Multi-unmanned aerial vehicle cooperative path planning and scheduling method and system

Abstract

The invention relates to a multi-unmanned aerial vehicle cooperative path planning and scheduling method and system. The method comprises the following steps: acquiring task requirements, and determining a plurality of task areas needing aerial survey, coverage requirements and unmanned aerial vehicle parking positions; constructing a coverage path with the minimum turning cost for each task area according to coverage requirements; calculating the flight path cost of the unmanned aerial vehicle according to the parking position and the coverage path of the unmanned aerial vehicle; and according to the flight path cost, planning an access area and an access sequence for each unmanned aerial vehicle by using a genetic algorithm, and generating an unmanned aerial vehicle flight path. According to the method, the task demand is acquired, the unmanned aerial vehicle observation coverage path with turning optimization is generated in the task area, and the optimized unmanned aerial vehicle scheduling scheme and flight path are generated by using the genetic algorithm based on the coverage path cost, so that the surveying and mapping demand can be met while the quality and quantity are guaranteed; the total flight distance is reduced to the maximum extent, the workload distribution among the unmanned aerial vehicles is balanced, and a data acquisition window for large-scale surveying and mapping is shortened.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicles, and in particular to a multi-unmanned aerial vehicle cooperative path planning and scheduling method and system. BACKGROUND

[0002] In the face of large-area remote sensing observation scenarios, due to the low efficiency and limited endurance of a single unmanned aerial vehicle, a multi-unmanned aerial vehicle cluster can simultaneously cover different areas through task segmentation and parallel operation, thereby greatly shortening the data acquisition time window of a large-area region. Although the multi-unmanned aerial vehicle system brings many advantages to remote sensing applications, how to build an efficient cooperative scheduling and flight path planning mechanism to fully exploit its potential is still a major challenge. In the complex scenarios of endurance limitation, unknown target area, or multiple regional takeoff and landing, unreasonable regional allocation, access order, and flight path design can significantly increase invalid flight and excessive turns, leading to increased energy consumption, shortened endurance, and delayed data acquisition, affecting decision-making timeliness.

[0003] In order to improve the deployment flexibility and continuous operation capability in remote sensing applications, the prior art has modified a ground vehicle into a mobile platform integrating unmanned aerial vehicle transportation, rapid deployment, launch and recovery, on-board data processing, and energy replenishment, which is a vehicle-mounted unmanned aerial vehicle system. The vehicle-mounted multi-unmanned aerial vehicle system is a ground vehicle transformed into a mobile platform integrating unmanned aerial vehicle transportation, rapid deployment, launch and recovery, data processing, and energy replenishment, which can solve the transportation, energy replenishment limitations, and computing bottlenecks faced by small and medium-sized unmanned aerial vehicles in field operations.

[0004] However, most existing vehicle-mounted unmanned aerial vehicle systems mainly support manual flight path planning for a single unmanned aerial vehicle, and are difficult to adapt to the complex needs of multi-unmanned aerial vehicle cooperative operation. Simply increasing the number of unmanned aerial vehicles will lead to uneven task loads and uneven completion times for each unmanned aerial vehicle if effective cooperative strategies are lacking, and the overall efficiency is limited by the "bottleneck effect".

[0005] Therefore, there is an urgent need to provide a cooperative path planning and scheduling scheme that can achieve high-quality coverage of the flight path, avoid excessive turns of the unmanned aerial vehicle, and flexibly achieve high-quality coverage and time efficiency according to the type of unmanned aerial vehicle. SUMMARY

[0006] The present application provides a multi-unmanned aerial vehicle cooperative path planning and scheduling method and system to overcome at least one of the above technical problems in the prior art.

[0007] To achieve the above-mentioned purpose, the embodiments of the present application adopt the following technical solutions: In a first aspect, the present application provides a multi-unmanned aerial vehicle cooperative path planning and scheduling method, comprising: Acquire task requirements, determine a plurality of task areas requiring aerial survey, coverage requirements and unmanned aerial vehicle parking positions, wherein each task area is independent of each other; According to the coverage requirements, construct a coverage path with minimum turning cost for each task area; According to the unmanned aerial vehicle parking positions and the coverage path, calculate a flight path cost of the unmanned aerial vehicle; According to the flight path cost, plan a region and sequence visited by each unmanned aerial vehicle using a genetic algorithm, and generate a flight trajectory of the unmanned aerial vehicle.

[0008] In a possible implementation manner of the first aspect, the constructing a coverage path with minimum turning cost for each task area according to the coverage requirements comprises: Discretize each task area into a primitive topology graph according to the coverage requirements; Perform linear programming on the primitive topology graph to obtain an end-point matching graph; Perform matching on the end-point matching graph using a Blossom V algorithm to obtain a matching result, project the matching result onto the primitive topology graph to obtain an initial coverage path; Optimize the initial coverage path using local mixed integer programming to obtain the coverage path with minimum turning cost.

[0009] In a possible implementation manner of the first aspect, the discretizing each task area into a primitive topology graph according to the coverage requirements comprises: Discretize each task area into a primitive topology graph using equilateral triangles, wherein a distance between adjacent nodes in the primitive topology graph matches the coverage requirements.

[0010] In a possible implementation manner of the first aspect, the performing linear programming on the primitive topology graph to obtain an end-point matching graph comprises: Introduce a ternary path variable , representing a frequency of occurrence at a path node , a skip variable , representing a value loss paid when a path node is skipped, and the loss value is Perform linear programming on the primitive topology graph using the following function to obtain a fractional solution; wherein, represents a vertex of the primitive topology graph, represents a coverage value of a path node, includes a Euclidean distance and a turning angle cost; convert the score into a plurality of atomic bands, each of the atomic bands representing a small piece of imaginary movement at one of the path nodes with one of the edge orientations; select the atomic bands with the best orientations in each of the path nodes as candidate atomic bands; construct corresponding end nodes for both ends of each of the candidate atomic bands, and establish matching edges between any two end nodes to obtain an end node matching graph.

[0011] In a possible implementation of the first aspect, the flight path cost of the UAV is calculated according to the UAV parking position and the coverage path, including: The load of the UAV is calculated according to the UAV parking position and the coverage path by the following formula: ; wherein, represents the number of UAVs, represents the endurance mileage of the UAV, represents the total length of the flight path required for completing the coverage observation in the task area, represents the Euclidean distance between two positions, represents the UAV parking position, represents the entry point, represents the exit point; The total path cost of the flight task is calculated by the following formula: ; wherein, represents the number of UAVs, represents the endurance mileage of the UAV; The load balance of the UAV is calculated by the following formula: ; The total path cost and the load balance are weighted by using a weighted summation mechanism to obtain the flight path cost.

[0012] In a possible implementation of the first aspect, the flight path cost of the UAV is calculated according to the UAV parking position and the coverage path, including: The task area is randomly assigned to each of the UAVs to obtain an initial population; The path connection scheme fitness of each population individual in the initial population is calculated according to the flight path cost; The population individuals are selected by using an NSGA-II framework according to the path connection scheme fitness to obtain parent population individuals; The parent population individuals are processed by using a multi-region path crossover operator with edge recombination to generate child population individuals; According to the adaptive hybrid variation mechanism, the offspring population individuals are subjected to variation processing to obtain variation offspring population individuals; The iteration is performed until a preset iteration number is reached, and the region and sequence visited by each UAV are obtained, and a UAV flight track is generated.

[0013] In a possible implementation manner of the first aspect, before the task region is randomly allocated to each UAV to obtain an initial population, the method further includes: The UAV is encoded by using double-chromosome encoding, where a first layer represents a task sequence, and a second layer represents a UAV number.

[0014] In a possible implementation manner of the first aspect, the parent population individuals are processed by using the multi-region path crossover operator based on edge recombination to generate offspring population individuals, including: Extracting a parent region and a parent region assigned to a UAV from the parent population individuals, and determining a set of task nodes that need to be visited by the UAV in the parent region and the parent region ; ; Constructing an adjacency list for each node in the set , adding all the edges constructed from the parent region and the parent region to the adjacency list, and recording the numbers of adjacent nodes in the parent region and the parent region , the distance of the edge, and a flag indicating whether the edge exists in both the parent region and the parent region ; Initializing an offspring region to an empty sequence, randomly selecting a starting node from the set , adding the starting node to the offspring population individual, and marking the starting node as visited, so that the current node ; Retrieving all the unvisited adjacent nodes of the current node curr from the adjacency list; If a candidate adjacent node exists, the candidate adjacent node is used as a next node ; If no candidate adjacent node exists, a node Randomly select an unvisited node as the next node. ; The next node Add the child region Mark as visited and update ; The retrieval process continues until the child region is reached. Length and the parent region The lengths are consistent, and the resulting child regions after intersection are obtained. ; offspring region Initialize to an empty sequence, then repeat the child region. The crossover step is used to obtain the crossover child region. ; The offspring region after all the drones are crossed and the child region Combine them to obtain offspring individuals.

[0015] In one possible implementation of the first aspect, the mutation processing of the offspring population individuals according to the adaptive hybrid mutation mechanism includes: According to the aforementioned adaptive hybrid mutation mechanism, with a probability of Select a combination of mutation operators The offspring population was subjected to mutation treatment; Wherein, the probability The probability is the current dynamic application probability of the combination of mutation operators. The dynamic adjustment method is as follows: Initialize an empty set of applied mutation operators. The combination of mutation operators Include Different mutation operators Each mutation operator Generate a probability ,if Then the mutation operator Add to the set of mutation operators The The mutation operator is The current dynamic application probability, the Initially, all the mutation operators mentioned above are used. The average value; With the set of mutation operators All of the aforementioned mutation operators The offspring population was subjected to mutation treatment; The improved score is calculated by the following formula : ; wherein, represents a minimum positive number, represents the path connection scheme fitness after mutation; represents the path connection scheme fitness before mutation; The improved score is averagely distributed to all the mutation operators in the set ; for each mutation operator , its contribution this time is recorded, if > 0, the success counter of each mutation operator is increased by 1 ; ; The average contribution of each mutation operator in the last time of application is calculated, and the new base probability of each mutation operator is calculated by the following average contribution calculation formula : ; The base probability is normalized to obtain a new application probability.

[0016] Compared with the prior art, the present application has at least the following beneficial effects: The multi-unmanned aerial vehicle cooperative path planning and scheduling method provided by the present application can generate an unmanned aerial vehicle observation coverage path with turning optimization in a task area by acquiring task requirements, and then generate an optimized unmanned aerial vehicle scheduling scheme and flight trajectory based on coverage path cost using a genetic algorithm, so that the total flight distance can be minimized and the workload distribution among unmanned aerial vehicles can be balanced while the quality and quantity of the completed surveying and mapping requirements are ensured, and the data acquisition window of large-scale surveying and mapping is shortened.

[0017] In a second aspect, the present application provides a multi-unmanned aerial vehicle cooperative path planning and scheduling system, comprising: An acquisition module is configured to acquire task requirements, determine a plurality of task areas requiring aerial survey, coverage requirements, and unmanned aerial vehicle parking positions, wherein each task area is independent of each other; A path generation module is configured to construct a coverage path with minimum turning cost for each task area according to the coverage requirements; A path cost calculation module is configured to calculate the flight path cost of an unmanned aerial vehicle according to the unmanned aerial vehicle parking positions and the coverage path. a path planning module configured to plan a flight path for each of the UAVs according to the flight path cost using a genetic algorithm.

[0018] In a third aspect, the present application provides an electronic device, comprising at least one processor and at least one memory, wherein the memory has stored thereon computer readable instructions; and the computer readable instructions are executed by one or more of the processors to cause the electronic device to implement the method for multi-UAV cooperative path planning and scheduling according to any implementation manner of the first aspect.

[0019] In a fourth aspect, the present application provides a storage medium having stored thereon a computer executable program for causing a computer to execute the method for multi-UAV cooperative path planning and scheduling according to any implementation manner of the first aspect.

[0020] It can be understood that the beneficial effects achieved by the system of the second aspect, the electronic device of the third aspect, and the storage medium of the fourth aspect can refer to the beneficial effects of the first aspect and any possible design manner thereof, which will not be described here again. BRIEF DESCRIPTION OF DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0022] Figure 1 A structural schematic diagram of an electronic device provided by an embodiment of the present application; Figure 2 A method flowchart of a multi-UAV cooperative path planning and scheduling method provided by an embodiment of the present application; Figure 3 A structural block diagram of a file external sending and leakage prevention system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application. In the description of the present application, unless otherwise specified, " / " represents an "or" relationship between the objects before and after the " / ", for example, A / B can represent A or B; in the present application, "or" is only a description of the relationship between the associated objects, which means that there can be three relationships, for example, A or B, which can mean that A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. In addition, in the description of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like means any combination of the items, including any combination of single or multiple items.

[0024] In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second" and the like are used to distinguish the same items or similar items with basically the same function and effect. Those skilled in the art can understand that "first", "second" and the like do not limit the number and execution order, and "first", "second" and the like do not necessarily mean different.

[0025] Meanwhile, in the embodiments of the present application, "exemplary" or "for example" and the like are used to represent as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more excellent or more advantageous than other embodiments or design schemes. Rather, the use of "exemplary" or "for example" and the like is intended to present the relevant concept in a specific manner, for understanding.

[0026] In the face of large-area remote sensing observation scenarios, due to the low efficiency of a single unmanned aerial vehicle and the limited endurance, a multi-unmanned aerial vehicle cluster can simultaneously cover different areas through task segmentation and parallel operation, thereby greatly shortening the data acquisition time window of a large-area region. Although the multi-unmanned aerial vehicle system brings many advantages to remote sensing applications, how to build an efficient cooperative scheduling and flight path planning mechanism to fully exploit its potential is still a major challenge. In the complex scenarios of endurance limitation, unknown target area or multiple regional take-off and landing, unreasonable regional allocation, access order and flight path design can significantly increase invalid flight and excessive turning, leading to increased energy consumption, shortened endurance, and delayed data acquisition, affecting decision-making timeliness.

[0027] In order to improve the deployment flexibility and continuous operation capability in remote sensing application, the prior art has a ground vehicle modified into a mobile platform integrating unmanned aerial vehicle transportation, rapid deployment, launch and recovery, on-board data processing and energy supplement, etc., as a vehicle-mounted unmanned aerial vehicle system. The vehicle-mounted multi-unmanned aerial vehicle system is a ground vehicle converted into a mobile platform integrating unmanned aerial vehicle transportation, rapid deployment, launch and recovery, data processing and energy supplement, which can solve the transportation, energy supplement limitation and calculation bottleneck faced by small and medium-sized unmanned aerial vehicles in field operation.

[0028] However, most of the existing vehicle-mounted unmanned aerial vehicle systems mainly support manual route planning of a single unmanned aerial vehicle, and are difficult to adapt to the complex requirements of multi-unmanned aerial vehicle cooperative operation. Simply increasing the number of unmanned aerial vehicles will lead to uneven task load of each unmanned aerial vehicle and uneven completion time if effective cooperative strategies are lacking, and the overall efficiency is limited by the "bottleneck effect".

[0029] In view of this, in one aspect, the embodiment of the present application provides a multi-unmanned aerial vehicle cooperative path planning and scheduling method, comprising: obtaining task requirements, determining a plurality of task areas requiring aerial survey, coverage requirements and unmanned aerial vehicle parking positions, wherein each task area is independent of each other; constructing a coverage path with minimum turning cost for each task area according to the coverage requirements; calculating the flight path cost of the unmanned aerial vehicle according to the unmanned aerial vehicle parking position and the coverage path; and planning the visited areas and sequence for each unmanned aerial vehicle according to the flight path cost, and generating the unmanned aerial vehicle flight trajectory by using a genetic algorithm.

[0030] The multi-unmanned aerial vehicle cooperative path planning and scheduling method provided by the embodiment of the present application can generate an unmanned aerial vehicle observation coverage path with turning optimization in the task area by obtaining the task requirements, and then generate an optimized unmanned aerial vehicle scheduling scheme and flight trajectory based on the coverage path cost by using a genetic algorithm, which can complete the surveying and mapping requirements while minimizing the total flight distance and balancing the workload distribution among the unmanned aerial vehicles, and shorten the data acquisition window of large-scale surveying and mapping.

[0031] In some embodiments, the multi-unmanned aerial vehicle cooperative path planning and scheduling method provided by the embodiment of the present application can be executed by any electronic device 20 with data processing capability, such as a general-purpose computer, a personal computer, a notebook computer, a switch or a tablet computer, etc., and the specific implementation of the electronic device 20 is not limited here.

[0032] Figure 1 The hardware structure schematic diagram of the electronic device provided by the embodiment of the present application is shown. The electronic device 20 includes a processor 210, a memory 220 and a communication interface 230.

[0033] The processor 210 can include one or more processing cores. The processor 210 connects various parts within the electronic device 20 with various interfaces and lines, performs various functions of the electronic device 20 and processes data by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Alternatively, the processor 210 can be implemented in at least one hardware form of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), a programmable logic array (PLA).

[0034] The memory 220 can include a random access memory (RAM) and can also include a read-only memory (ROM). Alternatively, the memory 220 includes a non-transitory computer-readable storage medium. The memory 220 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 220 can include a program storage area. The program storage area can store instructions for implementing an operating system, instructions for implementing at least one function (such as a data processing function, a data storage function and a display push function), instructions for implementing each of the above-mentioned method embodiments, etc.

[0035] The communication interface 230 is configured to communicate with other devices, equipment or communication networks, such as data storage devices, image processing equipment or Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0036] In physical implementation, each of the above-mentioned devices (such as the processor 210, the memory 220 and the communication interface 230) can be a device in the same device (such as a notebook computer). Alternatively, at least two of them can be arranged in the same device as different devices in the device, similar to the deployment of devices or components in a distributed system.

[0037] It is to be understood that the structure illustrated in the embodiments does not constitute a specific limitation on the electronic device 20. In other embodiments of the present application, the electronic device 20 can include more or fewer components than illustrated, or combine certain components, or split certain components, or different arrangement of components. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0038] A multi-unmanned aerial vehicle cooperative path planning and scheduling method is described below with reference to the accompanying drawings.

[0039] As shown in the drawings, Figure 2 The multi-unmanned aerial vehicle cooperative path planning and scheduling method provided by the embodiments of the present application can include, but is not limited to, the following steps: Step S1: Obtain task requirements, determine a plurality of task areas requiring aerial survey, coverage requirements, and unmanned aerial vehicle parking positions, wherein each task area is independent of each other.

[0040] The task requirements in the embodiments of the present application can include, but are not limited to, task targets and surveying requirements. Before starting the surveying task, the task targets are used to determine a plurality of task areas requiring aerial survey, the positions and boundaries of each task area, and the coverage requirements, such as the percentage of overlap between adjacent flight lines, the percentage of overlap between the same heading, and the flight height of the unmanned aerial vehicle, according to the surveying requirements.

[0041] In the specific implementation process, the embodiments of the present application can obtain the geographic center of each area and the polygon sequence of the boundary of each area by using existing machine algorithms based on high-definition resolution satellite images, and count the number of task areas.

[0042] In the specific implementation process, after the positions of the task areas are determined, the unmanned aerial vehicle parking positions are selected according to the actual situation on site. In the embodiments of the present application, the unmanned aerial vehicle is a vehicle-mounted unmanned aerial vehicle, and the unmanned aerial vehicle parking position is the vehicle parking position. Generally, an open and good communication signal position in the center of the task area is selected as the unmanned aerial vehicle parking position.

[0043] Step S2: According to the coverage requirements, construct a coverage path with the minimum turning cost for each task area.

[0044] In the specific implementation process, when the unmanned aerial vehicle needs to change direction during flight, it must slow down to a certain speed and adjust the attitude. Additional thrust / power is required to overcome the centrifugal force to change direction to safely turn. In particular, fixed-wing unmanned aerial vehicles have a minimum turning radius limit according to the speed, lift coefficient, and load coefficient. By constructing a coverage path with the minimum turning cost for each task area, the embodiments of the present application can reduce the number of sharp turns of the unmanned aerial vehicle, thereby reducing its power consumption.

[0045] In a feasible implementation, the method of constructing a minimum-turning-cost coverage path for each task area according to the coverage requirement in the embodiment of the present application may, but is not limited to, include the following steps: discretizing each task area into a primitive topological graph according to the coverage requirement; performing linear programming on the primitive topological graph to obtain an end-point matching graph; performing matching on the end-point matching graph by using a Blossom V algorithm to obtain a matching result, and projecting the matching result onto the primitive topological graph to obtain an initial coverage path; optimizing the initial coverage path by using local mixed integer programming to obtain the minimum-turning-cost coverage path.

[0046] In the implementation, the method of discretizing each task area into a primitive topological graph according to the coverage requirement in the embodiment of the present application may, but is not limited to, include the following steps: discretizing each task area into a primitive topological graph by using equilateral triangles, wherein the distance between adjacent nodes in the primitive topological graph matches the coverage requirement.

[0047] Specifically, the method of discretizing each task area into a primitive topological graph by using equilateral triangles in the embodiment of the present application includes the following steps: obtaining a set of vertices and edges ; constructing a Voronoi cell of each node on a grid, and taking the area of the cell as the coverage value of each node , reflecting the approximate coverage area when the path covers the node; and the length of the edge matches the coverage requirement to meet the accuracy requirement of surveying and mapping.

[0048] In the implementation, the method of performing linear programming on the primitive topological graph to obtain an end-point matching graph in the embodiment of the present application may, but is not limited to, include the following steps: introducing a ternary path variable , representing the frequency of occurrence of a path node , and a skip variable , representing that the path node is skipped and a value loss is paid, and the loss value is performing linear programming on the primitive topological graph by using the following function to obtain a fractional solution; wherein, represents a vertex of the primitive topological graph, represents the coverage value of a path node, Includes Euclidean distance and turning angle costs; The fractional solution is converted into multiple atomic bands, each atomic band representing a small imaginary movement at a path node with an adjacent edge orientation; Select the atomic bands with the best orientations in each of the path nodes as candidate atomic bands; For each candidate atomic band, construct corresponding endpoint nodes at both ends, and establish matching edges between any two endpoints to obtain an endpoint matching graph.

[0049] In the specific implementation process, on any triangular mesh, each path node There can be multiple adjacent edge orientations. In this embodiment of the invention, the selection of the optimal several orientations of the atomic bands in each path node as candidate atomic bands can be, but is limited to, the following methods: First, enumerate the path nodes. All adjacent edges are taken as candidate orientations, and the path of the orientation is calculated. Central Order The path node is obtained by weighted summing the directions of its closest neighboring nodes. Orientation evaluation value. The optimal orientations for each node are retained as candidate atomic bands.

[0050] In specific implementation, the embodiment of the present invention describes constructing corresponding endpoint nodes at both ends of each candidate atomic band and establishing matching edges between any two endpoints to obtain an endpoint matching graph. This can be achieved, but is not limited to, using the following methods: If the two ends come from adjacent nodes and have the same geometric orientation, then the edge weight is equal to "half the distance from one end to the other + the turning cost"; if they are the two ends of the same atomic band, then the matching edge weight is set as the loss when that node is skipped. This results in an endpoint matching graph.

[0051] In specific implementation, the Blossom V algorithm used in this embodiment of the invention to match the endpoint matching graph, obtain matching results, and project the matching results onto the original topology graph to obtain the initial coverage path can be implemented, but is not limited to, the following methods: The minimum weight perfect match is solved using the Blossom-V algorithm in the endpoint matching graph, and the result is a set of pairs. Each pair of matches This either indicates connecting the two corresponding atomic band endpoints along the two ends to form a path segment, or it indicates skipping the node and paying a value loss. The matching result is then projected back to the original graph. This allows for the creation of several non-overlapping cycle covers, which form the initial coverage path. These cycle covers balance coverage value and turning costs at the global level, while avoiding excessive unnecessary backtracking.

[0052] In specific implementation, the method described in this embodiment of the invention for optimizing the initial coverage path using local mixed integer programming to obtain the coverage path with the minimum turning cost can be, but is not limited to, the following: Select the node with the "highest cost" Using it as the root, perform a breadth-first search (BFS) to construct a structure containing the previous... Subgraph of nodes In this subgraph, the corresponding path and skip variables are set as binary (0 / 1) variable variables, while the remaining external variables are fixed as constants rounded up from the fractional solution. After solving the entire subgraph, if the objective value decreases and the local solution can connect with the external solution, the global solution is updated. Redundant turns and unnecessary skipping of nodes are reduced through repeated iterations. A Prize-Collecting Steiner Tree (PCST) model is introduced, where the edge weight between two closed loops represents their shortest connection cost. Solving the PCST yields a "value-maximizing" connected subtree. Then, only the selected closed loops in the PCST are merged, while the rest are discarded. For geometrically adjacent closed loops with low connection costs, Dijkstra's algorithm is used to calculate the shortest path with turning costs, and these are merged into a larger closed loop. Finally, a global-scale local MIP optimization is performed on this large closed loop to further eliminate redundancy and overlapping coverage generated during merging. The covered path with the minimum turning cost is ultimately obtained.

[0053] Step S3: Calculate the flight path cost of the drone based on the drone docking location and the coverage path.

[0054] In one feasible implementation, the calculation of the drone's flight path cost based on the drone's docking location and the coverage path in this embodiment of the invention includes: Based on the drone's docking location and the coverage path, the drone's load is calculated using the following formula: ; in, Indicates drone In the mission area The total length of the flight path required to complete coverage observations within the area. This represents the Euclidean distance between two locations. Indicates the drone docking position. Indicates the entry point. Indicates the exit point; The total path cost of the flight task is calculated by the following formula: ; wherein, represents the number of UAVs, represents the endurance mileage of the UAVs; The load balance of the UAVs is calculated by the following formula: ; The total path cost and the load balance are weighted by using a weighted summation mechanism to obtain the flight path cost.

[0055] Step S4: According to the flight path cost, a genetic algorithm is used to plan the regions and sequences visited by each UAV to generate a UAV flight trajectory.

[0056] In a feasible implementation, the step of generating a UAV flight trajectory according to the flight path cost by using a genetic algorithm to plan the regions and sequences visited by each UAV in the embodiment of the present application may, but is not limited to, include the following steps: The task regions are randomly assigned to each UAV to obtain an initial population; The path connection scheme fitness of each population individual in the initial population is calculated according to the flight path cost; The population individuals are selected according to the path connection scheme fitness by using an NSGA-II framework to obtain parent population individuals; The parent population individuals are processed by using a side-recombination multi-region path crossover operator to generate offspring population individuals; The offspring population individuals are mutated by using an adaptive hybrid mutation mechanism to obtain mutated offspring population individuals; An iterative loop is performed until a preset iteration number is reached to obtain the regions and sequences visited by each UAV to generate a UAV flight trajectory.

[0057] It should be noted that the iterative loop in the embodiment of the present application refers to that after the mutated offspring population individuals are obtained, the path connection scheme fitness of the mutated offspring population individuals is calculated according to the flight path cost, then the population individuals are selected by using an NSGA-II framework, and then the population individuals are crossed and mutated until a preset iteration number is reached to finally determine the regions and sequences visited by each UAV.

[0058] In the specific implementation process, after the regions and sequences visited by each UAV are determined, Dubins paths may, but are not limited to, be used to connect the entry points and exit points of the regions to generate smooth flight trajectories that conform to the UAV dynamics constraints.

[0059] In the specific implementation process, before the task area is randomly allocated to each of the unmanned vehicles to obtain an initial population in the embodiment of the application, the method further comprises the following steps of: The unmanned vehicles are encoded by using double-chromosome encoding, wherein a first layer represents a task sequence, and a second layer represents a number of the unmanned vehicles.

[0060] Specifically, in the first layer, each of the unmanned vehicles is allocated a list, and a table head and a table tail represent a parking position (a vehicle position) of the unmanned vehicle; after the task is initialized, a middle part of the list is filled with an area access task; and a vehicle index is always located at a head and a tail of the list allocated to each of the unmanned vehicles, and the position of the vehicle index is not changed. The unmanned vehicles are encoded by using double-chromosome encoding, thereby breaking through a limitation of a number of tasks in a traditional method and supporting dynamic task allocation and load balancing.

[0061] In the specific implementation process, the parent population individuals are processed by using the multi-region path crossover operator based on edge recombination to generate offspring population individuals, which can but are not limited to include the following steps of: extracting a parent region allocated to an unmanned vehicle from the parent population individuals and a parent region , and determining a set of task nodes that need to be accessed by the unmanned vehicle in the parent region and the parent region : ; constructing an adjacency list for each node in the set , adding all paths constructed from the parent region and the parent region to the adjacency list, and recording a number of adjacent nodes in the parent region and the parent region , a distance of an edge, and a flag indicating whether the edge appears in both the parent region and the parent region ; initializing a child region to an empty sequence, randomly selecting a starting node from the set , adding the starting node to the offspring population individual, and marking the starting node as having been visited, so that the starting node ; retrieving all neighbor nodes of the current node curr that have not been visited from the adjacency list; if a candidate neighbor node exists, the candidate neighbor node is used as a next node ; if there is no candidate neighbor node, randomly selecting an unvisited node from the set as the next node ; adding the next node to the offspring region , marking it as visited, and updating ; repeating the searching step until the length of the offspring region is consistent with the length of the parent region , obtaining the offspring region after crossover; initializing the offspring region to an empty sequence, repeating the crossover step of the offspring region , and obtaining the offspring region after crossover; combining all the offspring regions of the drones after crossover and the offspring region , obtaining offspring population individuals.

[0062] In the specific implementation process, the adaptive hybrid mutation mechanism is used to mutate the offspring population individuals in the embodiment of the application, including: a mutation operator combination is selected according to the adaptive hybrid mutation mechanism with a probability to mutate the offspring population individuals; wherein the probability is a current dynamic application probability of the mutation operator combination, and a dynamic adjustment method of the probability is as follows: an empty applied mutation operator set is initialized; the mutation operator combination contains different mutation operators , each mutation operator generates a probability , if , the mutation operator is added to the mutation operator set , the is a current dynamic application probability of the mutation operator , and the is initially the average value of all the mutation operators ; all the mutation operators in the mutation operator set the offspring population individuals are subjected to mutation processing; The path connection scheme fitness of each population individual before and after mutation is compared, and an improvement score is calculated by the following formula : ; Wherein, represents a very small positive number, represents the path connection scheme fitness after mutation; represents the path connection scheme fitness before mutation; The improvement score is evenly distributed to all the mutation operators in the set ; for each mutation operator , its contribution this time is recorded, if > 0, the success counter of each mutation operator increases by 1 ; ; The average contribution of each mutation operator in the last time of application is calculated, and the new base probability of each mutation operator is calculated by the following average contribution calculation formula : ; The base probability is normalized to obtain a new application probability.

[0063] The above-mentioned multi-unmanned aerial vehicle cooperative path planning and scheduling method is applied in the embodiment of the application, damaged buildings after a disaster are investigated in a certain place, 13 building damaged areas are detected by using 3 unmanned aerial vehicles, and the three unmanned aerial vehicles undertake 20.9%, 35.4% and 43.7% of the aerial survey tasks respectively, village gathering area investigation is carried out in a certain place, 42 areas are detected by 6 unmanned aerial vehicles respectively, and the tasks undertaken by the unmanned aerial vehicles are 17%, 17%, 16%, 16%, 17% and 17% respectively.

[0064] The above-mentioned multi-unmanned aerial vehicle cooperative path planning and scheduling method provided by the application can generate an unmanned aerial vehicle observation coverage path with turning optimization in a task area by acquiring task requirements, and then generate an optimized unmanned aerial vehicle scheduling scheme and flight trajectory based on coverage path cost by using a genetic algorithm, so that the mapping demand can be completed with quality and quantity guaranteed, the total flight distance is minimized, the workload distribution among unmanned aerial vehicles is balanced, and the data acquisition window of large-scale mapping is shortened.

[0065] Based on the multi-unmanned aerial vehicle cooperative path planning and scheduling method provided in the first aspect, the embodiment of the present application provides a multi-unmanned aerial vehicle cooperative path planning and scheduling system. Figure 3 As shown in the figure, the multi-unmanned aerial vehicle cooperative path planning and scheduling system comprises: The acquisition module 110 is configured to acquire task requirements, determine a plurality of task areas requiring aerial survey, coverage requirements and unmanned aerial vehicle parking positions, wherein each task area is independent of each other. The path generation module 120 is configured to construct a coverage path with minimum turning cost for each task area according to the coverage requirements. The path cost calculation module 130 is configured to calculate the flight path cost of the unmanned aerial vehicle according to the unmanned aerial vehicle parking positions and the coverage path. The path planning module 140 is configured to plan the visited areas and sequence for each unmanned aerial vehicle according to the flight path cost, and generate the unmanned aerial vehicle flight trajectory by using a genetic algorithm.

[0066] Based on the multi-unmanned aerial vehicle cooperative path planning and scheduling method provided in the first aspect, the embodiment of the present application further provides a storage medium, wherein the storage medium stores a computer executable program, and the computer executable program is configured to enable a computer to execute the multi-unmanned aerial vehicle cooperative path planning and scheduling method in any implementation manner of the first aspect. The explanation and beneficial effects of the related content in any of the above computer readable storage media are described above, and will not be repeated here.

[0067] Those skilled in the art can understand that all or part of the steps of the above-mentioned embodiments can be completed by a program instructing related hardware, and the program can be stored in a computer readable storage medium. The storage medium mentioned above can be a read-only memory, a random access memory, etc. The processing unit or processor mentioned above can be a central processing unit, a general-purpose processor, an application specific integrated circuit (ASIC), a microprocessor (digital signal processor, DSP), a field programmable gate array (FPGA) or other programmable logic device, a transistor logic device, a hardware component or any combination thereof.

[0068] The embodiments of the present application also provide a computer program product containing instructions, which, when executed on a computer, cause the computer to perform any of the methods described above. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the processes or functions according to the embodiments of the present application are wholly or partially generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium accessible by a computer or a data storage device such as a server, data center, etc. containing one or more available media sets. The available media can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, an SSD), etc.

[0069] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided by the embodiments of the present application, such as but not limited to the above-mentioned memory, computer-readable storage medium, and communication chip, etc., are all non-transitory. Those skilled in the art should be aware that in one or more of the above examples, the functions described by the embodiments of the present application can be implemented by hardware, software, firmware, or any combination thereof. When implemented by software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. The computer-readable storage medium includes a computer storage medium and a communication medium, wherein the communication medium includes any medium that facilitates the transfer of a computer program from one place to another. The storage medium can be any available medium accessible by a general-purpose or special-purpose computer.

[0070] Although the embodiments of the present application have been shown and described above, it should be understood that the above-mentioned embodiments are exemplary and should not be construed as limiting the present application, and those skilled in the art can make changes, modifications, replacements, and variations to the above-mentioned embodiments within the scope of the present application.

Claims

1. A multi-UAV cooperative path planning and scheduling method, characterized in that, include: Obtain mission requirements, determine multiple mission areas requiring aerial surveys, coverage requirements, and drone docking locations, where each mission area is independent of the others; Based on the coverage requirements, construct a coverage path with the minimum turning cost for each task area; Calculate the flight path cost of the drone based on the drone docking location and the coverage path; Based on the flight path cost, a genetic algorithm is used to plan the areas and order of visits for each UAV, generating the UAV flight trajectory.

2. The multi-UAV cooperative path planning and scheduling method according to claim 1, characterized in that, Constructing a coverage path with minimum turning cost for each task area according to the coverage requirements includes: Based on the coverage requirements, each task region is decomposed into an original topology map; Perform linear programming on the original topology graph to obtain an endpoint matching graph; The endpoint matching graph is matched using the Blossom V algorithm to obtain the matching results. The matching results are then projected onto the original topology graph to obtain the initial coverage path. The initial coverage path is optimized using local mixed integer programming to obtain the coverage path with the minimum turning cost.

3. The multi-UAV cooperative path planning and scheduling method according to claim 2, characterized in that, The step of disaggregating each task region into an original topology map according to the coverage requirements includes: Each task region is discretized into an original topology graph using equilateral triangles, wherein the distance between adjacent nodes in the original topology graph matches the coverage requirement.

4. The multi-UAV cooperative path planning and scheduling method according to claim 2, characterized in that, The step of performing linear programming on the original topology graph to obtain an endpoint matching graph includes: Introducing ternary pathway variables , representing path nodes Frequency of occurrence at each location, skip variables This indicates that if a path node is skipped, a value loss must be paid, and the value loss is... Using the following functions, linear programming is performed on the original topology graph to obtain a fractional solution; in, Represents the vertices of the original topology graph. Indicates the coverage value of the path node. Includes Euclidean distance and turning angle costs; The fractional solution is converted into multiple atomic bands, each atomic band representing a small imaginary movement at a path node with an adjacent edge orientation; Select the atomic bands with the best orientations in each of the path nodes as candidate atomic bands; For each candidate atomic band, construct corresponding endpoint nodes at both ends, and establish matching edges between any two endpoints to obtain an endpoint matching graph.

5. The multi-UAV cooperative path planning and scheduling method according to claim 1, characterized in that, The step of calculating the flight path cost of the UAV based on the UAV docking location and the coverage path includes: Based on the drone's docking location and the coverage path, the drone's load is calculated using the following formula: ； in, Indicates drone In the mission area The total length of the flight path required to complete coverage observations within the area. This represents the Euclidean distance between two locations. Indicates the drone docking position. Indicates the entry point. Indicates the exit point; The total path cost of a flight mission is calculated using the following formula: ； in, Indicates the number of drones. Indicates the drone's flight range; The load balance of the drone is calculated using the following formula: ； The total path cost and the load balance are weighted using a weighted summation mechanism to obtain the flight path cost.

6. The multi-UAV cooperative path planning and scheduling method according to claim 1, characterized in that, The step of using a genetic algorithm to plan the areas and order of visits for each UAV based on the flight path cost, and generating the UAV flight trajectory, includes: The task area is randomly assigned to each of the drones to obtain an initial population; The fitness of the path connection scheme for each individual in the initial population is calculated based on the flight path cost. Based on the fitness of the path connection scheme, the individuals in the population are selected using the NSGA-II framework to obtain the parent population individuals; The parent population individuals are processed using the multi-region path crossover operator of edge recombination to generate the offspring population individuals; According to the adaptive hybrid mutation mechanism, the offspring population individuals are mutated to obtain mutated offspring population individuals; The process is iterated until a preset number of iterations is reached, obtaining the planned areas and order of visits for each drone, and generating the drone flight trajectory.

7. A multi-UAV cooperative path planning and scheduling method according to claim 6, characterized in that, Before randomly assigning the task area to each of the drones to obtain an initial population, the method further includes: The UAV is encoded using a dual-chromosome encoding method, where the first layer represents the mission sequence and the second layer represents the UAV number.

8. A multi-UAV cooperative path planning and scheduling method according to claim 6, characterized in that, The process of using the multi-region path crossover operator with edge recombination to process the parent population individuals and generate the offspring population individuals includes: Extract individuals from the parent population and assign them to the drone. Parental region and parent region and determine the drone In the parent region and parent region The set of task nodes that need to be accessed: ； For set Each node in Construct an adjacency list that includes regions from the parent region. and the parent region All edges constructed from the paths are added to the adjacency list, and the parent region is recorded. and the parent region The numbers of adjacent nodes, the distance between the edges, and an indication of whether the edge is in the parent region. and the parent region The mark that appears in both; offspring region Initialize as an empty sequence from the set Randomly select a starting node Add it to the offspring population and mark it as visited, so that the current node... ; Retrieve all neighboring nodes that the current node curr has not yet visited from the adjacency list; If a candidate neighbor node exists, then that candidate neighbor node is selected as the next node. ; If no candidate neighbor node exists, then from the set Randomly select an unvisited node as the next node. ; The next node Add the child region Mark as visited and update ; The retrieval process continues until the child region is reached. Length and the parent region The lengths are consistent, and the resulting child regions after intersection are obtained. ; offspring region Initialize to an empty sequence, then repeat the child region. The crossover step is used to obtain the crossover child region. ; The offspring region after all the drones are crossed and the child region Combine them to obtain offspring individuals.

9. A multi-UAV cooperative path planning and scheduling method according to claim 6, characterized in that, The mutation process performed on the offspring population individuals according to the adaptive hybrid mutation mechanism includes: According to the aforementioned adaptive hybrid mutation mechanism, with a probability of Select a combination of mutation operators The offspring population was subjected to mutation treatment; Wherein, the probability The probability is the current dynamic application probability of the combination of mutation operators. The dynamic adjustment method is as follows: Initialize an empty set of applied mutation operators. The combination of mutation operators Include Different mutation operators Each mutation operator Generate a probability ,if Then the mutation operator Add to the set of mutation operators The The mutation operator is The current dynamic application probability, the Initially, all the mutation operators mentioned above are used. The average value; With the set of mutation operators All of the aforementioned mutation operators The offspring population was subjected to mutation treatment; The fitness of the path connectivity schemes for each individual in the population before and after the mutation is compared, and the improvement score is calculated using the following formula. : ； in, Represents a very small positive number. This indicates the fitness of the modified path connection scheme; This indicates the fitness of the path connection scheme before the mutation; The improvement score Distributed equally to the set All of the aforementioned mutation operators For each of the mutation operators His contribution If recorded, >0, then each of the mutation operators The success counter increases by 1. ; Calculate each of the mutation operators In recent Average contribution in this application Each of the mutation operators is calculated using the following average contribution formula. New base probability: ； The base probability is normalized to obtain a new application probability.

10. A multi-UAV cooperative path planning and scheduling system, characterized in that, include: The acquisition module is used to acquire task requirements, determine multiple task areas that need aerial surveying, coverage requirements, and UAV docking locations, where each task area is independent of the others. The path generation module is used to construct a coverage path with the minimum turning cost for each task area according to the coverage requirements. The path cost calculation module is used to calculate the flight path cost of the UAV based on the UAV docking location and the coverage path. The path planning module is used to generate the drone flight trajectory by planning the areas and order to be visited by each drone based on the flight path cost using a genetic algorithm.

Images