting the second task coordinate group again, at this time, the path coordinate group sequence set is no longer an empty set, and it saves the updated memory group sequence corresponding to the first task coordinate group. At this time, the interference feature analysis can be carried out according to the optimal path sequence in the path coordinate group sequence set, so as to prevent the path corresponding to the first task coordinate group from overlapping when planning the path for the second task coordinate group.

[0044] Specifically, optimizing the ant colony simulation for the j-th task coordinate group based on the current wind speed, current gust vector, current rainfall, pre-constructed optimized heuristic function, pre-constructed path coordinate group sequence set, and negative marking space to obtain an updated coordinate group sequence set includes: Identifying the starting cell in the negative marking space according to the starting coordinate in the j-th task coordinate group, and denoting the ending coordinate in the j-th task coordinate group as the termination coordinate; Generating multiple virtual ants, and performing the following operations on each of the multiple virtual ants: Placing the virtual ant into the starting cell to obtain the starting cell; Identifying multiple neighboring cells of the starting cell in the negative marking space; Performing the following operations on each of the multiple neighboring cells: Analyzing the transfer strategy of the neighboring cell and the starting cell according to the current wind speed, current gust vector, current rainfall, optimized heuristic function, termination coordinate, preset number of loops, pre-constructed memory coordinate group sequence, preset starting time, and path coordinate group sequence set to obtain the transfer comprehensive index and updated time; Aggregate the transfer comprehensive index and the update time respectively to obtain a plurality of transfer comprehensive indexes and a plurality of update times. Among them, the transfer comprehensive index and the update time correspond to adjacent cells one by one; Perform probability transfer on a plurality of adjacent cells based on the plurality of transfer comprehensive indexes and the plurality of update times to obtain transfer cells and landing times; Move the virtual ant to the transfer cell to obtain a landing cell, and identify the landing coordinates of the landing cell in the negative marking space; Combine the landing coordinates and the landing time to obtain a landing coordinate group; Use the landing coordinate group to update the memory coordinate group sequence to obtain an updated memory group sequence; Judge whether the landing coordinates are equal to the termination coordinates; If the landing coordinates are not equal to the termination coordinates, then use the landing cell as the starting cell, the updated memory group sequence as the memory coordinate group sequence, and the landing time as the starting time, and return to the step of identifying a plurality of adjacent cells of the starting cell in the negative marking space until the landing coordinates are equal to the termination coordinates; If the landing coordinates are equal to the termination coordinates, then use the updated memory group sequence as the target path sequence; Aggregate the target path sequences to obtain a plurality of target path sequences. Among them, the target path sequence includes: a plurality of target coordinate groups, and the target coordinate group includes: target coordinates and target times; Perform path analysis on the plurality of target path sequences to obtain path coincidence degrees and a plurality of total path times; Judge the path coincidence degree and compare the loop count with the preset loop threshold; If the path coincidence degree is less than the path threshold and the loop count is less than the loop threshold, then optimize the pheromone in the negative marking space according to the plurality of total path times and the plurality of target path sequences to obtain a path marking space, calculate the update count according to the loop count, use the path marking space as the negative marking space, and use the update count as the loop count, and return to the step of generating a plurality of virtual ants until the path coincidence degree is greater than or equal to the path threshold or the loop count is greater than or equal to the loop threshold; If the path coincidence degree is greater than or equal to the path threshold or the loop count is greater than or equal to the loop threshold, then confirm the optimal path sequence based on the plurality of total path times and the plurality of target path sequences, and update the path coordinate group sequence set according to the optimal path sequence to obtain an updated coordinate group sequence set.

[0045] It should be explained that the method of identifying the starting cell in the negative marking space according to the starting coordinates in the j-th task coordinate group is the same as the method of identifying the faulty cell in the three-dimensional mapping space based on the historical fault coordinates in the historical fault group, which will not be elaborated here. The adjacent cells refer to: among the multiple initial cells in the negative marking space, the initial cells adjacent to the faces, edges, and points of the starting cell. For example: each cell in the 3×3 cell area centered on the starting cell is adjacent to the faces, edges, and points of the starting cell, that is, one starting cell corresponds to a total of 26 adjacent cells.

[0046] It can be understood that the multiple virtual ants are path search individuals generated based on the ant colony algorithm, used to simulate path selection behavior in the negative marking space. By simulating the parallel search process of multiple virtual ants, multiple feasible paths from the starting coordinates to the ending coordinates in the negative marking space can be explored.

[0047] It should be explained that the landing coordinates are the coordinates corresponding to the position of the landing cell in the negative marking space in the space rectangular coordinate system.

[0048] It should be understood that the memory coordinate group sequence includes: multiple memory coordinate groups. The number of loops, the starting time, and the memory coordinate group sequence will all be continuously looped and updated when the step of returning the multiple adjacent cells of the starting cell identified in the negative marking space is executed. The initial values of the number of loops, the starting time, and the memory coordinate group sequence in the first loop are as follows: the preset number of loops is 1, the preset starting time is 0 seconds, and the pre-constructed memory coordinate group sequence is: {[(0,0,0),0], [(0.5,0.5,0.5),0]}.

[0049] Exemplarily, if the landing coordinates are (1.5, 1.5, 1.5) and the landing time is 2 seconds, then the landing coordinate group is: [(1.5, 1.5, 1.5), 2]. The update of the memory coordinate group sequence using the landing coordinate group means: putting the landing coordinate group into the memory coordinate group sequence as a memory coordinate group, and the sorting position of the landing coordinate group in the memory coordinate group sequence is the last one. In the first loop, since the memory coordinate group sequence is: {[(0, 0, 0), 0], [(0.5, 0.5, 0.5), 0]}, the updated memory group sequence is: {[(0, 0, 0), 0], [(0.5, 0.5, 0.5), 0], [(1.5, 1.5, 1.5), 2]}. If the termination coordinates are (12.5, 9.5, 17.5), and the landing coordinates are not equal to the termination coordinates, then taking the landing cell as the starting cell, the updated memory group sequence as the memory coordinate group sequence, and the landing time as the starting time, return to the step of identifying multiple adjacent cells of the starting cell in the negative marking space until the landing coordinates are equal to the termination coordinates. At this time, after multiple iterative updates, the updated memory group sequence is: {[(0, 0, 0), 0], [(0.5, 0.5, 0.5), 0], [(1.5, 1.5, 1.5), 2] …… [(12.5, 9.5, 17.5), 19]}, then taking the updated memory group sequence at this time as the target path sequence, and one virtual ant corresponds to one target path sequence, so multiple target path sequences are obtained by summarization.

[0050] It can be understood that the calculation of the update times according to the number of loops means: adding 1 to the value of the number of loops to obtain the update times. For example, if the number of loops is 1, then the update times is 2. The confirmation of the optimal path sequence based on multiple total path times and multiple target path sequences means: taking the target path sequence corresponding to the shortest total path time among the multiple target path sequences as the optimal path sequence. The update of the path coordinate group sequence set according to the optimal path sequence means: putting the optimal path sequence into the path coordinate group sequence set as the path coordinate group sequence. Preferably, the path threshold is 0.5 and the loop threshold is 500 times.

[0051] Specifically, the analysis of the transfer strategy for adjacent cells and the starting cell based on the current wind speed, current gust vector, current rainfall, optimized heuristic function, termination coordinates, preset number of loops, pre - constructed memory coordinate group sequence, preset starting time, and path coordinate group sequence set to obtain the transfer comprehensive index and update time includes: Identifying the adjacent coordinates and starting coordinates of adjacent cells and the starting cell in the negative marking space respectively; Calculating the distance to the far - away according to the adjacent coordinates and the termination coordinates, and the calculation formula is as follows: Among them, is the far distance, , and are respectively the abscissa, ordinate and vertical coordinate in the termination coordinates, , and are respectively the abscissa, ordinate and vertical coordinate in the adjacent coordinates; Obtain the near distance based on the adjacent coordinates and the starting coordinates; Calculate the movement time according to the preset resolution conversion rate, near distance and preset average speed. The calculation formula is as follows: Among them, is the movement time, is the near distance, is the resolution conversion rate, is the average speed; Calculate the update time according to the movement time and the starting time. Among them, the update time is the sum of the movement time and the starting time; Judge whether the adjacent cell is the obstacle cell. If the adjacent cell is the obstacle cell, then use the preset zeroing probability as the transfer comprehensive index; Otherwise, confirm the movement vector based on the adjacent coordinates and the starting coordinates. Among them, the movement vector is as follows: Among them, is the movement vector, , and are respectively the abscissa, ordinate and vertical coordinate in the starting coordinates; Confirm the last coordinate group in the memory coordinate group sequence. Among them, the last coordinate group is the last memory coordinate group in the memory coordinate group sequence; Confirm the previous coordinate group in the memory coordinate group sequence based on the last coordinate group. Among them, the last coordinate group is adjacent to the previous coordinate group and lags behind the previous coordinate group in the memory coordinate group sequence; Extract the previous coordinates from the previous coordinate group, extract the last coordinates from the last coordinate group, obtain the memory vector based on the previous coordinates and the last coordinates, and calculate the corner energy consumption index according to the memory vector and the movement vector. The calculation formula is as follows: Among them, is the corner energy consumption index, is the memory vector, is the modulus of the movement vector, is the modulus of the memory vector, is the arccosine function, is the preset unit energy consumption value; Calculate the environmental impact index according to the movement vector, current wind speed, current gust vector and current rainfall. The calculation formula is as follows: where, is the environmental impact index, and are the current rainfall and current wind speed respectively, and are the current gust vector and the preset ascending vector respectively, is the movement vector, is the modulus of the movement vector, and are the preset ascending resistance coefficient and the preset wind speed resistance coefficient respectively, and are the modulus of the ascending vector and the modulus of the current gust vector respectively; Identify the pheromone concentration of adjacent cells; Conduct interference feature analysis on the sequence set of path coordinate groups based on the update time and adjacent coordinates to obtain the mutual interference index; Substitute the number of loops, adjacent pheromone concentration, near distance, far distance, mutual interference index, turning energy consumption index and environmental impact index into the optimization heuristic function to obtain the transfer comprehensive index.

[0052] It should be explained that the adjacent coordinates are the coordinates corresponding to the position of the adjacent cell in the negative marking space in the space rectangular coordinate system. The starting point coordinates are the coordinates corresponding to the position of the starting point cell in the negative marking space in the space rectangular coordinate system.

[0053] In the embodiments of the present invention, since the space rectangular coordinate system includes: the x-axis, the y-axis and the z-axis, the horizontal axis, the vertical axis and the vertical axis respectively correspond to the x-axis, the y-axis and the z-axis, and the abscissa, the ordinate and the vertical coordinate respectively correspond to the coordinates on the x-axis, the coordinates on the y-axis and the coordinates on the z-axis in the space rectangular coordinate system.

[0054] It is understandable that the method for obtaining the near distance based on the adjacent coordinates and the starting coordinates is the same as the method for calculating the far distance according to the adjacent coordinates and the ending coordinates, which will not be elaborated here. The preset average speed refers to the average speed of the drone during straight flight when operating at the rated power. The preset unit energy consumption value refers to the average electrical energy consumed when the flight direction of the drone changes by one degree during operation at the rated power. The preset upward resistance coefficient refers to the value of the electrical energy consumed when the drone rises linearly by 1 meter during operation at the rated power. The preset wind speed resistance coefficient refers to the value of the electrical energy consumed when the drone flies linearly against the wind direction by 1 meter during operation at the rated power and with a wind speed of 1 m / s. And the average speed, unit energy consumption value, upward resistance coefficient, and wind speed resistance coefficient are all measured by the staff of the drone control center through flight tests on the drone. The preset zeroing probability is 0%. The preset upward vector is (0, 0, 1).

[0055] It should be explained that the advance coordinate refers to the coordinate in the advance coordinate group, and the last coordinate refers to the coordinate in the last coordinate group. Exemplarily, if the advance coordinate group is [(0.5, 0.5, 0.5), 0], then the advance coordinate is (0.5, 0.5, 0.5); if the last coordinate group is [(1.5, 1.5, 1.5), 2], then the last coordinate is (1.5, 1.5, 1.5).

[0056] It is understandable that the method for obtaining the memory vector based on the advance coordinate and the last coordinate is the same as the method for confirming the movement vector based on the adjacent coordinates and the starting coordinates, which will not be elaborated here. The turning energy consumption index reflects the electrical energy consumed due to direction changes when the drone moves in reality according to the movement path of the virtual ant in the negatively marked space. The larger the turning energy consumption index, the more electrical energy is consumed due to direction changes when the drone moves in reality according to the movement path of the virtual ant in the negatively marked space. The environmental impact index reflects the electrical energy consumed due to the resistance of wind and rain in the environment when the drone moves in reality according to the movement path of the virtual ant in the negatively marked space. The smaller the environmental impact index, the less electrical energy is consumed due to the resistance of wind and rain in the environment when the drone moves in reality according to the movement path of the virtual ant in the negatively marked space.

[0057] It should be understood that since multiple cells in the negatively marked space have been marked using pheromone concentrations before, the adjacent pheromone concentration for identifying adjacent cells is: taking the pheromone concentration corresponding to the adjacent cell as the adjacent pheromone concentration. The transfer comprehensive index is the value output by the optimization heuristic function after substituting the number of cycles, adjacent pheromone concentration, near distance, far distance, mutual interference index, turning energy consumption index, and environmental impact index into the optimization heuristic function.

[0058] Specifically, the interference feature analysis of the path coordinate group sequence set based on the update time and adjacent coordinates to obtain the mutual interference index includes: Determine whether the path coordinate group sequence set is an empty set. If the path coordinate group sequence set is an empty set, use the preset initial interference index as the mutual interference index; otherwise, perform the following operations on each path coordinate group sequence in the path coordinate group sequence set: Identify the close coordinate group in the path coordinate group sequence based on the update time; Extract the close coordinates and close time from the close coordinate group; Calculate the mutual interference factor according to the update time, adjacent coordinates, close coordinates, and close time. The calculation formula is as follows: Wherein, is the mutual interference factor, and are the update time and the close time respectively, , and are the abscissa, ordinate, and vertical coordinate in the close coordinates respectively, is the hyperbolic tangent function; Sum up the mutual interference factors to obtain multiple mutual interference factors, and calculate the mutual interference index according to the multiple mutual interference factors. Among them, the mutual interference index is the sum of the multiple mutual interference factors.

[0059] It should be explained that the initial interference index is 0.

[0060] Exemplarily, when the path coordinate group sequence set is not an empty set, it indicates that during the loop process, the optimal path sequence has been placed into the path coordinate group sequence set as a path coordinate group sequence. The optimal path sequence comes from multiple target path sequences, and the target path sequences include: multiple target coordinate groups. That is, the identification of the close coordinate group in the path coordinate group sequence based on the update time means: taking the target coordinate group corresponding to the target time closest to the update time among the multiple target coordinate groups in the path coordinate group sequence as the close coordinate group. The close coordinates are the target coordinates in the close coordinate group, and the close time is the target time in the close coordinate group. For example: the path coordinate group sequence is: {[(0,0,0),0], [(0.5,0.5,0.5),0], [(1.5,1.5,1.5),2], [(1.5,2.5,2.5),2.7]... [(12.5,9.5,17.5),19]}. If the update time is 2.1 seconds, then the close coordinate group is: [(1.5,1.5,1.5),2], the close coordinates are (1.5,1.5,1.5), and the close time is 2 seconds.

[0061] It should be understood that the mutual interference factor reflects the relative proximity between the UAV and other UAVs when the UAV moves in reality according to the movement path of the virtual ant in the negative marked space. The larger the mutual interference factor, the greater the relative proximity between the UAV and other UAVs when the UAV moves in reality according to the movement path of the virtual ant in the negative marked space, that is, the closer the distance to other UAVs. The mutual interference index is used to evaluate the interference risk caused by the overlap of the paths of the UAV and other UAVs during the mission execution.

[0062] Specifically, the optimization heuristic function is as follows: Wherein, is the optimization heuristic function, is the corner energy consumption index, is the mutual interference index, is the concentration of adjacent pheromone, is the number of cycles, is the cycle threshold, is the far distance, is the near distance.

[0063] It can be understood that the transfer comprehensive index reflects the priority of the virtual ant moving from the starting cell to the adjacent cell corresponding to the transfer comprehensive index. The larger the transfer comprehensive index, the higher the priority of the virtual ant moving from the starting cell to the adjacent cell corresponding to the transfer comprehensive index.

[0064] It should be understood that in the embodiment of the present invention, by introducing the number of cycles into the optimization heuristic function, when the number of cycles is too small, the near distance, far distance, mutual interference index, corner energy consumption index and environmental impact index are used as the main influencing factors to prevent the multiple paths generated by multiple virtual ants from overlapping prematurely under the action of pheromone and falling into local optimum. When the number of cycles is too large, the concentration of adjacent pheromone is used as the main influencing factor, so as to promote the multiple paths generated by multiple virtual ants to converge as soon as possible and improve the planning speed of the optimal path.

[0065] Specifically, the probability transfer of multiple adjacent cells based on multiple transfer comprehensive indexes and multiple update times to obtain the transfer cell and the landing time includes: Perform the following operations on each of the multiple adjacent cells: Calculate the transfer probability according to the transfer comprehensive index corresponding to the adjacent cell. The calculation formula is as follows: Wherein, is the transfer probability, is the transfer comprehensive index corresponding to adjacent cells is the transfer comprehensive index corresponding to the th adjacent cell among multiple adjacent cells is the number of adjacent cells among multiple adjacent cells; Perform probability selection according to the transfer probability corresponding to each adjacent cell among multiple adjacent cells to obtain a transfer cell; Use the update time corresponding to the transfer cell among multiple update times as the landing time.

[0066] It should be understood that the performing probability selection according to the transfer probability corresponding to each adjacent cell among multiple adjacent cells to obtain a transfer cell means: using the roulette method to randomly select an adjacent cell from multiple adjacent cells according to the transfer probability corresponding to each adjacent cell among multiple adjacent cells. The roulette method is a random selection mechanism based on probability distribution commonly used in the ant colony algorithm. By simulating the process of the roulette pointer falling in a certain area, the probability of each candidate being selected is proportional to its weight (here the transfer probability).

[0067] Specifically, the parsing the multiple target path sequences to obtain the path overlap degree and the total time of multiple paths includes: Confirm the number of paths of multiple target path sequences; Perform the following operations on each target path sequence among multiple target path sequences: Extract the ath target coordinate group from the target path sequence, where the initial value of a is 1; Extract the ath coordinate from the ath target coordinate group, where the ath coordinate is the target coordinate in the ath target coordinate group; Summarize the ath coordinates to obtain multiple ath coordinates, and extract multiple reference abscissas, multiple reference ordinates and multiple reference vertical coordinates from the multiple ath coordinates; Calculate the abscissa variance according to multiple reference abscissas, where the abscissa variance is the variance of multiple reference abscissas; Obtain the ordinate variance and the vertical coordinate variance respectively based on multiple reference ordinates and multiple reference vertical coordinates; Calculate the average coordinate variance according to the abscissa variance, the ordinate variance and the vertical coordinate variance, where the average coordinate variance is the average of the abscissa variance, the ordinate variance and the vertical coordinate variance; Let A = a + 1, use A as a, and return to the step of confirming the number of paths of multiple target path sequences until A = M, where M is the number of paths; Summarize the variances of the average coordinates to obtain multiple variances of the average coordinates, and calculate the path coincidence degree based on the multiple variances of the average coordinates. The calculation formula is as follows: Among them, is the path coincidence degree, is the th variance of the average coordinates among the multiple variances of the average coordinates, and m is the number of variances of the average coordinates among the multiple variances of the average coordinates; Perform the following operations on each of the multiple target path sequences: Extract multiple target times from the multiple target coordinate groups in the target path sequence; Calculate the total path time based on the multiple target times, where the total path time is the sum of the multiple target times; Summarize the total path times to obtain multiple total path times.

[0068] It should be explained that the number of paths is the number of target path sequences in the multiple target path sequences. The reference abscissa, reference ordinate, and reference vertical coordinate are the abscissa, ordinate, and vertical coordinate in the a-th coordinate respectively.

[0069] It can be understood that the method of obtaining the variance of the ordinate based on multiple reference ordinates and the method of obtaining the variance of the vertical coordinate based on multiple reference vertical coordinates are both the same as the method of calculating the variance of the abscissa based on multiple reference abscissas, and will not be elaborated here.

[0070] Specifically, the method of optimizing the pheromone in the negative marking space based on the multiple total path times and the multiple target path sequences to obtain the path marking space includes: Extract the target path sequences from the multiple target path sequences in sequence, and perform the following operations on the extracted target path sequences: Calculate the target pheromone increment based on the initial pheromone concentration and the total path time corresponding to the target path sequence in the multiple total path times. The calculation formula is as follows: Among them, is the target pheromone increment, is the total path time, is the preset reference total time; Extract multiple target coordinates from the multiple target coordinate groups in the target path sequence; Perform the following operations on each of the multiple target coordinates: Identify the target cell based on the target coordinate in the negative marking space; Identify the target pheromone concentration of the target cell, and calculate the replacement pheromone concentration according to the target pheromone concentration and the target pheromone increment. The calculation formula is as follows: Among them, is the replacement pheromone concentration, is the target pheromone concentration, is the preset replacement coefficient; Update the pheromone of the target cell based on the replacement pheromone concentration to obtain a supplementary cell; Summarize the supplementary cells to obtain multiple supplementary cells; Update the negative marking space based on the multiple supplementary cells to obtain a supplementary three-dimensional space; Take the supplementary three-dimensional space as the negative marking space, and return to the step of sequentially extracting the target path sequences from the multiple target path sequences until all the multiple target path sequences are extracted, and take the supplementary three-dimensional space as the path marking space.

[0071] It should be explained that the reference total time is set by the staff of the UAV control center according to the historical operation records of the UAV. Optionally, the average value of all the path total times recorded by the UAV in history is used as the reference total time.

[0072] It should be understood that extracting multiple target coordinates from multiple target coordinate groups in the target path sequence means: extracting the target coordinates in each target coordinate group in the multiple target coordinate groups and summarizing them to obtain multiple target coordinates. Identifying the target cell based on the target coordinates in the negative marking space means: taking the initial cell with the coordinates of the target coordinates in the negative marking space as the target cell. The method for identifying the target pheromone concentration of the target cell is the same as the method for identifying the adjacent pheromone concentration of the adjacent cell, which will not be elaborated here. The replacement coefficient is a value artificially set by the staff of the UAV control center. Preferably, the replacement coefficient is 0.2.

[0073] It can be understood that since the target cell has been previously marked with the target pheromone concentration, updating the pheromone of the target cell based on the replacement pheromone concentration means: erasing the original target pheromone concentration on the target cell and using the replacement pheromone concentration to re-mark the target cell. Updating the negative marking space based on the multiple supplementary cells to obtain a supplementary three-dimensional space means: sequentially extracting the supplementary cells from the multiple supplementary cells, and using the extracted supplementary cells to replace the initial cells in the negative marking space with the same coordinates as the supplementary cells until all the multiple supplementary cells are extracted, and taking the negative marking space replaced by the multiple supplementary cells as the supplementary three-dimensional space.

[0074] S6. Use the updated coordinate group sequence set as the path coordinate group sequence set. Let J = j + 1, use J as j, and return the step of extracting the j-th task coordinate group from the UAV task sequence until j = K. Generate multiple optimal paths using the updated coordinate group sequence set, where each optimal path corresponds to a task coordinate group one by one.

[0075] Specifically, the generating of multiple optimal paths using the updated coordinate group sequence set includes: Perform the following operations on each optimal path sequence in the updated coordinate group sequence set: Obtain the target coordinate sequence using the optimal path sequence; Generate an optimal path using the target coordinate sequence; Summarize the optimal paths to obtain multiple optimal paths.

[0076] It should be explained that obtaining the target coordinate sequence using the optimal path sequence means: extracting multiple target coordinates from multiple target coordinate groups in the optimal path sequence, and sorting the multiple target coordinates in the order of the multiple target coordinate groups in the optimal path sequence to obtain the target coordinate sequence. Generating an optimal path using the target coordinate sequence means: using the cubic spline interpolation method to fit the multiple target coordinates in the target coordinate sequence in order into a continuous and smooth three-dimensional path curve, and the three-dimensional path curve is the optimal path. And the technology of using the cubic spline interpolation method to fit the multiple target coordinates in the target coordinate sequence in order into a continuous and smooth three-dimensional path curve is a prior art and will not be elaborated here.

[0077] Exemplarily, when j = K, that is, the path planning for K task coordinate groups is completed. Therefore, at this time, multiple optimal paths can be generated using the updated coordinate group sequence set, and multiple UAVs can move along the corresponding paths in reality according to their respective optimal paths.

[0078] S7. Complete the multi-UAV navigation path planning based on multiple optimal paths.

[0079] To solve the problems described in the background art, the present invention obtains a three-dimensional mapping space. The shape of the three-dimensional mapping space is a cube, and the three-dimensional mapping space includes: a space rectangular coordinate system and multiple cells. The shape of each cell is a cube. The unit length of the space rectangular coordinate system is the side length of the cell. Each of the multiple cells has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system. The multiple cells are composed of multiple blank cells and multiple obstacle cells. It can be seen that in the embodiment of the present invention, the terrain features and spatial structure of the target task area in reality are mapped into a three-dimensional mapping space, so as to convert the real spatial environment information into a mathematical model that can be processed by a computer, providing a computable spatial structure basis for subsequent path planning. Furthermore, the current wind speed, the current gust vector, the current rainfall amount, and the UAV task sequence are determined. The UAV task sequence includes: K task coordinate groups. Each task coordinate group includes: a starting coordinate and an ending coordinate. It can be seen that in the embodiment of the present invention, by obtaining the current wind speed, the current gust vector, and the current rainfall amount, real-time environment parameters are provided for subsequent path planning, enhancing the reliability and safety of path planning. At the same time, by obtaining the UAV task sequence, it is convenient to perform path planning in sequence according to the priority of the tasks in the UAV task sequence. Multiple historical fault groups are obtained. Each historical fault group includes: a historical fault coordinate and a historical fault count. Based on the preset initial pheromone concentration and multiple historical fault groups, negative pheromone marking is performed on the three-dimensional mapping space to obtain a negatively marked space. It can be seen that in the embodiment of the present invention, by introducing historical fault data and using the historical fault data to perform negative pheromone marking on the three-dimensional mapping space, the ant colony algorithm execution process automatically avoids high-risk areas, improving the reliability and safety of path planning. The j-th task coordinate group is extracted from the UAV task sequence, where the initial value of j is 1. Based on the current wind speed, the current gust vector, the current rainfall amount, a pre-constructed optimization heuristic function, a pre-constructed path coordinate group sequence set, and the negatively marked space, an optimized ant colony simulation is performed on the j-th task coordinate group to obtain an updated coordinate group sequence set. The updated coordinate group sequence set includes: multiple optimal path sequences. It can be seen that in the embodiment of the present invention, through an improved ant colony algorithm, the search for the optimal path is realized on the basis of considering environmental factors and the mutual interference factors of multiple UAVs, improving the accuracy and reliability of path planning. The updated coordinate group sequence set is used as the path coordinate group sequence set. Let J = j + 1, and let J be j, and return to the step of extracting the j-th task coordinate group from the UAV task sequence until j = K. Multiple optimal paths are generated using the updated coordinate group sequence set. The optimal paths correspond one-to-one with the task coordinate groups. Based on the multiple optimal paths, the multi-UAV navigation path planning is completed. It can be seen that in the embodiment of the present invention, the task coordinate groups are sequentially extracted from the UAV task sequence through a loop process and the optimal paths are generated one by one, avoiding the situation of overlapping or interference of the multi-UAV paths, and enhancing the safety when multiple UAVs perform tasks simultaneously.Therefore, the present invention can improve the accuracy and reliability of path planning and enhance the safety when multiple drones perform tasks simultaneously.

[0080] As Figure 2 shown, it is a functional module diagram of a multi - drone navigation path planning system based on multi - task parameters provided by an embodiment of the present invention.

[0081] The multi - drone navigation path planning system 100 based on multi - task parameters of the present invention can be installed in the electronic device 1. According to the implemented functions, the multi - drone navigation path planning system 100 based on multi - task parameters can include a mapping space construction module 101, an environmental data marking module 102, an ant colony algorithm optimization module 103, and an optimal path generation module 104. The modules of the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by the processor of the electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0082] The mapping space construction module 101 is used to obtain a three - dimensional mapping space. Among them, the shape of the three - dimensional mapping space is a cube, and the three - dimensional mapping space includes: a space rectangular coordinate system and a plurality of cells. Among them, the shape of the cell is a cube, the unit length of the space rectangular coordinate system is the side length of the cell, each cell in the plurality of cells has a unique corresponding three - dimensional coordinate in the space rectangular coordinate system, and the plurality of cells are composed of a plurality of blank cells and a plurality of obstacle cells; The environmental data marking module 102 is used to confirm the current wind speed, the current gust vector, the current rainfall, and the drone task sequence. Among them, the drone task sequence includes: K task coordinate groups, and the task coordinate group includes: a starting coordinate and an ending coordinate. Obtain a plurality of historical fault groups. Among them, the historical fault group includes: a historical fault coordinate and a historical fault number. Perform negative pheromone marking on the three - dimensional mapping space based on a preset initial pheromone concentration and a plurality of historical fault groups to obtain a negative - marked space; The ant colony algorithm optimization module 103 is used to extract the j - th task coordinate group from the drone task sequence, where the initial value of j is 1. Perform optimized ant colony simulation on the j - th task coordinate group based on the current wind speed, the current gust vector, the current rainfall, a pre - constructed optimization heuristic function, a pre - constructed path coordinate group sequence set, and the negative - marked space to obtain an updated coordinate group sequence set. Among them, the updated coordinate group sequence set includes: a plurality of optimal path sequences; The optimal path generation module 104 is configured to use the updated coordinate group sequence set as the path coordinate group sequence set, let J = j + 1, use J as j, and return the step of extracting the j-th task coordinate group from the UAV task sequence until j = K. Multiple optimal paths are generated using the updated coordinate group sequence set, where the optimal paths correspond one-to-one with the task coordinate groups, and the multi-UAV navigation path planning is completed based on the multiple optimal paths.

[0083] Specifically, each module in the multi-UAV navigation path planning system 100 based on multi-task parameters in the embodiments of the present invention uses the same technical means as the Figure 1 multi-UAV navigation path planning method based on multi-task parameters described above and can produce the same technical effects, which will not be elaborated here.

[0084] As Figure 3 shown, it is a schematic structural diagram of an electronic device 1 for implementing the multi-UAV navigation path planning method based on multi-task parameters provided by an embodiment of the present invention.

[0085] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a multi-UAV navigation path planning method program based on multi-task parameters.

[0086] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and the external storage device. The memory 11 can not only be used to store application software installed in the electronic device 1 and various types of data, such as the code of the multi-UAV navigation path planning method program, but also be used to temporarily store data that has been output or will be output.

[0087] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting various components of the entire electronic device through various interfaces and circuits, and by running or executing programs or modules stored in the memory 11 (such as the multi-UAV navigation path planning method program based on multi-task parameters, etc.), and calling the data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0088] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is set to enable connection communication between the memory 11 and at least one processor 10, etc.

[0089] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that Figure 3 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component arrangement.

[0090] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0091] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device 1 and other electronic devices.

[0092] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, and is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0093] The multi-UAV navigation path planning method program based on multi-task parameters stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Obtain a three-dimensional mapping space, where the shape of the three-dimensional mapping space is a cube, and the three-dimensional mapping space includes: a spatial rectangular coordinate system and multiple cells, where the shape of the cell is a cube, the unit length of the spatial rectangular coordinate system is the side length of the cell, each cell in the multiple cells has a unique corresponding three-dimensional coordinate in the spatial rectangular coordinate system, and the multiple cells are composed of multiple blank cells and multiple obstacle cells; Confirm the current wind speed, the current gust vector, the current rainfall amount, and the UAV task sequence, where the UAV task sequence includes: K task coordinate groups, and the task coordinate group includes: a starting coordinate and an ending coordinate; Obtain multiple historical fault groups, where the historical fault group includes: historical fault coordinates and historical fault times; Perform negative pheromone marking on the three-dimensional mapping space based on a preset initial pheromone concentration and multiple historical fault groups to obtain a negatively marked space; Extract the jth task coordinate group from the UAV task sequence, where the initial value of j is 1; Perform an optimized ant colony simulation on the jth task coordinate group based on the current wind speed, the current gust vector, the current rainfall amount, a pre-constructed optimization heuristic function, a pre-constructed path coordinate group sequence set, and the negatively marked space to obtain an updated coordinate group sequence set, where the updated coordinate group sequence set includes: multiple optimal path sequences; Take the updated coordinate group sequence set as the path coordinate group sequence set, let J = j + 1, take J as j, and return to the step of extracting the jth task coordinate group from the UAV task sequence until j = K, and generate multiple optimal paths by using the updated coordinate group sequence set, where the optimal paths correspond to the task coordinate groups one by one; Complete the multi-UAV navigation path planning based on multiple optimal paths.

[0094] Specifically, for the specific implementation method of the above instructions by the processor 10, reference may be made to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0095] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0096] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by the processor of the electronic device, it can implement: Obtain a three-dimensional mapping space, where the shape of the three-dimensional mapping space is a cube, and the three-dimensional mapping space includes: a space rectangular coordinate system and a plurality of cells, where the shape of the cell is a cube, the unit length of the space rectangular coordinate system is the side length of the cell, each cell in the plurality of cells has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system, and the plurality of cells are composed of a plurality of blank cells and a plurality of obstacle cells; Confirm the current wind speed, current gust vector, current rainfall, and the UAV mission sequence, where the UAV mission sequence includes: K mission coordinate groups, and the mission coordinate group includes: a starting coordinate and an ending coordinate; Obtain a plurality of historical fault groups, where the historical fault group includes: historical fault coordinates and historical fault times; Perform negative pheromone marking on the three-dimensional mapping space based on the preset initial pheromone concentration and the plurality of historical fault groups to obtain a negative marked space; Extract the j-th mission coordinate group from the UAV mission sequence, where the initial value of j is 1; Perform an optimized ant colony simulation on the j-th mission coordinate group based on the current wind speed, current gust vector, current rainfall, pre-constructed optimization heuristic function, pre-constructed path coordinate group sequence set, and negative marked space to obtain an updated coordinate group sequence set, where the updated coordinate group sequence set includes: a plurality of optimal path sequences; Take the updated coordinate group sequence set as the path coordinate group sequence set, let J = j + 1, take J as j, and return the step of extracting the j-th task coordinate group from the UAV task sequence until j = K. Generate multiple optimal paths using the updated coordinate group sequence set, where the optimal paths correspond to the task coordinate groups one by one; Complete the multi-UAV navigation path planning based on multiple optimal paths.

[0097] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only illustrative, and there may be other partitioning methods in actual implementation.

[0098] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0099] In addition, each functional module in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional modules.

[0100] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A multi - UAV navigation path planning method based on multi - task parameters, characterized in that The method includes: Obtain a three-dimensional mapping space, where the shape of the three-dimensional mapping space is a cube, and the three-dimensional mapping space includes: a space rectangular coordinate system and a plurality of cells, where the shape of the cells is a cube, the unit length of the space rectangular coordinate system is the side length of the cells, each of the plurality of cells has a unique corresponding three-dimensional coordinate in the space rectangular coordinate system, and the plurality of cells consists of a plurality of blank cells and a plurality of obstacle cells; Confirm the current wind speed, the current gust vector, the current rainfall amount, and the UAV mission sequence, where the UAV mission sequence includes: K mission coordinate groups, and the mission coordinate group includes: a starting coordinate and an ending coordinate; Obtain a plurality of historical failure groups, where the historical failure group includes: historical failure coordinates and the number of historical failures; Perform negative pheromone marking on the three-dimensional mapping space based on a preset initial pheromone concentration and a plurality of historical failure groups to obtain a negatively marked space; Extract the j-th mission coordinate group from the UAV mission sequence, where the initial value of j is 1; Perform an optimized ant colony simulation on the j-th mission coordinate group based on the current wind speed, the current gust vector, the current rainfall amount, a pre-constructed optimization heuristic function, a pre-constructed sequence set of path coordinate groups, and the negatively marked space to obtain an updated sequence set of coordinate groups, where the updated sequence set of coordinate groups includes: a plurality of optimal path sequences; Take the updated sequence set of coordinate groups as the sequence set of path coordinate groups, let J = j + 1, take J as j, and return to the step of extracting the j-th mission coordinate group from the UAV mission sequence until j = K, and generate a plurality of optimal paths by using the updated sequence set of coordinate groups, where the optimal paths correspond to the mission coordinate groups one by one; Complete the multi-UAV navigation path planning based on the plurality of optimal paths.

2. The multi - UAV navigation path planning method based on multi - task parameters according to claim 1, wherein, The performing negative pheromone marking on the three-dimensional mapping space based on a preset initial pheromone concentration and a plurality of historical failure groups to obtain a negatively marked space includes: Perform the following operations on each of the plurality of historical failure groups: Confirm a failed cell in the three-dimensional mapping space based on the historical failure coordinates in the historical failure group; Confirm a plurality of dangerous cells in the three-dimensional mapping space based on the failed cell, where the dangerous cells are adjacent to the failed cell in the three-dimensional mapping space; Calculate the dangerous pheromone concentration based on the initial pheromone concentration and the number of historical failures in the historical failure group; Calculate the obstacle pheromone concentration according to the dangerous pheromone concentration, where the obstacle pheromone concentration is half of the dangerous pheromone concentration; Mark the failed cell based on the obstacle pheromone concentration to obtain an obstacle marked cell, and mark each of the plurality of dangerous cells based on the dangerous pheromone concentration to obtain a plurality of dangerous marked cells; Summarize the obstacle marked cell and the plurality of dangerous marked cells to obtain a plurality of repulsive cells, where the repulsive cells are obstacle marked cells or dangerous marked cells; Remove the plurality of repulsive cells from the plurality of cells in the three-dimensional mapping space to obtain a plurality of basic cells; Mark each of the multiple basic cells based on the initial pheromone concentration to obtain multiple initially marked cells; Summarize the multiple repulsive cells and the multiple initially marked cells to obtain multiple initial cells, where the initial cells are either repulsive cells or initially marked cells; Identify the negative marking space based on the multiple initial cells and the three-dimensional mapping space.

3. The multi-UAV navigation path planning method based on multi-task parameters according to claim 2, wherein The step of performing an optimized ant colony simulation on the j-th task coordinate group based on the current wind speed, the current gust vector, the current rainfall, the pre-constructed optimized heuristic function, the pre-constructed sequence set of path coordinate groups, and the negative marking space to obtain an updated sequence set of coordinate groups includes: Identify the starting cell in the negative marking space according to the starting coordinate in the j-th task coordinate group, and denote the ending coordinate in the j-th task coordinate group as the termination coordinate; Generate multiple virtual ants, and perform the following operations on each of the multiple virtual ants: Place the virtual ant into the starting cell to obtain the starting point cell; Identify the multiple neighboring cells of the starting point cell in the negative marking space; Perform the following operations on each of the multiple neighboring cells: Analyze the transfer strategy for the neighboring cell and the starting point cell according to the current wind speed, the current gust vector, the current rainfall, the optimized heuristic function, the termination coordinate, the preset number of loops, the pre-constructed sequence of memory coordinate groups, the preset starting time, and the sequence set of path coordinate groups to obtain the transfer comprehensive index and the update time; Summarize the transfer comprehensive index and the update time respectively to obtain multiple transfer comprehensive indexes and multiple update times, where the transfer comprehensive index and the update time correspond to the neighboring cells one by one; Perform probability transfer on the multiple neighboring cells based on the multiple transfer comprehensive indexes and the multiple update times to obtain the transfer cell and the landing time; Move the virtual ant to the transfer cell to obtain the landing cell, and identify the landing coordinate of the landing cell in the negative marking space; Combine the landing coordinate and the landing time to obtain the landing coordinate group; Update the sequence of memory coordinate groups using the landing coordinate group to obtain the updated sequence of memory groups; Judge whether the landing coordinate is equal to the termination coordinate; If the landing coordinate is not equal to the termination coordinate, then use the landing cell as the starting point cell, use the updated sequence of memory groups as the sequence of memory coordinate groups, use the landing time as the starting time, and return to the step of identifying the multiple neighboring cells of the starting point cell in the negative marking space until the landing coordinate is equal to the termination coordinate; If the landing coordinate is equal to the termination coordinate, then use the updated sequence of memory groups as the target path sequence; Summarize the target path sequences to obtain multiple target path sequences, where the target path sequence includes: multiple target coordinate groups, and the target coordinate group includes: the target coordinate and the target time; Perform path analysis on the multiple target path sequences to obtain the path overlap degree and the multiple total path times; Judge the path overlap degree and compare the number of loops with the preset loop threshold; If the path overlap degree is less than the path threshold and the number of cycles is less than the cycle threshold, optimize the pheromone in the negative marking space according to the total time of multiple paths and multiple target path sequences to obtain the path marking space. Calculate the update times according to the number of cycles, use the path marking space as the negative marking space, use the update times as the number of cycles, and return to the step of generating multiple virtual ants until the path overlap degree is greater than or equal to the path threshold or the number of cycles is greater than or equal to the cycle threshold; If the path overlap degree is greater than or equal to the path threshold or the number of cycles is greater than or equal to the cycle threshold, confirm the optimal path sequence based on the total time of multiple paths and multiple target path sequences, and update the path coordinate group sequence set according to the optimal path sequence to obtain the updated coordinate group sequence set.

4. The multi-UAV navigation path planning method based on multi-task parameters according to claim 3, wherein, The analysis of the transfer strategy for neighboring cells and the starting cell according to the current wind speed, current gust vector, current rainfall, optimization heuristic function, termination coordinates, preset number of cycles, pre-constructed memory coordinate group sequence, preset starting time, and path coordinate group sequence set to obtain the transfer comprehensive index and the update time includes: Identify the neighboring coordinates and the starting coordinates of the neighboring cells and the starting cell in the negative marking space respectively; Calculate the far distance according to the neighboring coordinates and the termination coordinates; Obtain the near distance based on the neighboring coordinates and the starting coordinates; Calculate the movement time according to the preset resolution conversion rate, near distance, and preset average speed; Calculate the update time according to the movement time and the starting time, where the update time is the sum of the movement time and the starting time; Judge whether the neighboring cell is the obstacle cell. If the neighboring cell is the obstacle cell, use the preset zeroing probability as the transfer comprehensive index; Otherwise, confirm the movement vector based on the neighboring coordinates and the starting coordinates; Confirm the last coordinate group in the memory coordinate group sequence, where the last coordinate group is the last memory coordinate group in the memory coordinate group sequence; Confirm the previous coordinate group in the memory coordinate group sequence based on the last coordinate group. The last coordinate group is adjacent to and lags behind the previous coordinate group in the memory coordinate group sequence; Extract the previous coordinate from the previous coordinate group, extract the last coordinate from the last coordinate group, obtain the memory vector based on the previous coordinate and the last coordinate, and calculate the corner energy consumption index according to the memory vector and the movement vector; Calculate the environmental impact index according to the movement vector, current wind speed, current gust vector, and current rainfall. The calculation formula is as follows: Among them, is the environmental impact index, and are the current rainfall and the current wind speed respectively, and are the current gust vector and the preset ascending vector respectively, is the movement vector, is the modulus of the movement vector, and are the preset ascending resistance coefficient and the preset wind speed resistance coefficient respectively, and are the modulus of the ascending vector and the modulus of the current gust vector respectively; Identify the neighboring pheromone concentration of the neighboring cell; Conduct interference feature analysis on the path coordinate group sequence set based on the update time and the neighboring coordinates to obtain the mutual interference index; Substitute the number of cycles, neighboring pheromone concentration, near distance, far distance, mutual interference index, corner energy consumption index, and environmental impact index into the optimization heuristic function to obtain the transfer comprehensive index.

5. The multi-UAV navigation path planning method based on multi-task parameters according to claim 4, wherein The interference feature analysis of the path coordinate group sequence set based on the update time and the neighboring coordinates to obtain the mutual interference index includes: Determine whether the set of path coordinate group sequences is an empty set. If the set of path coordinate group sequences is an empty set, use the preset initial interference index as the mutual interference index. Otherwise, perform the following operations on each path coordinate group sequence in the set of path coordinate group sequences: Identify the close coordinate group in the path coordinate group sequence based on the update time; Extract the close coordinates and close time from the close coordinate group; Calculate the mutual interference factor according to the update time, neighboring coordinates, close coordinates, and close time; Summarize the mutual interference factors to obtain multiple mutual interference factors, and calculate the mutual interference index based on the multiple mutual interference factors. Among them, the mutual interference index is the sum of the multiple mutual interference factors.

6. The multi - UAV navigation path planning method based on multi - task parameters according to claim 5, characterized in that, The optimization heuristic function is as follows: Among them, is to optimize the heuristic function, is the corner energy dissipation index, is the mutual interference index, is the concentration of neighboring pheromones, is the number of cycles, is the cycle threshold, is the far distance, is the near distance.

7. The multi-UAV navigation path planning method based on multi-task parameters according to claim 6, characterized in that, Performing probability transfer on multiple neighboring cells based on multiple transfer comprehensive indices and multiple update times to obtain transfer cells and landing times, including: Perform the following operations on each of the multiple neighboring cells: Calculate the transfer probability according to the transfer comprehensive index corresponding to the neighboring cell; Perform probability selection according to the transfer probabilities corresponding to each of the multiple neighboring cells to obtain transfer cells; Use the update time corresponding to the transfer cell among the multiple update times as the landing time.

8. The multi-UAV navigation path planning method based on multi-task parameters according to claim 7, wherein, Performing path parsing on multiple target path sequences to obtain path coincidence degrees and multiple total path times, including: Confirm the number of paths of the multiple target path sequences; Perform the following operations on each target path sequence among the multiple target path sequences: Extract the a-th target coordinate group from the target path sequence, where the initial value of a is 1; Extract the a-th coordinate from the a-th target coordinate group, where the a-th coordinate is the target coordinate in the a-th target coordinate group; Summarize the a-th coordinates to obtain multiple a-th coordinates, and extract multiple reference abscissas, multiple reference ordinates, and multiple reference vertical coordinates from the multiple a-th coordinates; Calculate the abscissa variance according to the multiple reference abscissas, where the abscissa variance is the variance of the multiple reference abscissas; Obtain the ordinate variance and vertical coordinate variance based on the multiple reference ordinates and multiple reference vertical coordinates respectively; Calculate the average coordinate variance according to the abscissa variance, ordinate variance, and vertical coordinate variance, where the average coordinate variance is the average of the abscissa variance, ordinate variance, and vertical coordinate variance; Let A = a + 1, use A as a, and return to the step of confirming the number of paths of the multiple target path sequences until A = M, where M is the number of paths; Summarize the average coordinate variances to obtain multiple average coordinate variances, and calculate the path coincidence degree according to the multiple average coordinate variances; Perform the following operations on each target path sequence among the multiple target path sequences: Extract multiple target times from the multiple target coordinate groups in the target path sequence; Calculate the total path time according to the multiple target times, where the total path time is the sum of the multiple target times; Summarize the total path times to obtain multiple total path times.

9. The multi-UAV navigation path planning method based on multi-task parameters according to claim 8, characterized in that, Performing pheromone optimization on the negative marking space according to the multiple total path times and the multiple target path sequences to obtain the path marking space, including: Extract the target path sequences from multiple target path sequences in sequence, and perform the following operations on the extracted target path sequences: Calculate the target pheromone increment based on the initial pheromone concentration and the path total time corresponding to the target path sequence in the multiple path total times; Extract multiple target coordinates from multiple target coordinate groups in the target path sequence; Perform the following operations on each target coordinate in the multiple target coordinates: Identify the target cell based on the target coordinate in the negative marking space; Identify the target pheromone concentration of the target cell, and calculate the replacement pheromone concentration according to the target pheromone concentration and the target pheromone increment; Update the pheromone of the target cell based on the replacement pheromone concentration to obtain a supplementary cell; Summarize the supplementary cells to obtain multiple supplementary cells; Update the negative marking space based on the multiple supplementary cells to obtain a supplementary three-dimensional space; Use the supplementary three-dimensional space as the negative marking space, and return to the step of extracting the target path sequences from the multiple target path sequences in sequence until all the multiple target path sequences are extracted, and use the supplementary three-dimensional space as the path marking space.

10. A multi-UAV navigation path planning system based on multi-task parameters, characterized in that, The system includes: A mapping space construction module for obtaining a three-dimensional mapping space, where the shape of the three-dimensional mapping space is a cube, and the three-dimensional mapping space includes: a spatial rectangular coordinate system and multiple cells, where the shape of the cell is a cube, the unit length of the spatial rectangular coordinate system is the side length of the cell, each cell in the multiple cells has a unique corresponding three-dimensional coordinate in the spatial rectangular coordinate system, and the multiple cells are composed of multiple blank cells and multiple obstacle cells; An environmental data marking module for identifying the current wind speed, the current gust vector, the current rainfall, and the UAV mission sequence, where the UAV mission sequence includes: K mission coordinate groups, and the mission coordinate group includes: a starting coordinate and an ending coordinate, obtaining multiple historical failure groups, where the historical failure group includes: a historical failure coordinate and a historical failure number, and performing negative pheromone marking on the three-dimensional mapping space based on the preset initial pheromone concentration and the multiple historical failure groups to obtain a negative marking space; An ant colony algorithm optimization module for extracting the j-th mission coordinate group from the UAV mission sequence, where the initial value of j is 1, and performing an optimized ant colony simulation on the j-th mission coordinate group based on the current wind speed, the current gust vector, the current rainfall, a pre-constructed optimization heuristic function, a pre-constructed path coordinate group sequence set, and the negative marking space to obtain an updated coordinate group sequence set, where the updated coordinate group sequence set includes: multiple optimal path sequences; An optimal path generation module for using the updated coordinate group sequence set as the path coordinate group sequence set, setting J = j + 1, using J as j, and returning to the step of extracting the j-th mission coordinate group from the UAV mission sequence until j = K, generating multiple optimal paths using the updated coordinate group sequence set, where the optimal paths correspond to the mission coordinate groups one by one, and completing the multi-UAV navigation path planning based on the multiple optimal paths.

Images