A dynamic task planning method based on hybrid genetic algorithm

Abstract

The application discloses a dynamic task planning method based on a hybrid genetic algorithm, belongs to the technical field of dynamic task planning of unmanned aerial vehicles, and is used for realizing dynamic task distribution in a search reconnaissance task scene. First, the hybrid genetic algorithm is used to perform pre-planning according to task information and unmanned aerial vehicle capability information, and a pre-planning scheme is obtained. The hybrid genetic algorithm is combined by an original genetic algorithm and a variable neighborhood search algorithm, the basic genetic algorithm is used to ensure the exploration ability of the algorithm, and the variable neighborhood search algorithm is used to ensure the development ability of the algorithm. Then, dynamic task information is loaded, and dynamic tasks are sorted according to the time when the dynamic task information appears. Then, a dynamic distribution mechanism is used for distributing the dynamic tasks, four kinds of dynamic adjustment strategies are designed for different task scenes, and the four kinds of dynamic adjustment strategies are respectively a random distribution strategy, a distribution strategy based on clustering center distribution, a nearest distribution strategy and a distribution strategy based on fuel remaining amount. Finally, the unmanned aerial vehicle updates a task sequence.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of dynamic task planning of unmanned aerial vehicles, and particularly relates to a dynamic task planning method based on a hybrid genetic algorithm, which is used for realizing dynamic task allocation in a search reconnaissance task scenario. BACKGROUND

[0002] With the rapid development of science and technology, the application of unmanned aerial vehicles and unmanned vehicles has been greatly expanded. Task allocation is a key in the execution of multiple tasks by multiple unmanned platforms. In the traditional task allocation problem, a task is planned once and completed, but in actual application scenarios, most tasks are dynamically changing. Therefore, in addition to pre-planning at the beginning of the task, dynamic reallocation of the task is also required. In the dynamic task planning problem, the types of dynamically changing tasks mainly include the following categories. The first category is that new tasks appear over time, such as search reconnaissance tasks. The second category is that the task is a dynamically moving target, and the position of the target changes over time, such as a task of tracking a dynamic target. The third category is that the demand of the task is dynamically changing, and the demand of the task increases linearly or nonlinearly over time, such as a fire rescue task.

[0003] There are various planning algorithms for dynamic task allocation problems, such as particle swarm algorithm, ant colony algorithm, genetic algorithm, A* algorithm, etc. Each algorithm has its own characteristics and application scope, such as the data storage structure of the map directly affecting the selection of the algorithm. The present application designs four dynamic adjustment strategies for different dynamic tasks, which are random allocation strategy, allocation strategy based on clustering center allocation, nearest allocation strategy, and allocation strategy based on fuel remaining amount. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a dynamic task planning method based on a hybrid genetic algorithm, which is used for realizing dynamic task allocation in a search reconnaissance task scenario. The present application first uses a hybrid genetic algorithm to pre-plan according to task information and unmanned aerial vehicle capability information, to obtain a pre-planning scheme. The hybrid genetic algorithm is combined by a primitive genetic algorithm and a variable neighborhood search algorithm, the basic genetic algorithm is used to ensure the exploration ability of the algorithm, and the variable neighborhood search algorithm is used to ensure the development ability of the algorithm; then dynamic task information is loaded, and the dynamic tasks are sorted according to the time of occurrence of the dynamic task information; and then a dynamic allocation mechanism is used to allocate the dynamic tasks.

[0005] A dynamic task planning method, comprising:

[0006] Step 1: using a hybrid genetic algorithm to pre-plan according to task information and unmanned aerial vehicle capability information, to obtain a pre-planning scheme, specifically:

[0007] First, initialization is performed to generate an initial population; the initialized individual is represented by the following formula:

[0008] X = [x1, x2, …, x I , x I+1 , x I+2 , …, x I+N-1 ]

[0009] wherein I represents the total number of tasks, N represents the total number of unmanned aerial vehicles; the number of times of segmenting the task sequence is N-1; x1, x2, …, x I represent tasks, and the value range is [1, I]; x I+1 , x I+2 , …, x I+N -1 represent the segmentation positions of tasks, and the value range is [1, I-1];

[0010] Next, individual selection is performed according to the constructed selection function; then, an evolution iteration stage is entered, and when the iteration termination condition is met, a pre-planning scheme is output;

[0011] wherein the evolution iteration stage includes: a crossover operation, a mutation operation and a variable neighborhood operation;

[0012] The crossover operation first generates a crossover position, and then exchanges the genes corresponding to the crossover position; wherein the individual task number position and the segmentation position are independently subjected to the crossover operation;

[0013] The mutation operation first randomly selects two mutation individuals; then, a mutation bit is generated; finally, the genes on the mutation bit are exchanged, and the genes in the respective codes that are the same as the genes after the mutation of the mutation bit are changed to the original genes on the mutation bit; different numbers of mutation bits are set according to the number of tasks;

[0014] Step 2: Load dynamic task information, and sort the dynamic tasks according to the time of occurrence of the dynamic task information;

[0015] Step 3: Assign the dynamic tasks, and then the unmanned aerial vehicles update the task sequence.

[0016] Preferably, the method of selecting individuals according to the constructed selection function includes: evaluating individuals according to the constructed evaluation function; and the optimization target is the total length of the flight path of the unmanned aerial vehicle to complete the task, that is:

[0017] f(X) = l1 + l2 + … + l n + … + l N

[0018] wherein l nrepresents the flight distance required for the nth UAV to complete the task; the UAV needs to meet its own endurance time constraint during the execution of the task, and the solution formula of the time required for the UAV to complete the task is as follows:

[0019] t n =l n / v n ,n∈{1,2,…,N}

[0020] Wherein, t n represents the time required for the nth UAV to complete the task, v n represents the flight speed of the nth UAV; if the individual does not meet the above UAV endurance time constraint, the individual will be discarded in the evolution process;

[0021] Then, according to the constructed selection function, the individual selection is performed; the solution process of the fitness value of the individual is as follows:

[0022]

[0023] Wherein, represents the fitness value of the pth individual of the gth generation, represents the objective function value of the pth individual of the gth generation; and respectively represent the minimum and maximum objective function values of the gth generation;

[0024] The selection of the individual is based on the following formula:

[0025]

[0026] Wherein, represents the pth individual of the gth generation, 1 and 0 respectively represent retaining and discarding the individual, and fv represents the fitness threshold.

[0027] Preferably, when the individual selection is performed, the fitness value is set to be larger in the early stage of evolution to ensure that the selected individual is more excellent; in the later stage of evolution, the fitness value is adjusted to be smaller to ensure that more individuals are selected, and the adjustment process is as follows:

[0028]

[0029] Wherein, g represents the iteration number.

[0030] Preferably, the variable neighborhood operation includes exchange, shift and reversal operations;

[0031] The exchange method includes: generating an exchange position, exchanging the genes at the two exchange positions, and then obtaining a new individual;

[0032] The method of the shift comprises: generating a gene position 1 to be shifted and a position 2 to which the gene position 1 is to be shifted; and moving the gene at the gene position 1 to the rear of the gene at the gene position 2.

[0033] The method of the reverse comprises: generating a reverse interval, and performing a reverse operation on the genes in the reverse interval.

[0034] Preferably, the dynamic tasks are allocated by using a random allocation strategy, specifically: when a new task appears, the new task is randomly allocated to a UAV, and the UAV updates its task list later.

[0035] Preferably, the dynamic tasks are allocated by using a clustering center-based allocation strategy, specifically: first, the task center of each UAV is calculated; then, when a new task appears, the new task is allocated to the nearest cluster; finally, the UAVs in the cluster update their task lists.

[0036] Preferably, the dynamic tasks are allocated by using a nearest distance-based allocation strategy, specifically: first, the distance between each UAV and the position where the new task appears is calculated; then, the UAV with the minimum distance is obtained, and the new task is allocated to the UAV; finally, the UAV updates its task list.

[0037] Preferably, the dynamic tasks are allocated by using a fuel remaining amount-based allocation strategy, specifically: first, the remaining endurance time of each UAV is calculated according to the time when the dynamic task appears; then, the UAV with the maximum remaining endurance time is obtained, and the new task is allocated to the UAV; finally, the UAV updates its task list.

[0038] The present application has the following beneficial effects:

[0039] Firstly, the present application adopts a hybrid genetic algorithm to perform pre-planning according to task information and UAV capability information, and obtain a pre-planning scheme.

[0040] Secondly, the present application allocates dynamic tasks by using a dynamic allocation mechanism, and designs four dynamic adjustment strategies, i.e., a random allocation strategy, a clustering center-based allocation strategy, a nearest allocation strategy, and a fuel remaining amount-based allocation strategy, for coping with different dynamic task situations.

[0041] Third, the method of the present application is used to realize dynamic task allocation in search reconnaissance task scenarios. The present application first uses a hybrid genetic algorithm to pre-plan according to task information and unmanned aerial vehicle capability information, to obtain a pre-planning scheme. The hybrid genetic algorithm is combined from a basic genetic algorithm and a variable neighborhood search algorithm, the basic genetic algorithm is used to ensure the exploration ability of the algorithm, and the variable neighborhood search algorithm is used to ensure the development ability of the algorithm; then dynamic task information is loaded, and the dynamic tasks are sorted according to the time of occurrence of the dynamic task information; then a dynamic allocation mechanism is used to allocate the dynamic tasks, four kinds of dynamic adjustment strategies are designed for different task scenarios, which are respectively a random allocation strategy, an allocation strategy based on a clustering center allocation, a nearest allocation strategy, and an allocation strategy based on a fuel remaining amount; finally, the unmanned aerial vehicle updates the task sequence. BRIEF DESCRIPTION OF DRAWINGS

[0042] Figure 1 is a coding and decoding schematic diagram;

[0043] Figure 2 is a crossover operator schematic diagram;

[0044] Figure 3 is a mutation operator schematic diagram;

[0045] Figure 4 is a variable neighborhood operator schematic diagram. DETAILED DESCRIPTION

[0046] The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0047] A dynamic task planning method based on a hybrid genetic algorithm, steps of the method include:

[0048] Step 1: using a hybrid genetic algorithm to pre-plan according to task information and unmanned aerial vehicle capability information, to obtain a pre-planning scheme, specifically:

[0049] First, initialization is performed, and an initial population is generated; the individual of the initialization is expressed by the following formula:

[0050] X = [x1, x2, …, x I , x I+1 , x I+2 , …, x I+N-1 ]

[0051] Wherein, I represents the total number of tasks, and N represents the total number of unmanned aerial vehicles. Since the number of unmanned aerial vehicles is N, the number of times of segmentation of the task sequence is N-1. x1, x2, …, x I represent tasks, and the value range is [1, I]. x I+1 , x I+2 , …, x I+N-1The segmentation position of the task, the value range is [1, I-1].

[0052] For example, the specific coding process is as shown in the following table Figure 1 The segmentation positions are 2, 5 and 7, indicating that the segmentation is performed after the positions x2, x5 and x7 in the task sequence, and four task sequences are obtained, which are respectively assigned to the four unmanned aerial vehicles. As shown in the following table Figure 1 The task sequence of the unmanned aerial vehicle 1 is 2→4, the task sequence of the unmanned aerial vehicle 2 is 6→1→7, the task sequence of the unmanned aerial vehicle 3 is 3→9, and the task sequence of the unmanned aerial vehicle 4 is 5→8.

[0053] Then, the individual is evaluated according to the constructed evaluation function; the optimization target is the total distance length of the unmanned aerial vehicles to complete the tasks, that is:

[0054] f(X)=l1+l2+…+l n +…+l N

[0055] Wherein, l n represents the flight distance required by the nth unmanned aerial vehicle to complete the task. The unmanned aerial vehicle needs to meet its own endurance time constraint in the process of executing the task, and the solution formula of the time required by the unmanned aerial vehicle to complete the task is as follows:

[0056] t n =l n / v n ,n∈{1,2,…,N}

[0057] Wherein, t n represents the time required by the nth unmanned aerial vehicle to complete the task, and v n represents the flight speed of the nth unmanned aerial vehicle. If the individual does not meet the above unmanned aerial vehicle endurance time constraint, the individual will be discarded in the process of evolution.

[0058] Then, the individual is selected according to the constructed selection function; the solution process of the fitness value of the individual is as shown in the following formula:

[0059]

[0060] Wherein, represents the fitness value of the pth individual of the gth generation, represents the target function value of the pth individual of the gth generation. And respectively represent the minimum and maximum target function values of the gth generation. In order to prevent ε can be set to 0.001.

[0061] The selection of the individual can be based on the following formula:

[0062]

[0063] wherein, represents the pth individual of the gth generation, 1 and 0 represent retaining and discarding the individual respectively, and fv represents the adaptive value threshold.

[0064] The selection operation of the design is adjusted according to the iteration number of the algorithm, in the early stage of evolution, the adaptive value is set to be larger, so as to ensure that the selected individual is more excellent. In the later stage of evolution, the adaptive value is appropriately reduced, so as to ensure that more individuals are selected. The adjustment process is shown in the following formula:

[0065]

[0066] wherein, g represents the iteration number.

[0067] Then, the evolution iteration stage is entered, and when the termination condition is met, the pre-planning scheme is output. The evolution iteration stage mainly includes three types of evolution operators: crossover operator, mutation operator and variable neighborhood operation operator.

[0068] The crossover operation first generates a crossover position, and then exchanges the genes corresponding to the crossover position. The difference is that, in the coding of the present application, the individual task number position and the segmentation position should be independently subjected to crossover and mutation operations. In view of the characteristics of the present problem, the designed crossover operator is as shown in the following formula: Figure 2

[0069] When the crossover operator is used to perform individual crossover operation, the original individual retains its respective task sequence, and the segmentation positions thereof are exchanged. As shown in the following formula: Figure 2 the segmentation position sequence of individual one is 257, and the segmentation position sequence of individual two is 348. After the crossover operation is performed, the segmentation position sequence of new individual one is 348, and the segmentation position sequence of new individual two is 257.

[0070] The mutation operation first randomly selects two mutation individuals. Then, a mutation bit is generated. Finally, the genes on the mutation bit are exchanged, and the genes which are the same as the genes after mutation of the mutation bit in the respective coding are changed to the original genes on the mutation bit. In view of the characteristics of the problem, a parameter adaptive mutation operation is designed. According to the number of tasks, different numbers of mutation bits are set. The designed mutation operator is as shown in the following formula: Figure 3

[0071] In the following formula: Figure 3 an example of the case where the number of mutation bits is 1 is shown. First, a mutation bit c=2 is generated. Then, the genes on the second gene bit of individual one and individual two are exchanged, that is, the 4 on the second gene bit of individual one and the 1 on the second gene bit of individual two are exchanged. Finally, the genes which are the same as the genes after mutation of the mutation bit in the respective coding are changed to the original genes on the mutation bit.​​

[0072] The variable neighborhood operator includes swap, shift and reversal operations. Among them, the number of gene positions operated is adaptively adjusted with the problem size, i.e., the coding length. The designed variable neighborhood operator is shown as Figure 4

[0073] Firstly, the swap(1, 1) in the swap operator is described. The first step of the swap(1, 1) operation is to generate the swap positions, as shown in Figure 4 The two swap positions are 2 and 8. The second step of the swap(1, 1) operation is to swap the genes 4 and 5 in the two swap positions, and then a new individual is obtained. The operations of swap(1, 2) and swap(2, 1) are similar to swap(1, 1), wherein 2 represents that 1 gene position and 2 gene positions are swapped, or 2 gene positions and 1 gene position are swapped.

[0074] Then, the shift(1, 0) in the shift operator is described. The first step of the shift(1, 0) operation is to generate a gene position to be shifted and a position to which the gene position is to be moved. As shown in Figure 4 The generated gene position is 2, and the gene position is to be moved to the rear of gene position 8. The second step of the shift(1, 0) operation is to move the gene 4 in gene position 2 to the rear of the gene 5 in gene position 8. The operation of shift(2, 0) is similar to shift(1, 0), wherein 2 represents that 2 gene positions are shifted.

[0075] Finally, the reversal operator is described. The first step of the reversal operation is to generate a reversal interval, as shown in Figure 4 The reversal interval is 2 to 8. The second step of the reversal operation is to perform the reversal operation on the genes in the reversal interval, i.e., the genes in the original reversal interval are 4617395, and after the reversal operation, they are 5937164.

[0076] Step 2: Load dynamic task information, and sort the dynamic tasks according to the time of occurrence of the dynamic task information;

[0077] Load dynamic task information, and sort the dynamic tasks according to the time of occurrence of the dynamic task information; the dynamic task information is represented by the following formula:

[0078]

[0079] Among them, represents the occurrence time of the new task j, i.e., how long after the start time the new task occurs. x j and y j ​The x and y coordinates represent the dynamic task j, and J represents the number of dynamic tasks.

[0080] Dynamic tasks are sorted in ascending order of their occurrence time.

[0081] Step 3: Use a dynamic allocation mechanism to assign dynamic tasks, and then the drone updates the task sequence.

[0082] A dynamic allocation mechanism is used to assign tasks, and the drone then updates the task sequence. Four dynamic adjustment strategies are designed for different task scenarios: random allocation, cluster center-based allocation, proximity-based allocation, and fuel-remaining-amount-based allocation.

[0083] Next, the detailed process of the four dynamic adjustment strategies will be described:

[0084] (1) Random assignment strategy (DS=1): The main strategy is to randomly assign a new task to a drone when it appears, and the drone can then update its own task list. The random assignment strategy can prevent the general assignment strategy from being applicable only to a certain type of special case due to its fixed assignment rules.

[0085] The specific steps are as follows:

[0086] 1) Traverse all dynamic tasks;

[0087] 2) Generate a random number Uj = rand(N), where Uj represents the UAV number assigned to dynamic task j, rand() is the function to generate a random number, and rand(N) means to generate a random number. The value range of the random number is [1,N].

[0088] 3) Update the drone mission sequence.

[0089] (2) Cluster-center-based allocation strategy (DS=2): The main strategy is to first calculate the task center for each UAV. Then, when a new task appears, it is assigned to the nearest cluster. Finally, the UAVs in this cluster update their task lists. The cluster-center-based allocation strategy is suitable for scenarios where tasks are widely distributed, and the original task can be quickly resumed after the UAV completes the new task.

[0090] The specific steps are as follows:

[0091] 1) Traverse all drone mission sequences;

[0092] 2) Find the cluster center of the task sequence for each UAV. The cluster center C of UAV n is... n =(x n ,y n The solution process for ) is as follows: x n and y n represent the horizontal and vertical coordinates of the cluster center, respectively, x i and y i represent the horizontal and vertical coordinates of the i-th task in the task sequence of the UAV n, respectively, I n represents the length of the task list of the UAV n;

[0093] 3) Traverse all dynamic tasks;

[0094] 4) Solve the Euclidean distance between each dynamic task and the cluster center of the UAV task sequence;

[0095] 5) Get the minimum distance and assign the dynamic task to the UAV;

[0096] 6) The UAV updates the task sequence.

[0097] (3) Assignment strategy based on the nearest distance (DS = 3): The main strategy is to first calculate the distance between each UAV and the location where the new task appears. Then, find the UAV with the minimum distance and assign the new task to this UAV. Finally, this UAV updates its own task list. The assignment strategy based on the nearest distance is suitable for the case where the priority of the dynamically appearing task is high. This strategy can ensure that the UAV can respond quickly when the dynamic task appears.

[0098] The specific steps are as follows:

[0099] 1) Traverse all dynamic tasks;

[0100] 2) Traverse all UAVs;

[0101] 3) According to the appearance time of the dynamic task, solve the current position of each UAV;

[0102] 4) Solve the Euclidean distance between the dynamic task and the current position of the UAV, and get the minimum distance;

[0103] 5) Assign the dynamic task to this UAV;

[0104] 6) The UAV updates the task sequence.

[0105] (4) Assignment strategy based on the remaining fuel quantity (DS = 4): The main strategy is to first calculate the remaining endurance time of each UAV according to the appearance time of the dynamic task. Then, find the UAV with the maximum remaining endurance time and assign the new task to this UAV. Finally, this UAV updates its own task list. The assignment strategy based on the remaining fuel quantity is suitable for the case where the original task may not be completed after the dynamic task appears and the task is assigned. This strategy can ensure that the task is executed to the greatest extent as a whole.

[0106] The specific steps are as follows:

[0107] 1) Traverse all dynamic tasks;

[0108] 2) Traverse all UAVs;

[0109] 3) According to the appearance time of the dynamic task, calculate the fuel remaining amount of each UAV, and obtain the maximum fuel remaining amount;

[0110] 4) Assign the dynamic task to the UAV;

[0111] 5) The UAV updates the task sequence.

[0112] To sum up, the above is only a preferred embodiment of the present application, and is not used to limit the protection scope of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A dynamic task planning method, characterized by, The application relates to a method for dynamic task allocation of unmanned aerial vehicles (UAVs), which comprises the following steps: Step 1: pre-planning is carried out according to task information and UAV capability information by using a hybrid genetic algorithm to obtain a pre-planning scheme, specifically as follows: First, initialization is carried out to generate an initial population; the individual of the initialization is expressed by the following formula: X = [x1, x2,..., x I ,x I+1 ,x I+2 ,…,x I+N-1 ] Wherein, I represents the total number of tasks, N represents the total number of unmanned aerial vehicles; the number of times of segmenting the task sequence is N-1; x1, x2, …, x I represents a task, and the value range is [1, I]; x I+1 I+2 I+N-1 represents the segmentation position of the task, and the value range is [1, I-1];​​ Then, individual selection is carried out according to the constructed selection function; subsequently, an evolution iteration stage is entered, and when the iteration termination condition is met, the pre-planning scheme is outputted; The evolution iteration stage comprises a crossover operation, a mutation operation and a variable neighborhood operation; The crossover operation firstly generates a crossover position, and then the genes corresponding to the crossover position are exchanged; wherein, the individual task number position and the segmentation position are independently subjected to the crossover operation; when the individual crossover operation is carried out, individual one and individual two respectively retain their own task sequences, and the same segmentation positions are exchanged; The mutation operation firstly randomly selects two mutation individuals; then, a mutation bit is generated; finally, the genes at the mutation bit are exchanged, and the genes which are the same as the genes at the mutation bit in the respective codes are changed into the original genes at the mutation bit; according to the number of tasks, different numbers of mutation bits are set; Step 2: dynamic task information is loaded, and the dynamic tasks are sorted according to the time of occurrence of the dynamic task information; Step 3: the dynamic tasks are allocated, and then the UAVs update the task sequences; The method for carrying out individual selection according to the constructed selection function comprises the following steps: individual evaluation is carried out according to the constructed evaluation function; the optimization target is the total path length of the UAVs for completing the tasks, that is: f(x) = l1 + l2 +... + l n +... + l N wherein, l n represents the flight distance required for the nth UAV to complete the task; the UAV needs to meet its own endurance time constraint during the execution of the task, and the solution formula of the time required for the UAV to complete the task is as follows: t n = l n / v n n e {1,2,...,N} where t n represents the time required for the nth UAV to complete the task, v n represents the flight speed of the nth UAV; if the individual does not satisfy the above UAV endurance time constraint, the individual will be discarded in the process of evolution; Then, individual selection is carried out according to the constructed selection function; the solving process of the fitness value of the individual is shown in the following formula: wherein, represents the fitness value of the pth individual of the gth generation, represents the objective function value of the pth individual of the gth generation; and respectively represent the minimum and maximum objective function values of the gth generation; ε = 0.001; The selection of the individual is based on the following formula: wherein, represents the pth individual of the gth generation, 1 and 0 represent retaining and discarding the individual, respectively, and fv represents a threshold value of the adaptive value. When the individual selection is carried out, the fitness value is set to be relatively large in the early evolution stage to ensure that the selected individual is more excellent; in the later evolution stage, the fitness value is adjusted to be small to ensure that more individuals are selected; the adjustment process is shown in the following formula: Wherein, g represents the iteration number.

2. A dynamic task planning method as claimed in claim 1, characterized in that, The variable neighborhood operation comprises exchange, shift and reversal operations; The exchange method comprises the following steps: an exchange bit is generated, the genes at two exchange positions are exchanged, and then a new individual is obtained; The shift method comprises the following steps: a gene position 1 which will be shifted and a gene position 2 which will move the gene are generated; the gene at the gene position 1 is moved to the rear of the gene at the gene position 2; The reversal method comprises the following steps: a reversal interval is generated, and the genes in the reversal interval are subjected to a reversal operation.

3. The dynamic mission planning method of claim 1, wherein, The dynamic tasks are allocated by using a random allocation strategy, specifically as follows: when a new task appears, the new task is randomly allocated to a UAV, and the UAV updates the task list of the UAV itself later.

4. The dynamic mission planning method of claim 1, wherein, The dynamic tasks are allocated by using a clustering center-based allocation strategy, specifically as follows: first, the task center of each UAV is calculated; then, when a new task appears, the new task is allocated to the nearest cluster; finally, the UAVs in the cluster update their own task lists.

5. The dynamic mission planning method of claim 1, wherein, The allocation strategy based on the nearest distance is used to allocate the dynamic task, specifically: first, the distance between each UAV and the location where the new task appears is calculated; then, the UAV with the minimum distance is obtained, and the new task is allocated to the UAV; finally, the UAV updates its own task list.

6. The dynamic mission planning method of claim 1, wherein, The allocation strategy based on the fuel remaining amount is used to allocate the dynamic task, specifically: first, the remaining endurance time of each UAV is calculated according to the time when the dynamic task appears; then, the UAV with the maximum remaining endurance time is obtained, and the new task is allocated to the UAV; finally, the UAV updates its own task list.

Images