A method for multi-UAV cooperative search task allocation and path planning

Abstract

This application provides a method for multi-UAV cooperative search task allocation and path planning, belonging to the field of UAV technology. The method includes: acquiring a set of search task points, a set of UAV take-off and landing sites, the number of UAVs at each take-off and landing site, the maximum range and speed of the UAVs; based on the acquired data, constructing an optimization model, defining the objective function as minimizing the task completion time or minimizing the number of dispatched UAVs, and setting constraints; solving the optimization model based on a genetic algorithm, including initializing the population, defining a fitness function, applying a combination of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results. By comprehensively considering constraints such as the number of UAVs at each take-off and landing site, range, and minimum task load, an optimization model is established. An improved genetic algorithm based on a two-segment encoding strategy and multi-operator hybrid optimization is used to solve the optimization model, thus solving the problem of multi-UAV cooperative search task allocation and path planning.

Description

Technical Field

[0001] This invention belongs to the field of unmanned aerial vehicle (UAV) technology, and in particular relates to a method for multi-UAV collaborative search task allocation and path planning. Background Technology

[0002] Multi-UAV cooperative search is an important task pattern in UAV applications, especially when dealing with a large number of search points. Task allocation and path planning are two key issues, and their quality directly affects the efficiency of the entire system. The multi-UAV cooperative search problem studies how to efficiently utilize multiple UAVs to complete a series of search tasks. Specifically, given a set of search points and a set of available UAVs, the problem is to rationally allocate search points to each UAV and plan its flight path while satisfying various constraints such as UAV range, number of UAVs, and UAV take-off and landing points, so as to optimize the overall system's search task completion efficiency.

[0003] Extensive research has been conducted by scholars both domestically and internationally on the problem of multi-UAV cooperative search, mainly focusing on the application of intelligent algorithms in multi-UAV trajectory planning. However, further research is needed on how to optimize the allocation of multi-UAV search tasks and trajectory planning when the number of UAVs is uncertain and the task time limit is given.

[0004] Therefore, the present invention provides a method for multi-UAV collaborative search task allocation and path planning. Summary of the Invention

[0005] This invention provides a method for multi-UAV cooperative search task allocation and path planning to solve the problem of multi-UAV cooperative search trajectory planning for a given number of UAVs and the problem of optimizing the number of UAVs and their path planning for a given task completion time limit.

[0006] This application provides a method for multi-UAV cooperative search task allocation and path planning, the method including:

[0007] Obtain the set of search task points, the set of drone take-off and landing sites, the number of drones at each take-off and landing site, and the maximum range and speed of the drones;

[0008] Based on the acquired data, an optimization model is constructed, the objective function is defined as minimizing the task completion time or minimizing the number of drones dispatched, and constraints are set.

[0009] The optimization model is solved based on a genetic algorithm, including initializing the population, defining the fitness function, applying a combination of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results.

[0010] Furthermore, the set of search task points is as follows: ,in, This indicates the number of search task points. The position is ;

[0011] The drone take-off and landing sites are collectively known as ,in, This indicates the number of drone take-off and landing sites. The position is ;

[0012] All take-off and landing sites The number of drones inside is ;

[0013] The maximum range of the drone is ;

[0014] The drone's speed is .

[0015] Furthermore, based on the acquired data, an optimization model is constructed. The construction process is as follows:

[0016] take-off and landing site The dispatched drones:

[0017]

[0018] in, Indicates the take-off and landing site The dispatched drones assembled. Indicates the take-off and landing site Number of drones deployed Indicates drone, ;

[0019] drones The set of search task points:

[0020]

[0021] in, Indicates drone The set of search task points, Indicates allocation to drones The number of search task points;

[0022] drones Task path:

[0023]

[0024] in, Indicates drone From the take-off and landing site Start by going through the search task points in sequence. Search task points , Search task points Then return to the take-off and landing site ;

[0025] Path length:

[0026]

[0027] in, Indicates drone From the take-off and landing site Start by going through the search task points in sequence. Search task points , Search task points Then return to the take-off and landing site Path length, This is a distance function between two points;

[0028] drones Task time:

[0029]

[0030] in, Indicates drone Task time;

[0031] Time required for multi-drone collaborative search to complete the mission:

[0032]

[0033] in, This indicates the time required for multiple drones to collaboratively complete a search mission.

[0034] Furthermore, the objective function of the optimization model is:

[0035] At a given take-off and landing site Number of drones dispatched Minimize task completion time in the following case Its expression is:

[0036]

[0037] Given a task completion time limit To minimize the total number of drones deployed, the expression is:

[0038] .

[0039] Furthermore, the constraints include:

[0040] Drone path length Not exceeding the maximum range ,Right now:

[0041]

[0042] Drone take-off and landing site Number of drones dispatched No more than the take-off and landing area Total number of drones ,Right now:

[0043]

[0044] Each dispatched drone must complete at least one search task point, i.e., the set of search task points. Non-empty, that is:

[0045] .

[0046] Furthermore, the optimization model is solved based on a genetic algorithm, including initializing the population, defining the fitness function, applying a combination of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results, specifically including:

[0047] An initial population is generated using a random initialization process.

[0048] Calculate the fitness value for all individuals in the current population;

[0049] The entire population is divided into several subgroups;

[0050] Each subgroup of individuals randomly selects a combination operator to perform operations, resulting in newly generated offspring individuals;

[0051] Determine whether the newly generated offspring individuals satisfy the constraints;

[0052] If the following conditions are met: the newly generated individuals are retained;

[0053] If the conditions are not met: retain the original individual;

[0054] Determine if the maximum number of iterations has been reached;

[0055] If the process ends, output the optimal solution found so far;

[0056] If not reached: return to calculate the fitness value of all individuals in the current population and start a new loop.

[0057] Furthermore, the genetic algorithm employs a two-segment chromosome encoding scheme;

[0058] The first segment is a random permutation of the sequence of search task points;

[0059] The second segment is the location segmentation code, used to divide the sequence of search task points for the UAV.

[0060] Furthermore, the fitness function is defined as the maximum time required for multiple UAVs to collaboratively search and complete a task, i.e.:

[0061]

[0062] in, For individuals within a population.

[0063] Furthermore, the genetic algorithm also includes dividing the population into multiple subpopulations for group optimization, where the population size and subpopulation size satisfy the following relationship:

[0064]

[0065] in, For population size, For the size of the subgroup, This represents the number of subpopulations, which is an integer. Dividing the population into multiple subpopulations, each evolving independently, increases population diversity and avoids premature convergence.

[0066] Furthermore, the genetic operators include flip operators, exchange operators, shift operators, and random partitioning operators;

[0067] The flip operator is based on the best individual in the subgroup, randomly selecting a segment of genes encoded by the path and flipping its order;

[0068] The exchange operator is based on the optimal individual in a subgroup, randomly selecting two genes in the path encoding for exchange.

[0069] The shift operator is based on the optimal individual in the subgroup, randomly selecting a segment of the gene encoded by the path and performing a shift operation;

[0070] The random segmentation operator is based on the optimal individual in the subgroup, and performs a random regeneration operation on the segmentation position encoding;

[0071] The combined operators include combinations of flip operators and random partitioning operators, combinations of exchange operators and random partitioning operators, and combinations of shift operators and random partitioning operators.

[0072] As can be seen from the above technical solutions, the present invention has the following advantages:

[0073] The multi-UAV cooperative search task allocation and path planning method provided in this application establishes an optimization model by comprehensively considering constraints such as the number of UAVs at each take-off and landing site, flight range, and minimum task workload. The optimization model is solved by an improved genetic algorithm based on a two-segment coding strategy and multi-operator hybrid optimization, thus solving the problem of multi-UAV cooperative search task allocation and path planning. Attached Figure Description

[0074] To more clearly illustrate the technical solution of this application, the accompanying drawings used in the description will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0075] Figure 1 This is a flowchart of one embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0076] Figure 2 This is a schematic diagram of the coding scheme of an embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0077] Figure 3 This is a schematic diagram of the flip operator in one embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0078] Figure 4 This is a schematic diagram of the exchange operator in one embodiment of the multi-UAV cooperative search task allocation and path planning method of the present invention.

[0079] Figure 5 This is a schematic diagram of a shift operator in an embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0080] Figure 6 This is a schematic diagram of a random segmentation operator in an embodiment of the multi-UAV cooperative search task allocation and path planning method of the present invention.

[0081] Figure 7 This is a schematic diagram of the combination of the flip operator and the random segmentation operator in one embodiment of the multi-UAV cooperative search task allocation and path planning method of the present invention.

[0082] Figure 8 This is a schematic diagram of the combination of the exchange operator and the random partitioning operator in one embodiment of the multi-UAV cooperative search task allocation and path planning method of the present invention.

[0083] Figure 9 This is a schematic diagram of the combination of shift operator and random segmentation operator in one embodiment of the multi-UAV cooperative search task allocation and path planning method of the present invention.

[0084] Figure 10 This is a flowchart of the genetic algorithm solution model in an embodiment of the multi-UAV cooperative search task allocation and path planning method of the present invention.

[0085] Figure 11 This is a task situation diagram of one embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0086] Figure 12 This is a schematic diagram illustrating the shortest time task allocation and path planning in an embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0087] Figure 13 This is a schematic diagram showing the relationship between the shortest time and the number of iterations in one embodiment of the multi-UAV collaborative search task allocation and path planning method of the present invention.

[0088] Figure 14 This is a schematic diagram illustrating the relationship between the drone path length and the number of iterations in one embodiment of the multi-drone collaborative search task allocation and path planning method of the present invention.

[0089] Figure 15 This is a schematic diagram illustrating the relationship between the number of drones and the minimum task time in one embodiment of the multi-drone collaborative search task allocation and path planning method of the present invention. Detailed Implementation

[0090] To make the purpose, features, and advantages of this application more apparent and understandable, specific embodiments and accompanying drawings will be used to clearly and completely describe the technical solution protected by this application. Obviously, the embodiments described below are only some embodiments of this application, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0091] This application provides a method for multi-UAV cooperative search task allocation and path planning, which solves the current urgent technical problem of multi-UAV cooperative search trajectory planning for a given number of UAVs and the optimization of the number of UAVs and their path planning for a given task completion time limit.

[0092] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0093] Figure 1 A flowchart illustrating a multi-UAV cooperative search task allocation and path planning method provided in this application embodiment. Figure 1 As shown in the figure, this application provides a method for multi-UAV cooperative search task allocation and path planning, which specifically includes the following steps:

[0094] Step S1: Obtain the set of search task points, the set of drone take-off and landing sites, the number of drones at each take-off and landing site, and the maximum range and speed of the drones.

[0095] Step S2: Based on the acquired data, construct an optimization model, define the objective function as minimizing the task completion time or minimizing the number of drones dispatched, and set constraints.

[0096] Step S3: Solve the optimization model based on the genetic algorithm, including initializing the population, defining the fitness function, applying the combination operator of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results.

[0097] This invention establishes an optimization model that comprehensively considers constraints such as the number of UAVs at each take-off and landing site, flight range, and minimum task load. The optimization model is then solved using a genetic algorithm, thus addressing the problem of task allocation and path planning for multi-UAV collaborative search.

[0098] It supports minimizing task completion time or the number of drones deployed as optimization objectives, adapting to different task scenarios. A closed loop is achieved based on a genetic algorithm, from task input to model construction, iterative optimization, and final output, avoiding the inefficiency of manual planning. Furthermore, as a refinement and extension of the specific implementation of the above embodiments, to fully illustrate the specific implementation process in this embodiment, another method for multi-drone cooperative search task allocation and path planning is provided, the method including:

[0099] Obtain the set of search task points, the set of drone take-off and landing sites, the number of drones at each take-off and landing site, and the maximum range and speed of the drones.

[0100] The set of search task points is as follows: ,in, This indicates the number of search task points. The position is The drone take-off and landing sites are collectively known as ,in, This indicates the number of drone take-off and landing sites. The position is Each take-off and landing site The number of drones inside is The maximum range of the drone is The drone's flight speed is .

[0101] According to another embodiment of the present invention, an optimization model is constructed based on the acquired data, and the construction process is as follows:

[0102] take-off and landing site The dispatched drones:

[0103]

[0104] in, Indicates the take-off and landing site The dispatched drones assembled. Indicates the take-off and landing site Number of drones deployed Indicates drone, ;

[0105] drones The set of search task points:

[0106]

[0107] in, Indicates drone The set of search task points, Indicates allocation to drones The number of search task points;

[0108] drones Task path:

[0109]

[0110] in, Indicates drone From the take-off and landing site Start by going through the search task points in sequence. Search task points , Search task points Then return to the take-off and landing site ;

[0111] Path length:

[0112]

[0113] in, Indicates drone From the take-off and landing site Start by going through the search task points in sequence. Search task points , Search task points Then return to the take-off and landing site Path length, This is a distance function between two points;

[0114] drones Task time:

[0115]

[0116] in, Indicates drone Task time;

[0117] Time required for multi-drone collaborative search to complete the mission:

[0118]

[0119] in, This indicates the time required for multiple drones to collaboratively complete a search mission.

[0120] Define the objective function as minimizing the task completion time or minimizing the number of drones dispatched, and set the constraints.

[0121] In an exemplary embodiment, the objective function of the optimization model is:

[0122] At a given take-off and landing site Number of drones dispatched Minimize task completion time in the following case Its expression is:

[0123]

[0124] Given a task completion time limit To minimize the total number of drones deployed, the expression is:

[0125] .

[0126] This invention addresses two key issues in multi-UAV collaborative search: task allocation and path planning. It establishes an optimization model with the objective functions of minimizing task time and minimizing the number of UAVs deployed, and comprehensively considers constraints such as the number of UAVs at each take-off and landing site, flight range, and minimum task workload.

[0127] According to another embodiment of the present invention, the constraint conditions include:

[0128] Drone path length Not exceeding the maximum range ,Right now:

[0129]

[0130] Drone take-off and landing site Number of drones dispatched No more than the take-off and landing area Total number of drones ,Right now:

[0131]

[0132] Each dispatched drone must complete at least one search task point, i.e., the set of search task points. Non-empty, that is:

[0133] .

[0134] The optimization model is solved using a genetic algorithm, including initializing the population, defining the fitness function, applying a combination of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results. Specifically, this includes:

[0135] Step S31: Generate the initial population using a random initialization process;

[0136] Step S32: Calculate the fitness value of all individuals in the current population; the fitness function is defined as the maximum time required for multi-UAV cooperative search to complete the task, i.e.:

[0137]

[0138] in, For individuals in a population, the smaller the fitness function value, the shorter the task time and the better the quality of the individual.

[0139] Step S33: Divide the entire population into several subpopulations; perform grouping optimization by dividing the population into multiple subpopulations, with the population size and subpopulation size satisfying the following relationship:

[0140]

[0141] in, For population size, For the size of the subgroup, This represents the number of subgroups, which is an integer.

[0142] Dividing the population into multiple subpopulations, each of which evolves independently, increases population diversity and avoids premature convergence.

[0143] Step S34: Each subgroup of individuals randomly selects a combination operator to perform the operation, resulting in newly generated offspring individuals;

[0144] Step S35: Determine whether the newly generated offspring individuals meet the constraints; the constraints include:

[0145] Drone path length Not exceeding the maximum range ,Right now:

[0146]

[0147] Drone take-off and landing site Number of drones dispatched No more than the take-off and landing area Total number of drones ,Right now:

[0148]

[0149] Each dispatched drone must complete at least one search task point, i.e., the set of search task points. Non-empty, that is:

[0150] ;

[0151] If the following conditions are met: the newly generated individuals are retained;

[0152] If the conditions are not met: retain the original individual;

[0153] Step S36: Determine whether the maximum number of iterations has been reached;

[0154] If the process ends, output the optimal solution found so far;

[0155] If not achieved: return to step S32, calculate the fitness value of all individuals in the current population, and start a new loop.

[0156] The genetic algorithm employs a two-segment chromosome encoding scheme;

[0157] The first segment is a random permutation of the sequence of search task points;

[0158] The second segment is the location segmentation code, used to divide the sequence of search task points for the UAV.

[0159] The chromosome encoding should reflect the search task points and their search order for each UAV. To improve solution efficiency, a two-segment chromosome encoding scheme is adopted. The first segment is path encoding, ensuring that each task point is searched only once; the second segment is path segmentation position encoding, which clarifies the search task allocation for each UAV.

[0160] like Figure 2 As shown, for a search problem involving n task points and m drones, the length of its chromosome is n+m-1. The first n positions are a random arrangement of the n search task points, and the last m-1 positions are the arrangement of the division positions of the m drones on the sequence of n search task points. The m-1 division positions divide the n search task points into m segments, where each segment represents the search track of a drone.

[0161] Following the above encoding scheme and rules, in order to ensure population diversity and a wide search space, a random initialization process is adopted to generate the initial population.

[0162] The fitness function is defined as the maximum time required for multiple UAVs to collaboratively search and complete a task, i.e.:

[0163]

[0164] in, For individuals in a population, a smaller fitness function value indicates a shorter task time and better individual quality.

[0165] The genetic algorithm further includes dividing the population into multiple subpopulations for group optimization, where the population size and subpopulation size satisfy the following relationship:

[0166]

[0167] in, For population size, For the size of the subgroup, This represents the number of subgroups, which is an integer.

[0168] Dividing the population into multiple subpopulations, each of which evolves independently, increases population diversity and avoids premature convergence.

[0169] The genetic operators include flip operators, exchange operators, shift operators, random partitioning operators, and combination operators;

[0170] like Figure 3 As shown, the flip operator is based on the best individual in the subgroup, randomly selecting a segment of genes encoded by the path and flipping its order.

[0171] like Figure 4 As shown, the exchange operator is based on the optimal individual in the subgroup, randomly selecting two genes in the path encoding for exchange;

[0172] like Figure 5 As shown, the shift operator is based on the optimal individual in the subgroup, randomly selecting a segment of the path-encoded gene for shifting operation;

[0173] As shown in 6, the random segmentation operator performs a random regeneration operation on the segmentation position code based on the optimal individual in the subgroup.

[0174] like Figure 7 , Figure 8 , Figure 9 As shown, the combination operators include combinations of flip operators and random partitioning operators, combinations of exchange operators and random partitioning operators, and combinations of shift operators and random partitioning operators.

[0175] This invention provides an improved genetic algorithm solution model based on a two-segment encoding strategy (task point sequence encoding + segmentation position encoding) and multi-operator hybrid optimization (flip, exchange, shift, random segmentation and their combination operators), which effectively solves the task allocation and path planning problem of multi-UAV multi-target cooperative search.

[0176] For example, the algorithm parameters are set as follows: population size 80, subpopulation size 8, and maximum number of iterations 5000.

[0177] Scenario 1: Given the number of drones, simulation of the shortest time trajectory planning:

[0178] like Figure 11 As shown, assuming there are 3 take-off and landing sites for the drone, that is... ,in, The position is (0,0). The position is (50000,0). The location is (0, 50000), and the unit is... , at 100km 30 drone search mission points are randomly generated within a 100km range.

[0179] take-off and landing site , , One drone was dispatched from each drone to collaboratively complete the search tasks at 30 locations. The maximum range of each drone was 500km, and their speeds were 100m / s, 80m / s, and 60m / s, respectively. Through algorithmic calculation, the shortest time was 54.4 minutes. The task allocation and path planning for each drone are as follows: Figure 12 As shown.

[0180] During the algorithm iteration process, the change in the shortest time required for the UAV to complete the search task is as follows: Figure 13 As shown; the search paths of each UAV change as follows Figure 14 As shown.

[0181] Scenario 2: Simulation of task time limit, number of drones and trajectory planning:

[0182] If the take-off and landing site , , There are 5 drones in each scenario, with other parameters the same as in scenario 1. The relationship between the search task time and the number of drones deployed is determined using an algorithm as follows: Figure 15 As shown.

[0183] Figure 15 In this context, different mission times corresponding to the same number of drones represent different combinations of drones dispatched from different take-off and landing sites for the same number of drones.

[0184] like Figure 15 As shown in Table 1, if the task completion time limit is 3000s, the minimum number of drones to be dispatched should be 3. The relationship between the number of drones dispatched from different take-off and landing sites and the time taken for the search task is shown in Table 1. Among them, the combinations [0, 3, 0], [1, 2, 0], [2, 0, 1], [2, 1, 0] and [3, 0, 0] all meet the conditions, and the combination [3, 0, 0] takes the least time.

[0185] Table 1. Relationship between different combinations and search task time

[0186]

[0187] This invention addresses two key issues in multi-UAV cooperative search: task allocation and path planning. It sets the objective functions as minimizing task time and the number of deployed UAVs, respectively. An optimization model is established by comprehensively considering constraints such as the number of UAVs at each takeoff and landing site, flight range, and minimum task workload. An improved genetic algorithm solution model is designed based on a two-segment encoding strategy (task point sequence encoding + segmentation position encoding) and multi-operator hybrid optimization (flipping, swapping, shifting, random segmentation, and their combinations). Simulation results in typical scenarios demonstrate that the proposed model and algorithm can effectively solve the task allocation and path planning problems in multi-UAV multi-target cooperative search.

[0188] The various embodiments of this disclosure will be described more fully in the foregoing detailed description of the multi-UAV cooperative search task allocation and path planning method. This disclosure may have various embodiments, and adjustments and changes may be made therein. However, it should be understood that there is no intention to limit the various embodiments of this disclosure to the specific embodiments disclosed herein, but rather this disclosure should be understood to cover all adjustments, equivalents, and / or alternatives falling within the spirit and scope of the various embodiments of this disclosure.

[0189] In the foregoing, the terms “comprising” or “may include”, which may be used in the various embodiments of this disclosure, indicate the presence of the disclosed functions, operations, or elements, and do not limit the addition of one or more functions, operations, or elements. Furthermore, as used in the various embodiments of this disclosure, the terms “comprising,” “having,” and their cognates are intended only to indicate a specific feature, number, step, operation, or combination of the foregoing, and should not be construed as primarily excluding the presence of one or more other features, numbers, steps, operations, or combinations of the foregoing, or the possibility of adding one or more features, numbers, steps, operations, or combinations of the foregoing.

[0190] In various embodiments of this disclosure, the expression "or" or "at least one of A and / or B" includes any combination or all combinations of the words listed simultaneously. For example, the expression "A or B" or "at least one of A and / or B" may include A, may include B, or may include both A and B.

[0191] Obviously, the embodiments described above are only some embodiments of the present invention, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0192] The above description of the disclosed embodiments enables those skilled in the art to make or use the invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Therefore, the invention is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0193] Any changes, modifications, substitutions, and variations made to the embodiments without departing from the principles and spirit of the present invention still fall within the protection scope of the present invention.

Claims

1. A method for multi-UAV cooperative search task allocation and path planning, characterized in that, The method includes: Obtain the set of search task points, the set of drone take-off and landing sites, the number of drones at each take-off and landing site, and the maximum range and speed of the drones; Based on the acquired data, an optimization model is constructed, the objective function is defined as minimizing the task completion time or minimizing the number of drones dispatched, and constraints are set. The optimization model is solved based on a genetic algorithm, including initializing the population, defining the fitness function, applying a combination of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results. Based on the acquired data, an optimization model is constructed. The construction process is as follows: take-off and landing site The dispatched drones: in, Indicates the take-off and landing site The dispatched drones assembled. Indicates the take-off and landing site Number of drones deployed Indicates drone, ; drones The set of search task points: in, Indicates drone The set of search task points, Indicates allocation to drones The number of search task points; drones Task path: in, Indicates drone From the take-off and landing site Start by going through the search task points in sequence. Search task points , Search task points Then return to the take-off and landing site ; Path length: in, Indicates drone From the take-off and landing site Start by going through the search task points in sequence. Search task points , Search task points Then return to the take-off and landing site Path length, This is a distance function between two points; drones Task time: in, Indicates drone Task time; Time required for multi-drone collaborative search to complete the mission: in, Indicates the time required for multiple drones to collaboratively complete a search mission; The optimization model is solved using a genetic algorithm, including initializing the population, defining the fitness function, applying a combination of genetic operators for iterative optimization, and outputting the optimal UAV task allocation and path planning results. Specifically, this includes: An initial population is generated using a random initialization process. Calculate the fitness value for all individuals in the current population; The entire population is divided into several subgroups; Each subgroup of individuals randomly selects a combination operator to perform operations, resulting in newly generated offspring individuals; Determine whether the newly generated offspring individuals satisfy the constraints; If the following conditions are met: the newly generated individuals are retained; If the conditions are not met: retain the original individual; Determine if the maximum number of iterations has been reached; If the process ends, output the optimal solution found so far; If not reached: return to calculate the fitness value of all individuals in the current population and start a new loop; The genetic algorithm employs a two-segment chromosome encoding scheme; The first segment is a random permutation of the sequence of search task points; The second segment is the location segmentation code, used to divide the sequence of search task points for the UAV.

2. The multi-UAV cooperative search task allocation and path planning method as described in claim 1, characterized in that, The search task point set is ,in, This indicates the number of search task points. The position is ; The drone take-off and landing sites are set up as follows ,in, This indicates the number of drone take-off and landing sites. The position is ; All take-off and landing sites The number of drones inside is ; The maximum range of the drone is ; The drone's speed is .

3. The multi-UAV cooperative search task allocation and path planning method as described in claim 2, characterized in that, The objective function of the optimization model is: At a given take-off and landing site Number of drones dispatched Minimize task completion time in the following case Its expression is: Given a task completion time limit To minimize the total number of drones deployed, the expression is: 。 4. The multi-UAV cooperative search task allocation and path planning method as described in claim 3, characterized in that, The constraints include: Drone path length Not exceeding the maximum range ,Right now: Drone take-off and landing site Number of drones dispatched No more than the take-off and landing area Total number of drones ,Right now: Each dispatched drone must complete at least one search task point, i.e., the set of search task points. Non-empty, that is: 。 5. The multi-UAV cooperative search task allocation and path planning method as described in claim 4, characterized in that, The fitness function is defined as the maximum time required for multiple UAVs to collaboratively search and complete a task, i.e.: in, For individuals within a population.

6. The multi-UAV cooperative search task allocation and path planning method as described in claim 5, characterized in that, The genetic algorithm further includes dividing the population into multiple subpopulations for group optimization, where the population size and subpopulation size satisfy the following relationship: in, For population size, For the size of the subgroup, This represents the number of subgroups, which is an integer.

7. The multi-UAV cooperative search task allocation and path planning method as described in claim 6, characterized in that, The genetic operators include flip operators, exchange operators, shift operators, and random partitioning operators; The flip operator is based on the best individual in the subgroup, randomly selecting a segment of genes encoded by the path and flipping its order; The exchange operator is based on the optimal individual in a subgroup, randomly selecting two genes in the path encoding for exchange. The shift operator is based on the optimal individual in the subgroup, randomly selecting a segment of the gene encoded by the path and performing a shift operation; The random segmentation operator is based on the optimal individual in the subgroup, and performs a random regeneration operation on the segmentation position encoding; The combined operators include combinations of flip operators and random partitioning operators, combinations of exchange operators and random partitioning operators, and combinations of shift operators and random partitioning operators.

Images