Flight Mission Planning and Management System and Method for Multi-UAV Collaboration

Abstract

The present invention relates to the technical field of unmanned aerial vehicles, and specifically to a flight mission planning and management system and method for multi-unmanned aerial vehicle collaboration. The method includes: decomposing the flight area of the unmanned aerial vehicle based on the flight mission of the unmanned aerial vehicle and dividing the flight area; performing path planning within the flight area of the unmanned aerial vehicle, using a genetic algorithm for global flight path planning, and using the A* algorithm for local flight path planning after planning the global path; constructing an obstacle avoidance strategy during the flight of the unmanned aerial vehicle, and re-performing local flight path planning when the obstacle avoidance strategy is triggered; formulating a priority judgment criterion for multi-unmanned aerial vehicle tasks according to the constraints of the unmanned aerial vehicle flight mission, and allocating and scheduling unmanned aerial vehicle resources. The present invention can significantly improve the intelligent level of unmanned aerial vehicle mission planning, enhance the adaptability to complex environments, ensure flight safety and efficient mission execution, and provide practical technical support for the actual application of unmanned aerial vehicles.

Description

Technical Field

[0001] The present invention relates to the technical field of unmanned aerial vehicles, and specifically to a flight mission planning and management system and method for multi-unmanned aerial vehicle cooperation. Background Art

[0002] With the rapid development of unmanned aerial vehicle technology and the continuous expansion of application fields, using multiple unmanned aerial vehicles to cooperate in executing complex tasks has become a research hotspot. Through the division of labor and cooperation of multiple unmanned aerial vehicles, the multi-unmanned aerial vehicle cooperation system can significantly improve the task execution efficiency and success rate. However, how to reasonably plan and schedule multiple unmanned aerial vehicles so that they can work together efficiently, safely, and orderly during the task execution process still faces many challenges.

[0003] Some existing multi-unmanned aerial vehicle mission planning methods adopt a centralized control method, where the ground station or central node uniformly plans and schedules the tasks of unmanned aerial vehicles. Although this method can obtain the global optimal solution, it has the risk of single-point failure, and the computational complexity is high, making it difficult to adapt to large-scale unmanned aerial vehicle clusters and dynamically changing environments. Other methods adopt a completely distributed architecture, and each unmanned aerial vehicle independently plans tasks and paths based on local information. Although this method has good robustness and scalability, it lacks global information and coordination mechanisms, and is prone to task conflicts and resource waste problems.

[0004] Therefore, the existing multi-unmanned aerial vehicle mission planning and management methods generally have problems such as insufficient real-time performance, poor adaptability, and low reliability when dealing with large-scale, dynamic, and complex environments, and it is difficult to meet the requirements of actual applications. There is a need for a more efficient, flexible, and robust mission planning and management method that comprehensively considers the heterogeneity of the unmanned aerial vehicle cluster, the dynamics of the environment, and the complexity of the task, realizes the cooperation of multiple unmanned aerial vehicles under complex conditions, and improves the effectiveness of task execution.

[0005] In view of this, the present invention proposes a flight mission planning and management system and method for multi-unmanned aerial vehicle cooperation. Summary of the Invention

[0006] To achieve the above object, the present invention provides a flight mission planning and management system and method for multi-unmanned aerial vehicle cooperation. The specific technical solutions are as follows: The flight mission planning and management method for multi-unmanned aerial vehicle cooperation includes:

[0007] Based on the flight mission of the unmanned aerial vehicle, decompose the flight area of the unmanned aerial vehicle, and divide the flight area based on the flight parameters of the unmanned aerial vehicle;

[0008] Perform path planning within the flight area of the unmanned aerial vehicle. Use the genetic algorithm for global flight path planning, and use the A* algorithm for local flight path planning after planning the global path;

[0009] Construct an obstacle avoidance strategy for the UAV during flight. After the obstacle avoidance strategy is triggered, re-plan the local flight path;

[0010] According to the UAV flight mission constraints, formulate a priority judgment criterion for multi-UAV missions, and allocate and schedule UAV resources.

[0011] Preferably, based on the mission objectives and execution scope of the UAV, determine the geographical boundary of the entire flight mission area, denoted as the mission area , where is the coordinate point within the area, is the boundary coordinate of the area;

[0012] Collect the environmental information of terrain, meteorology, and airspace control within the mission area to construct an environmental feature matrix , where represents the environmental feature value at the position ;

[0013] Obtain the UAV flight parameters. According to the models and quantities of UAVs participating in the mission, extract the UAV flight parameters, including the maximum range , the maximum payload , and the maximum flight speed ;

[0014] Estimate the total flight time required to complete the entire mission area , as well as the total payload requirement , where are the flight time and payload requirement of the UAV respectively;

[0015] Divide the flight area. Considering the environmental feature matrix of the mission area , as well as the flight parameters of the UAV, divide into non-overlapping sub-areas to form a sub-area set ; Define a division loss function to evaluate the quality of the division scheme;

[0016] Minimize the division loss function , where is the weight coefficient, solve the minimum value of the division loss function to obtain the optimal division scheme ; Among them, is the environmental feature difference degree within the sub-area, is the sub-area area balance degree, is the task relevance between sub-regions;

[0017] Match the drones with the sub-regions and calculate the area of each sub-region and the task complexity , where the task complexity is the weighted sum of the number, density, and priority of task points in the sub-region;

[0018] Estimate the number of drones required to execute the sub-region task, the formula is: , where represents rounding down, represents the maximum task coverage area of a single drone;

[0019] Select drones from the drones participating in the task, and according to the flight parameters of the drones and the environmental characteristics of the sub-region , assign the drones to each sub-region to form an optimal matching relationship , where represents assigning the drone to the sub-region

[0020] . Preferably, a genetic algorithm is used for global flight path planning. Define the flight area of the drone as a three-dimensional space , and any point in the space is represented by coordinates

[0021] ; Define the set of path points , where represents the coordinates of the th path point, is the total number of path points; Define the population , where is the population size, represents the th path, which is composed of path points ; Define the fitness function , which is used to evaluate the quality of the path

[0022] , considering factors such as path length, smoothness, flight time, and energy consumption;

[0023] The steps of global flight path planning by genetic algorithm are as follows:

[0023] Step 1: Initialize the population , randomly generate Path;

[0024] Step 2: Calculate the fitness of each path ;

[0025] Step 3: Perform the selection operation. According to the fitness value, select excellent paths as parents with a probability of ;

[0026] Step 4: Perform the crossover operation: Crossover the parent paths pairwise to generate new offspring paths with a probability of ;

[0027] Step 5: Perform the mutation operation. Mutate the offspring paths randomly with a probability of to introduce new path points or delete existing path points;

[0028] Step 6: Repeat Step 2 to Step 5 until the maximum number of iterations ;

[0029] Output the global path with the highest fitness as the result of the global flight path planning.

[0030] Preferably, the A* algorithm is used for local flight path planning. The global path is discretized into a series of grid points to form a grid map , define the set of grid points , where represents the coordinates of the th grid point, is the total number of grid points;

[0031] Define the open list and the closed list , which store the grid points to be expanded and the expanded grid points respectively. Define the heuristic function , which represents the estimated cost from the grid point to the target point ; Define the cost function , which represents the actual cost from the starting point to the grid point ; Define the evaluation function , which is used to evaluate the expansion priority of the grid point ;

[0032] The steps of local flight path planning by the A* algorithm are as follows:

[0033] Step a: Add the starting point to the open list , and calculate ;

[0034] Step b: Take out from the open list the smallest grid point , and add it to the closed list ;

[0035] Step c: Expand all adjacent grid points of , calculate and ;

[0036] Step d: For each adjacent grid point , if it is in the closed list, ignore it; if it is in the open list and is smaller, then update and ; if it is not in the open list, add it to the open list;

[0037] Step e: Repeat Step b to Step d until the target point is added to the closed list;

[0038] Output the optimal local path from to , match and splice it with the global path to form a complete flight path. Preferably, construct an obstacle avoidance strategy, define the obstacle set

[0039] , where represents the th obstacle, is the total number of obstacles, and drones are regarded as obstacles to each other; define the safety distance of the drone, indicating the minimum allowable distance between the drone and the obstacle; define the collision detection function , used to judge whether the drone collides with the obstacle , and the judgment condition is whether the distance between the two is less than ; ;

[0040] During the flight of the drone, continuously monitor the distance between the drone and all obstacles, and calculate the collision detection function in real time; when it is detected that is true, that is, there is a collision risk between the drone and a certain obstacle , trigger the obstacle avoidance strategy, immediately stop the current flight path, and enter the local path replanning mode.

[0041] Preferably, the local path replanning after obstacle avoidance trigger defines the current position of the drone as , and the target position is , centered around , with as the radius, construct a local path planning space , where is the local planning range parameter, discretize into a series of grid points to form a local grid map ;

[0042] Define the set of local grid points , where represents the coordinates of the -th local grid point, is the total number of local grid points. For each obstacle , check whether it intersects with the local path planning space . If it intersects, mark its projection area in as impassable;

[0043] Define the set of local path points , where represents the coordinates of the -th local path point, is the total number of local path points. Use the A* algorithm to search in for the local optimal path from to , avoiding all impassable areas during the search; ;

[0044] Concatenate the local optimal path with the original global path to obtain the updated global path ; The drone continues to fly along the updated global path until it reaches the target position or triggers the obstacle avoidance strategy again.

[0045] Preferably, define the set of drone tasks , where represents the -th task, is the total number of tasks; For each task , extract its task attribute vector , where represents the -th attribute value of task , is the total number of attributes; Define the task priority evaluation function , where is the weight coefficient of the -th attribute;

[0046] Calculate the priority evaluation value of each task , and sort the tasks in descending order according to to obtain the task priority queue , where represents the task with the highest priority;

[0047] Define the UAV resource pool , where represents the th UAV, is the total number of UAVs; for each UAV , extract its flight parameter vector , where represents the th flight parameter value of the UAV , is the total number of flight parameters;

[0048] Construct the task and UAV matching degree evaluation function: , where is the weight coefficient of the th flight parameter, is the indicator function, indicating whether the UAV meets the constraint conditions of the task , if it meets, it is 1, otherwise it is 0;

[0049] Initialize the task and UAV allocation matrix , where indicates whether to allocate the task to the UAV ; according to the order of the task priority queue , process each task one by one; for the task , calculate the matching degree between the task and each idle UAV, and select the UAV with the highest matching degree to execute the task;

[0050] When all tasks are allocated or all UAVs are occupied, output the task and UAV allocation matrix , and according to obtain the task execution sequence of each UAV to form a task scheduling scheme for multiple UAVs.

[0051] A flight mission planning and management system for multi-UAV collaboration, which is used to implement the flight mission planning and management method for multi-UAV collaboration described above, including: a flight area division module, a flight path planning module, a flight obstacle avoidance module, and a flight scheduling module;

[0052] The flight area division module decomposes the flight area of ​​the UAV based on the flight mission of the UAV, and divides the flight area based on the flight parameters of the UAV;

[0053] The flight path planning module performs path planning within the flight area of ​​the UAV, uses a genetic algorithm to perform global flight path planning, and uses an A* algorithm to perform local flight path planning after planning the global path;

[0054] The flight obstacle avoidance module is used to construct an obstacle avoidance strategy for the UAV during flight. When the obstacle avoidance strategy is triggered, the local flight path planning is re-performed;

[0055] The flight scheduling module formulates priority judgment criteria for multiple UAV tasks according to the UAV flight mission constraints, and allocates and schedules UAV resources.

[0056] An electronic device comprises: a processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the flight mission planning and management method for multi-UAV collaboration by calling the computer program stored in the memory.

[0057] A computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute the flight mission planning and management method for multi-UAV collaboration.

[0058] Beneficial effects of the present invention: The present invention reduces task complexity, optimizes resource matching, and improves task planning precision and feasibility through regional decomposition and parameter division.

[0059] The present invention combines the genetic algorithm with the A* algorithm to search for the optimal flight path in a complex environment and achieve efficient, smooth, energy-saving and safe path planning.

[0060] The present invention builds real-time obstacle avoidance monitoring and response to avoid obstacles and ensure safety; after obstacle avoidance is triggered, rapid re-planning is carried out to minimize the impact on the flight plan.

[0061] The present invention optimizes matching and scheduling according to task priorities and flight parameters, thereby improving the quality and efficiency of multi-UAV collaborative task planning.

[0062] The present invention covers the key links of UAV mission planning, from area decomposition, path planning, obstacle avoidance strategy to task scheduling, forming a complete multi-UAV collaborative task planning system; through the optimized design of each link and the selection of algorithms, the intelligence level of UAV mission planning can be significantly improved, the adaptability to complex environments can be enhanced, flight safety and efficient mission execution can be ensured, and practical technical support can be provided for the practical application of UAVs. Brief Description of the Drawings

[0063] Figure 1 This is a flowchart of the flight mission planning and management method for multi-UAV cooperation provided by the present invention;

[0064] Figure 2 This is a structural diagram of the flight mission planning and management system for multi-UAV cooperation provided by the present invention. Detailed Embodiments

[0065] To better understand the present invention, more detailed descriptions of various aspects of the present invention will be made with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present invention and do not limit the scope of the present invention in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0066] In the drawings, for ease of illustration, the sizes, dimensions, and shapes of the elements have been slightly adjusted. The drawings are only examples and are not drawn strictly to scale. As used herein, terms such as "substantially", "about", and similar terms are used as approximate terms and not as terms of degree, and are intended to account for the inherent deviations in measured or calculated values that would be recognized by a person of ordinary skill in the art. Additionally, in the present invention, the order of description of the steps of the processes does not necessarily represent the order in which these processes occur in actual operation, unless otherwise clearly defined or derivable from the context.

[0067] It should also be understood that expressions such as "comprises", "comprising", "has", "including", and / or "including having" in this specification are open-ended rather than closed-ended expressions, which mean the presence of the stated features, elements, and / or components, but do not exclude the presence of one or more other features, elements, components, and / or combinations thereof. In addition, when an expression such as "at least one of..." appears after a list of listed features, it modifies the entire list of features rather than just individual elements in the list. Further, when describing embodiments of the present invention, the use of "may" means "one or more embodiments of the present invention". And the term "exemplary" is intended to refer to an example or illustration.

[0068] Unless otherwise defined, all terms used herein (including engineering terms and scientific and technical terms) have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention pertains. It should also be understood that, unless clearly stated in the present invention, words defined in a commonly used dictionary should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and should not be interpreted in an idealized or overly formal sense.

[0069] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the drawings and in combination with the embodiments.

[0070] Embodiment 1

[0071] Referring to Figure 1 , the first embodiment of the present invention provides a flight mission planning and management method for multi-UAV cooperation.

[0072] S1: Based on the flight mission of the UAV, decompose the flight area of the UAV and divide the flight area based on the flight parameters of the UAV.

[0073] Based on the mission objectives and execution scope of the UAV, determine the geographical boundary of the entire flight mission area, denoted as the mission area , where is the coordinate point within the area, is the boundary coordinate of the area.

[0074] Collect the environmental information of terrain, meteorology, and airspace control within the mission area to construct an environmental feature matrix , where represents the environmental feature value at the position .

[0075] Obtain the UAV flight parameters. According to the models and quantities of the UAVs participating in the mission, extract the UAV flight parameters, including the maximum range , the maximum payload , and the maximum flight speed .

[0076] Estimate the total flight time required to complete the entire mission area , and the total payload requirement , where are respectively the flight time and payload requirement of the UAV .

[0077] Divide the flight area. Considering the environmental feature matrix of the mission area , and the flight parameters of the UAV, divide into non-overlapping sub-areas to form a sub-area set ; Define a division loss function to evaluate the quality of the division scheme. The loss function should comprehensively consider the following factors: the environmental feature difference degree within the sub-area , where For the sub-region The average environmental characteristic value

[0078] The balance degree of the sub-region area , where is the area of the sub-region , , is the average area

[0079] The task correlation between sub-regions , where is the task correlation weight between sub-regions and .

[0080] Minimize the partitioning loss function , where is the weight coefficient, adjusted according to actual needs, and the minimum value of the partitioning loss function is solved using a heuristic search or simulated annealing optimization algorithm to obtain the optimal partitioning scheme .

[0081] Match the drones with the sub-regions, and calculate the area and task complexity of each sub-region , where the task complexity is the weighted sum of the number, density, and priority of task points in the sub-region

[0082] According to the sub-region area and task complexity, estimate the number of drones required to execute the sub-region task, and the formula is , where represents rounding down represents a single drone 's maximum task coverage area

[0083] Select drones from the drones participating in the task, and according to the flight parameters of the drones and the environmental characteristics of the sub-region, through methods such as the Hungarian algorithm and bipartite graph matching, assign the drones to each sub-region to form an optimal matching relationship , where represents assigning drone to sub-region .

[0084] In step S1, by decomposing and dividing the flight area of the drone and combining environmental information and drone parameters, the task complexity can be effectively reduced, the precision and feasibility of task planning can be improved, the matching between the drone and the task area can be optimized, the drone resources can be maximally utilized, and the task execution efficiency can be enhanced.

[0085] S2: Conduct path planning within the flight area of the drone. Use the genetic algorithm for global flight path planning, and use the A* algorithm for local flight path planning after planning the global path.

[0086] Use the genetic algorithm for global flight path planning. Define the flight area of the drone as a three-dimensional space , and any point in the space can be represented by coordinates .

[0087] Define the set of path points , where represents the coordinates of the th path point, and is the total number of path points.

[0088] Define the population , where is the population size, and represents the nd path, which is composed of path points .

[0089] Define the fitness function , which is used to evaluate the quality of the path , comprehensively considering factors such as path length, smoothness, flight time, and energy consumption.

[0090] The main steps of the genetic algorithm are as follows:

[0091] Step 1: Initialize the population , and randomly generate paths;

[0092] Step 2: Calculate the fitness of each path ;

[0093] Step 3: Conduct the selection operation. According to the fitness size, select excellent paths as parents with a probability ;

[0094] Step 4: Conduct the crossover operation: Cross the parent paths pairwise and generate new offspring paths with a probability ;

[0095] Step 5: Conduct the mutation operation. Mutate the offspring paths randomly with a probability , introducing new path points or deleting existing path points;

[0096] Step 6: Repeat Step 2 to Step 5 until the termination condition is met (such as reaching the maximum number of iterations or the fitness does not increase significantly for consecutive iterations).

[0097] Output the global path with the highest fitness as the result of the global flight path planning.

[0098] Use the A* algorithm for local flight path planning, discretize the global path into a series of grid points to form a grid map , define the set of grid points , where represents the coordinates of the th grid point, and

[0099] Define the open list and the closed list , store the grid points to be expanded and the expanded grid points respectively, define the heuristic function , which represents the estimated cost from the grid point to the target point , and can be measured by the Euclidean distance, Manhattan distance, etc.

[0100] Define the cost function , which represents the actual cost from the starting point to the grid point , and can be calculated according to the flight distance, number of turns, energy consumption factors.

[0101] Define the evaluation function , which is used to evaluate the expansion priority of the grid point .

[0102] The main steps of the A* algorithm are as follows:

[0103] Step a: Add the starting point to the open list , and calculate ;

[0104] Step b: Take out the grid point with the smallest from the open list, and add it to the closed list ;

[0105] Step c: Expand all adjacent grid points of , and calculate and ;

[0106] Step d: For each , if it is in the closed list, ignore it; if it is in the open list and is smaller, then update and ; if it is not in the open list, add it to the open list;

[0107] Step e: Repeat Step b to Step d until the target point is added to the closed list or the open list is empty.

[0108] Output the optimal local path from to , match and splice it with the global path to form a complete flight path.

[0109] The genetic algorithm in S2 step is used for global path planning, which can search for the optimal flight path in a complex environment, comprehensively consider various factors, and achieve efficient, smooth and energy-saving paths; the A* algorithm is used for local path planning, which can dynamically avoid obstacles, generate safe and feasible local paths, and effectively connect with the global path to ensure the optimization of the overall flight path.

[0110] S3: Construct an obstacle avoidance strategy for the UAV during flight. When the obstacle avoidance strategy is triggered, re-plan the local flight path.

[0111] Construct an obstacle avoidance strategy, define the obstacle set , where represents the th obstacle, is the total number of obstacles, and UAVs are regarded as obstacles to each other; for each obstacle , define its shape, size and position, which can be approximated by simple geometric bodies such as spheres, cubes, cylinders, etc., or accurately described by polyhedrons, define the safety distance of the UAV, which represents the minimum allowable distance between the UAV and the obstacle; define the collision detection function , which is used to judge whether the UAV collides with or is too close to the obstacle , and the judgment condition is whether the distance between the two is less than .

[0112] During the flight of the UAV, continuously monitor the distance between the UAV and all obstacles, and calculate the collision detection function in real time; when it is detected that is true, that is, the UAV collides with a certain obstacle ​If there is a collision risk, the obstacle avoidance strategy is triggered, the current flight path is immediately stopped, and the local path replanning mode is entered.

[0113] The local path replanning after obstacle avoidance trigger defines the current position of the UAV as , and the target position as . With as the center and as the radius, a local path planning space is constructed, where is the local planning range parameter. Discretize into a series of grid points to form a local grid map .

[0114] Define the set of local grid points , where represents the coordinates of the th local grid point, is the total number of local grid points. For each obstacle , check whether it intersects with the local path planning space . If it intersects, mark its projection area in as impassable.

[0115] Define the set of local path points , where represents the coordinates of the th local path point, is the total number of local path points. Use the A* algorithm to search for the local optimal path from to in , avoiding all impassable areas during the search process.

[0116] Concatenate the local optimal path with the original global path to obtain the updated global path ; the UAV continues to fly along the updated global path until it reaches the target position or the obstacle avoidance strategy is triggered again.

[0117] Step S3 constructs a real-time obstacle avoidance strategy during the UAV flight. Through continuous monitoring and rapid response, it can maximize the avoidance of obstacles and ensure flight safety; once the obstacle avoidance is triggered, through local path replanning, an obstacle avoidance path can be quickly generated online, minimizing the impact on the original flight plan and improving the ability to handle emergencies.

[0118] S4: According to the constraints of the UAV flight mission, formulate the priority judgment criteria for the multi-UAV mission, and allocate and schedule UAV resources.

[0119] Define the UAV mission set , where represents the th mission, and is the total number of missions; for each mission , extract its mission attribute vector , where represents the th attribute value of mission , and is the total number of attributes; mission attributes can include the importance level, time urgency, execution difficulty, etc. of the mission; define the mission priority evaluation function , where is the weight coefficient of the

[0120] th attribute, reflecting the influence degree of this attribute on the mission priority. Calculate the priority evaluation value of each mission, and sort the missions in descending order according to the size of to obtain the mission priority queue , where

[0121] represents the mission with the Define the UAV resource pool , where represents the th UAV, and is the total number of UAVs; for each UAV , extract its flight parameter vector , where represents the th flight parameter value of UAV

[0122] Construct the mission and UAV matching degree evaluation function: , where is the weight coefficient of the th flight parameter, is the indicator function, indicating whether UAV meets the constraint conditions of mission , if it meets, it is 1, otherwise it is 0.

[0123] Initialize the mission and UAV allocation matrix , where Indicates whether the task Assign to drone ; According to the task priority queue order, processing each task one by one; for tasks , calculate its matching degree with each idle drone , select the drone with the highest matching degree Execute the task.

[0124] When all tasks are assigned or all drones are occupied, output the task and drone allocation matrix ,according to The task execution sequence of each UAV is obtained to form a task scheduling plan for multiple UAVs.

[0125] In step S4, based on the mission priority and UAV flight parameters, through task attribute extraction, priority evaluation and task-UAV matching optimization, the priority judgment criteria of multi-UAV missions can be scientifically formulated to achieve the optimal matching and scheduling of tasks and UAVs, and improve the quality and efficiency of multi-UAV collaborative mission planning.

[0126] Example 2

[0127] Reference Figure 2 , which is the second embodiment of the present invention, provides a flight mission planning and management system for multi-UAV collaboration.

[0128] The system comprises: a flight area division module, a flight path planning module, a flight obstacle avoidance module and a flight scheduling module.

[0129] The flight area division module decomposes the flight area of ​​the UAV based on the flight mission of the UAV, and divides the flight area based on the flight parameters of the UAV.

[0130] The flight path planning module performs path planning within the flight area of ​​the UAV, adopts a genetic algorithm to perform global flight path planning, and adopts an A* algorithm to perform local flight path planning after planning the global path.

[0131] The flight obstacle avoidance module is used to construct an obstacle avoidance strategy for the UAV during flight. When the obstacle avoidance strategy is triggered, the local flight path planning is re-performed.

[0132] The flight scheduling module formulates priority judgment criteria for multiple UAV tasks according to the UAV flight mission constraints, and allocates and schedules UAV resources.

[0133] Example 3

[0134] The present invention also provides an electronic device. The electronic device may include one or more processors and one or more memories. Among them, computer-readable code is stored in the memory, and when the computer-readable code is run by one or more processors, it can execute the flight mission planning and management method for multi-UAV cooperation as described above.

[0135] The method or system according to an embodiment of the present invention can also be implemented by means of the architecture of the electronic device of the present invention.

[0136] The electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, input / output components, a hard disk, etc.

[0137] The storage device in the electronic device, such as ROM or a hard disk, can store the flight mission planning and management method for multi-UAV cooperation provided by the present invention.

[0138] The flight mission planning and management method for multi-UAV cooperation includes decomposing the flight area of the UAV based on the flight mission of the UAV, and dividing the flight area based on the flight parameters of the UAV; performing path planning within the flight area of the UAV, using a genetic algorithm for global flight path planning, and using the A* algorithm for local flight path planning after planning the global path; constructing an obstacle avoidance strategy during the flight of the UAV, and when the obstacle avoidance strategy is triggered, re-performing local flight path planning; formulating a priority judgment criterion for multi-UAV tasks according to the UAV flight mission constraints, and allocating and scheduling UAV resources.

[0139] Furthermore, the electronic device may further include a user interface. Of course, the architecture of the present invention is only exemplary, and when implementing different devices, one or more components in the electronic device disclosed in the present invention may be omitted according to actual needs.

[0140] Embodiment 4

[0141] The present invention also discloses a computer-readable storage medium.

[0142] Computer-readable instructions are stored on the computer-readable storage medium.

[0143] When the computer-readable instructions are run by a processor, the flight mission planning and management method for multi-UAV cooperation according to an embodiment of the present invention described with reference to the above drawings can be executed.

[0144] The storage medium includes, but is not limited to, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory, etc. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. Additionally, according to an embodiment of the present invention, the processes described above with reference to the flowcharts may be implemented as computer software programs.

[0145] For example, the present invention provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be run by a processor to execute instructions corresponding to the method steps provided by the present invention, such as: decomposing the flight area of the unmanned aerial vehicle (UAV) based on the flight mission of the UAV, and dividing the flight area based on the flight parameters of the UAV; performing path planning within the flight area of the UAV, using a genetic algorithm for global flight path planning, and using the A* algorithm for local flight path planning after planning the global path; constructing an obstacle avoidance strategy during the flight of the UAV, and re-performing local flight path planning when the obstacle avoidance strategy is triggered; formulating a priority judgment criterion for multi-UAV tasks according to the UAV flight mission constraints, and allocating and scheduling UAV resources.

[0146] When the computer program is executed by a central processing unit (CPU), the above functions defined in the method of the present invention are executed. The method, apparatus, and device of the present invention may be implemented in many ways. For example, the method, apparatus, and device of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware.

[0147] The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the specific order described above, unless otherwise specifically stated.

[0148] In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, and these programs include machine-readable instructions for implementing the method according to the present invention. Therefore, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0149] Furthermore, in the above technical solutions provided by the embodiments of the present invention, parts that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive elaboration.

[0150] As described above in the specific embodiments, the purpose, technical solution, and beneficial effects of the present invention are further described in detail. It should be understood that the above is only the specific embodiment of the present invention and is not used to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A flight mission planning and management method for multi-UAV collaboration, characterized in that: include: Based on the flight mission of the UAV, the flight area of ​​the UAV is decomposed, and the flight area is divided based on the flight parameters of the UAV; Based on the mission objectives and execution scope of the UAV, the geographical boundaries of the entire flight mission area are determined and recorded as the mission area; Collect environmental information on terrain, weather and airspace control in the mission area and construct an environmental feature matrix; obtain UAV flight parameters, and extract UAV flight parameters including maximum range, maximum payload and maximum flight speed according to the model and number of UAVs involved in the mission; estimate the total flight time and total payload required to complete the entire mission area; Divide the flight area, consider the environmental feature matrix of the mission area and the flight parameters of the UAV, divide the mission area into multiple non-overlapping sub-areas, form a sub-area set to define the partition loss function, which is used to evaluate the pros and cons of the partition scheme, solve the minimum value of the partition loss function, and obtain the optimal partition scheme; Match drones with sub-regions, calculate the area and mission complexity of each sub-region; estimate the number of drones required to perform sub-region missions based on the sub-region area and mission complexity; Select some drones from multiple drones participating in the mission, and assign the drones to each sub-area according to the flight parameters of the drones and the environmental characteristics of the sub-areas to form an optimal matching relationship; Perform path planning within the UAV's flight area, use genetic algorithm for global flight path planning, and use A* algorithm for local flight path planning after planning the global path; Build an obstacle avoidance strategy for the drone during flight. When the obstacle avoidance strategy is triggered, re-plan the local flight path. According to the UAV flight mission constraints, formulate the priority judgment criteria for multiple UAV tasks, and allocate and schedule UAV resources.

2. The flight mission planning and management method for multi-UAV collaboration according to claim 1 is characterized in that: Based on the mission objectives and execution scope of the UAV, the geographical boundaries of the entire flight mission area are determined, which is recorded as the mission area. ,in are the coordinate points in the region, are the boundary coordinates of the region; Collection Mission Area The environmental information of terrain, weather and airspace control within the area is used to construct an environmental feature matrix ,in Indicates location Environmental characteristic values; Get the flight parameters of the drone, according to the participating missions The model and number of drones, extracting the flight parameters of the drones, including the maximum range , Maximum load , Maximum flight speed ; Estimate the completion of the entire task area Total flight time required , and the total load demand ,in UAV Flight time and payload requirements; Divide the flight area and consider the mission area Environmental characteristics matrix , and the flight parameters of the drone ,Will Divide into non-overlapping sub-regions, forming a sub-region set ; Define the partition loss function , used to evaluate the pros and cons of the partitioning scheme; Minimize the partition loss function ,in is the weight coefficient, solve the minimum value of the partition loss function, and get the optimal partitioning solution ;in, is the difference of the internal environmental characteristics of the sub-region, is the sub-region area balance, is the task relevance between sub-regions; Match drones to sub-areas and calculate each sub-area Area and task complexity , where the task complexity The weighted sum is calculated using the number, density, and priority of task points in the sub-region; Estimate the execution sub-area based on the sub-area area and task complexity Number of drones required for the mission , the formula is: ,in Indicates rounding down. Represents a single drone Maximum mission coverage area; From participating in the task Select from drones According to the flight parameters of the drone and environmental characteristics of the sub-regions , assign drones to each sub-area to form the best matching relationship ,in Indicates that drones Assign to sub-area .

3. The flight mission planning and management method for multi-UAV collaboration according to claim 2 is characterized in that: Genetic algorithm is used for global flight path planning, and the flight area of ​​the drone is defined as three-dimensional space. , any point in space is represented by its coordinates express; Define a set of waypoints ,in Indicates The coordinates of the path points, is the total number of path points; define the population ,in is the population size, Indicates Paths, consisting of waypoints Composition; define fitness function , used to evaluate the path The advantages and disadvantages of the two technologies are comprehensively considered, including path length, smoothness, flight time and energy consumption. The steps for global flight path planning using genetic algorithm are as follows: Step 1: Initialize the population , randomly generated Paths; Step 2: Calculate the fitness of each path ; Step 3: Perform selection operation, according to the fitness size, with probability Select the good path as the parent; Step 4: Perform crossover operation: perform pairwise crossover on the parent paths, with probability Generate new child paths; Step 5: Perform mutation operation with probability Randomly mutate the offspring path, introduce new path points or delete the original path points; Step 6: Repeat steps 2 to 5 until the maximum number of iterations is reached. ; Output the global path with the highest fitness As a result of global flight path planning.

4. The flight mission planning and management method for multi-UAV collaboration according to claim 3 is characterized in that: The A* algorithm is used to plan the local flight path and the global path Discretize into a series of grid points to form a grid map , define the grid point set ,in Indicates The coordinates of the grid points, is the total number of grid points; Defining an open list and close list , respectively store the grid points to be expanded and those that have been expanded, and define the heuristic function , which means from the grid point To the destination Estimated cost of; define the cost function , indicating that from the starting point To grid point The actual cost of; define the evaluation function , used to evaluate the grid points The expansion priority of The steps for local flight path planning using the A* algorithm are as follows: Step a: Set the starting point Join the open list ,calculate ; Step b: Take from the open list Minimum grid point , add it to the closed list ; Step c: Extension All adjacent grid points ,calculate and ; Step d: For each adjacent grid point , if in the closed list, it is ignored; if in the open list and Smaller, newer and ; If it is not in the open list, add it to the open list; Step e: Repeat steps b to d until the target point Added to the closed list; Output from arrive The optimal local path , with the global path Match and splice to form a complete flight path.

5. The flight mission planning and management method for multi-UAV collaboration according to claim 4 is characterized in that: Build an obstacle avoidance strategy and define the obstacle set ,in Indicates obstacles, is the total number of obstacles. UAVs are considered obstacles to each other. Defines the safe distance between UAVs , represents the minimum allowed distance between the drone and the obstacle; defines the collision detection function , used to judge the drone Is there an obstacle? A collision occurs, and the judgment condition is whether the distance between the two is less than ; During the flight of the drone, the distance between the drone and all obstacles is continuously monitored, and the collision detection function is calculated in real time ; When detected True, that is, the drone is in contact with an obstacle If a collision risk occurs, the obstacle avoidance strategy is triggered, the current flight path is stopped immediately, and the local path replanning mode is entered.

6. The flight mission planning and management method for multi-UAV collaboration according to claim 5 is characterized in that: The local path replanning after obstacle avoidance is triggered defines the current position of the drone as , the target location is ,by Centered on As the radius, construct a local path planning space ,in is the local planning range parameter, Discretize into a series of grid points to form a local grid map ; Define a local grid point set ,in Indicates The coordinates of the local grid points, is the total number of local grid points, for each obstacle , check whether it is consistent with the local path planning space intersect, if so, place it in The projected area in is marked as impassable; Define a local path point set ,in Indicates The coordinates of the local path points, is the total number of local path points, using the A* algorithm in Search from arrive The local optimal path , avoiding all inaccessible areas during the search; The local optimal path With the original global path Perform splicing to get the updated global path ; The drone follows the updated global path Continue flying until you reach the target location Or trigger the obstacle avoidance strategy again.

7. The flight mission planning and management method for multi-UAV collaboration according to claim 6 is characterized in that: Define a set of drone missions ,in Indicates tasks, is the total number of tasks; for each task , extract its task attribute vector ,in Representation Task No. attribute values, is the total number of attributes; define the task priority evaluation function ,in For the The weight coefficient of each attribute; Calculate the priority evaluation value for each task , and according to Arrange the tasks in descending order according to their size to obtain the task priority queue ,in Indicates the priority High tasks; Define the drone resource pool ,in Indicates drone, is the total number of drones; for each drone , extract its flight parameter vector ,in Indicates drone No. Flight parameter values, is the total number of flight parameters; Construct a task and drone matching evaluation function: ,in For the The weight coefficients of the flight parameters, is the indicator function, indicating that the drone Is the task met? If the constraint condition is met, it is 1, otherwise it is 0; Initialize the task and drone allocation matrix ,in Indicates whether the task Assign to drone ; According to the task priority queue order, processing each task one by one; for tasks , computing tasks Matching degree with each idle drone , select the drone with the highest matching degree Execute tasks; When all tasks are assigned or all drones are occupied, output the task and drone allocation matrix ,according to The task execution sequence of each UAV is obtained to form a task scheduling plan for multiple UAVs.

8. A flight mission planning and management system for multi-UAV collaboration, which is used to implement the flight mission planning and management method for multi-UAV collaboration as described in any one of claims 1 to 7, characterized in that: include: Flight area division module, flight path planning module, flight obstacle avoidance module and flight scheduling module; The flight area division module decomposes the flight area of ​​the UAV based on the flight mission of the UAV, and divides the flight area based on the flight parameters of the UAV; The flight path planning module performs path planning within the flight area of ​​the UAV, uses a genetic algorithm to perform global flight path planning, and uses an A* algorithm to perform local flight path planning after planning the global path; The flight obstacle avoidance module is used to construct an obstacle avoidance strategy for the UAV during flight. When the obstacle avoidance strategy is triggered, the local flight path planning is re-performed; The flight scheduling module formulates priority judgment criteria for multiple UAV tasks according to the UAV flight mission constraints, and allocates and schedules UAV resources.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; the processor executes the flight mission planning and management method for multi-UAV collaboration as described in any one of claims 1 to 7 by calling the computer program stored in the memory.

10. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the flight mission planning and management method for multi-UAV collaboration as described in any one of claims 1 to 7.

Images