Multi-mechanical-arm task allocation method based on variable neighborhood genetic algorithm

Abstract

The invention discloses a variable neighborhood genetic algorithm-based multi-mechanical-arm task allocation method, which comprises the following steps of enabling m mechanical arms to execute n tasks, randomly setting a sequence of the n tasks, obtaining a task sequence, coding the task sequence based on a genetic algorithm, performing population initialization, and performing iteration based on the variable neighborhood genetic algorithm, stopping iteration until the number of iterations is equal to the maximum number of iterations, and outputting the optimal solution as a final optimal solution; decoding is carried out, a set Q * is obtained after decoding, and m task sequences in the set Q * are distributed to the corresponding mechanical arms; and each mechanical arm executes a task in a clockwise direction, and completes collision-free motion path planning by adopting a cubic bounding box method during task execution. According to the multi-mechanical-arm and multi-task allocation method, the multiple mechanical arms can accurately and efficiently complete tasks in different working environments, and the problems that in the prior art, the task allocation efficiency of the multiple mechanical arms is low, and the working environments are complex and changeable are effectively solved.

Description

Technical Field

[0001] The invention belongs to the technical field of robot arm control, and in particular relates to a multi-robot arm task allocation method based on a variable neighborhood genetic algorithm. Background Art

[0002] At present, with the rapid maturity and development of automation technology, the application of multi-robot system collaborative work is becoming more and more widespread. Faced with multi-task, multi-demand and complex work scenarios, multi-robot system has the advantages of high work efficiency and low use cost. However, in fact, under the influence of many factors such as variable tasks and uncertain environmental information, most of the solution sets obtained by traditional genetic algorithms are concentrated in a specific range. It is difficult to obtain an approximate solution that is closer to the optimal solution in the global distribution according to the distribution of task points, and after a certain number of iterations, it will fall into a local optimal situation and cannot continue to search for better results. Therefore, how to reasonably and efficiently assign all tasks to different robotic arms has become one of the technical difficulties in the industry. Summary of the invention

[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to propose a multi-manipulator task allocation method based on a variable neighborhood genetic algorithm, which calculates the sum of the path costs of all manipulators to complete all (to be) executed tasks, takes the sum of the path costs as the objective function, and transforms the solution of the multi-manipulator task allocation problem into the solution of the execution task sequence corresponding to the minimum objective function value. The problem of low efficiency of task allocation, poor allocation results, and inability to adapt to the complex and changeable working environment in the prior art of multi-manipulator collaborative work is effectively solved.

[0004] The purpose of the present invention is achieved through the following technical solutions.

[0005] A multi-manipulator task allocation method based on variable neighborhood genetic algorithm comprises the following steps:

[0006] S1, make m robotic arms perform n tasks, the initial positions of the m robotic arms are the same, n>m, randomly set the order of n tasks to obtain a task sequence, encode the task sequence based on a genetic algorithm to obtain an initial chromosome individual, set the population size and initialize the initial chromosome individual to obtain an initial chromosome population;

[0007] S2, iterate in the order of S2-1, S2-2, S2-3 and S2-4 until the number of iterations is equal to the maximum number of iterations, terminate the iteration, and output the optimal solution as the final optimal solution;

[0008] S2-1, calculate the fitness function values ​​of all chromosome individuals in the initial chromosome population, and perform a selection operation according to the fitness function values ​​of the chromosome individuals to obtain the chromosome population after the selection operation; set the mutation probability and perform a mutation operation on the chromosome population after the selection operation according to the mutation probability to obtain the chromosome population after the mutation operation; calculate the fitness function values ​​of all chromosome individuals in the chromosome population after the mutation operation, and take the chromosome individual with the largest fitness function value as the current optimal solution, wherein the fitness function value of each chromosome individual is the inverse of the objective function value of the chromosome individual;

[0009] S2-2, determine the selected neighborhood structure: judge the number of current iterations. When it is the first iteration, set the initial weights of the four neighborhood structures to 1, and randomly select one neighborhood structure from the four neighborhood structures as the selected neighborhood structure; when the number of iterations is greater than 1, select a neighborhood structure with a weight less than 4 and the largest weight from the four neighborhood structures as the selected neighborhood structure.

[0010] S2-3, search for the current optimal solution based on the selection neighborhood structure, and obtain the searched solution; take the searched solution and the current optimal solution as chromosome individuals, calculate the objective function values ​​of the searched solution and the current optimal solution, and judge the size relationship between the objective function value of the searched solution and the objective function value of the current optimal solution: if the objective function value of the searched solution is greater than or equal to the objective function value of the current optimal solution, then discard the searched solution, output the current optimal solution as the optimal solution, and judge whether the weight of the selection neighborhood structure of this search is 1, if not 1, reduce the weight of the selection neighborhood structure of this search by 1; if the objective function value of the searched solution is less than the objective function value of the current optimal solution, then take the searched solution as the optimal solution and output it, and judge whether the weight of the selection neighborhood structure of this search is 4, if not 4, increase the weight of the selection neighborhood structure of this search by 1;

[0011] S2-4, determine whether it is the maximum number of iterations: if it is the maximum number of iterations, terminate the iteration and output the optimal solution of this iteration as the final optimal solution; if it is not the maximum number of iterations, replace the chromosome individual with the smallest fitness function value in the initial chromosome population with the optimal solution and continue iterating;

[0012] S3, randomly generate m-1 breakpoint values ​​to divide the final optimal solution into m segments, decode each segment of the final optimal solution from left to right, and obtain the set after decoding is the i-th robot arm R i The sequence of tasks to be performed; the set Q *The m task sequences in are assigned to the corresponding robotic arms; each robotic arm performs the task in a clockwise direction and uses the cubic bounding box method to complete collision-free motion path planning during the execution of the task.

[0013] In S2, the method for calculating the objective function value of a chromosome individual is:

[0014] Randomly generate m-1 breakpoint values ​​to divide the chromosome into m segments, and decode each segment of the chromosome from left to right. After decoding, the task sequence executed by the m robotic arms is a set Q, Q = {Q i |i=1,…m}, where Q i is the i-th robot arm R i The task sequence to be executed, Q i Including g i tasks, 1 <g i <n;

[0015] Calculate the i-th robot arm R i Execute and complete the task sequence Q i The path cost C i , C i The calculation formula is as follows:

[0016]

[0017] In the formula, Represents the i-th robot arm R i Execute task q i1 When the robot arm R i The initial position o moves to task q i1 The path cost consumed during the location process, L i1 is the i-th robot arm R i From the initial position o to task q i1 Euclidean distance of the location; Indicates the robot arm R i Execute task sequence Q i The path cost consumed when performing the a+1th task in L i(a+1) For the robot arm R i From task q ia Location to task q i(a+1) Euclidean distance of the location; Represents the i-th robot arm R i implement Time by Task The path cost consumed by moving from the current position to the initial position o, L ois the i-th robot arm R i From the task The Euclidean distance from the current position to the initial position o; all the above Euclidean distances can be calculated according to the task sequence Q i Calculated.

[0018] Calculate the objective function value Cost, the calculation formula of Cost is:

[0019]

[0020] The fitness function value Fitness calculation formula is as follows:

[0021]

[0022] In S2, the selection operation adopts the tournament selection strategy. The tournament selection strategy is to repeat the following operations until the size of the chromosome population after the selection operation is consistent with the size of the initial chromosome population: each time a certain number of chromosome individuals are randomly selected from the initial chromosome population, and the optimal chromosome individuals are selected according to the fitness function values ​​of the chromosome individuals to enter the chromosome population after the selection operation.

[0023] In S2, the mutation operation adopts the exchange mutation strategy. The exchange mutation strategy performs the mutation operation on the chromosome individuals determined to be mutated in the chromosome population after the selection operation: randomly select two positions a and b in the chromosome individuals, and then exchange the gene at position a with the gene at position b, while the genes at other positions remain unchanged.

[0024] In S2, there are four types of neighborhood structures: two-point exchange neighborhood structure, insertion neighborhood structure, reversed order neighborhood structure, and shuffled exchange neighborhood structure.

[0025] In S1, the task sequence is encoded using segmented sequence encoding.

[0026] Compared with the prior art, the present invention has the following beneficial effects:

[0027] 1. The present invention comprehensively considers the working status of multiple robotic arms and the distribution of task points, and proposes a multi-robotic arm multi-task allocation method based on a variable neighborhood genetic algorithm. The multi-robotic arm task allocation method has the advantages of high efficiency, safety, reliability, and automation. The multi-robotic arm multi-task allocation method of the present invention enables multiple robotic arms to complete tasks accurately and efficiently in different working environments, effectively solving the problems of low efficiency of multi-robotic arm task allocation and complex and changeable working environment in the prior art, and is expected to be widely used in different industrial production, services, scientific and technological research and other fields.

[0028] 2. The present invention comprehensively considers the motion paths of each robotic arm during the entire task execution process when multiple robotic arms are performing tasks, and uses the cubic bounding box method to quickly calculate the collision-free motion paths of multiple robotic arms during the task allocation process, so that multiple robotic arms can smoothly reach the task point, thereby improving the safety and practicality of multiple robotic arms when performing tasks.

[0029] 3. The present invention improves the traditional genetic algorithm, introduces a variable neighborhood search algorithm, designs four neighborhood structures to expand the search range of the variable neighborhood search algorithm, and adopts a weighted scoring mechanism to dynamically select different neighborhood structures for search, so that the initial chromosome population can evolve rapidly in the direction of excellent individuals, giving full play to the global search capability of the genetic algorithm and the local search capability of the variable neighborhood search algorithm, improving the convergence speed of multiple robotic arms in task allocation, and obtaining a higher quality of the final optimal solution.

[0030] 4. The present invention adopts a variable neighborhood genetic algorithm to obtain better solution results. The path cost consumed when multiple robotic arms perform tasks is smaller and the task allocation is more balanced. At the same time, the variable neighborhood genetic algorithm has better convergence. The total objective function value (sum of path costs) solved by the multi-robotic arm multi-task allocation method based on the variable neighborhood genetic algorithm is reduced by 16.8% and 12.5% ​​respectively compared with the genetic algorithm and the variable neighborhood search algorithm. This verifies that the multi-robotic arm multi-task allocation method based on the variable neighborhood genetic algorithm of the present invention is more superior in solving the multi-robotic arm task allocation problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a comparison chart of different algorithm iteration results;

[0032] Figure 2 This is the result diagram of multi-robot task allocation of GA algorithm;

[0033] Figure 3 This is the result diagram of VNS algorithm multi-robot task allocation;

[0034] Figure 4 This is the result diagram of multi-robot task allocation of the GAVNS algorithm. DETAILED DESCRIPTION

[0035] A multi-manipulator task allocation method based on a variable neighborhood genetic algorithm of the present invention is described in detail below in conjunction with the accompanying drawings.

[0036] In the following embodiments, the problem of multi-robot task allocation in collaborative work is: efficiently and reasonably allocate the execution tasks consisting of n spherical objects (small balls) within the multi-robot workspace.

[0037] Assumptions: Each independent robot arm is isomorphic and has the same execution capabilities; each ball object in the task can only be completed by one robot arm at a time.

[0038] Example 1

[0039] A multi-manipulator task allocation method based on variable neighborhood genetic algorithm comprises the following steps:

[0040] S1, make m robotic arms perform n tasks, the initial positions of the m robotic arms are the same, n>m, randomly set the order of n tasks to obtain a task sequence, encode the task sequence based on a genetic algorithm to obtain an initial chromosome individual, set the population size and initialize the initial chromosome individual to obtain an initial chromosome population;

[0041] In S1, the task sequence is encoded using a segmented sequence encoding method (Wen Xinrong. Research on task allocation and path planning of multiple mobile robots based on intelligent warehouses [D]. Donghua University, 2023.). The segmented sequence encoding method is not only simple to run, but also can effectively handle optimization problems with sequential relationships, ensuring that the work of each robot arm is more balanced and reasonable, and improving the quality of the initial chromosome individuals. In this embodiment, the population size is set to 100.

[0042] S2, iterate in the order of S2-1, S2-2, S2-3 and S2-4 until the number of iterations is equal to the maximum number of iterations, terminate the iteration, and output the optimal solution as the final optimal solution; in this embodiment, the maximum number of iterations is set to 500 times;

[0043] S2-1, calculate the fitness function values ​​of all chromosome individuals in the initial chromosome population, and perform a selection operation according to the fitness function values ​​of the chromosome individuals to obtain the chromosome population after the selection operation; set the mutation probability and perform a mutation operation on the chromosome population after the selection operation according to the mutation probability to obtain the chromosome population after the mutation operation; calculate the fitness function values ​​of all chromosome individuals in the chromosome population after the mutation operation, and take the chromosome individual with the largest fitness function value as the current optimal solution, wherein the fitness function value of each chromosome individual is the inverse of the objective function value of the chromosome individual;

[0044] S2-2, determine the selected neighborhood structure: judge the number of current iterations. When it is the first iteration, set the initial weights of the four neighborhood structures to 1, and randomly select one neighborhood structure from the four neighborhood structures as the selected neighborhood structure; when the number of iterations is greater than 1, select a neighborhood structure with a weight less than 4 and the largest weight from the four neighborhood structures as the selected neighborhood structure.

[0045] S2-3, search for the current optimal solution based on the selection neighborhood structure, and obtain the searched solution; take the searched solution and the current optimal solution as chromosome individuals, calculate the objective function values ​​of the searched solution and the current optimal solution, and judge the size relationship between the objective function value of the searched solution and the objective function value of the current optimal solution: if the objective function value of the searched solution is greater than or equal to the objective function value of the current optimal solution, then discard the searched solution, output the current optimal solution as the optimal solution, and judge whether the weight of the selection neighborhood structure of this search is 1, if not 1, then reduce the weight of the selection neighborhood structure of this search by 1 (if it is 1, then do not select the optimal solution for this search); The weight of the selected neighborhood structure of the search is not subjected to any operation); if the objective function value of the searched solution is less than the objective function value of the current optimal solution, the searched solution is taken as the optimal solution and output, and it is determined whether the weight of the selected neighborhood structure of this search is 4, if not 4, the weight of the selected neighborhood structure of this search is increased by 1 (if it is 4, no operation is performed on the weight of the selected neighborhood structure of this search); that is, step S2-3 determines the selected neighborhood structure with emphasis and searches according to the weighted scoring mechanism, so that the variable neighborhood search algorithm is more efficient and flexible, and effectively improves the local search capability, flexibility and efficiency of the variable neighborhood search algorithm;

[0046] S2-4, determine whether it is the maximum number of iterations: if it is the maximum number of iterations, terminate the iteration and output the optimal solution of this iteration as the final optimal solution; if it is not the maximum number of iterations, replace the chromosome individual with the smallest fitness function value in the initial chromosome population with the optimal solution and continue iterating;

[0047] In S2, the method for calculating the objective function value of a chromosome individual is:

[0048] Randomly generate m-1 breakpoint values ​​to divide the chromosome into m segments, and decode each segment of the chromosome from left to right. After decoding, the task sequence executed by the m robotic arms is a set Q, Q = {Q i |i=1,…m}, where Q i is the i-th robot arm R i The task sequence to be executed, Q i Including g i tasks, 1 <g i <n;

[0049] Calculate the i-th robot arm R i Execute and complete the task sequence Q i The path cost C i , C i The calculation formula is as follows:

[0050]

[0051] In the formula, Represents the i-th robot arm R i Execute task q i1 When the robot arm R i The initial position o moves to task q i1 The path cost consumed during the location process, L i1 is the i-th robot arm R i From the initial position o to task q i1 Euclidean distance of the location; Indicates the robot arm R i Execute task sequence Q i The path cost consumed when performing the a+1th task in the robot arm R i By q ia The task location moves to q i(a+1) The path cost consumed by the task location), L i(a+1) For the robot arm R i From task q ia Location to task q i(a+1) Euclidean distance of the location; Represents the i-th robot arm R i implement Time by Task The path cost consumed by moving from the current position to the initial position o, L o is the i-th robot arm R i From the task The Euclidean distance from the current position to the initial position o.

[0052] Calculate the objective function value Cost (the sum of the path costs of m robotic arms performing n tasks). The calculation formula for Cost is:

[0053]

[0054] The fitness function value Fitness calculation formula is as follows:

[0055]

[0056] In S2, the selection operation adopts a tournament selection strategy, which is to repeat the following operations until the size of the chromosome population after the selection operation is consistent with the size of the initial chromosome population: randomly select a certain number of chromosome individuals from the initial chromosome population each time (in this embodiment, the certain number is set to 10), and select the best chromosome individuals according to the fitness function values ​​of the chromosome individuals to enter the chromosome population after the selection operation;

[0057] In S2, the mutation operation adopts the exchange mutation strategy, and the exchange mutation strategy performs the mutation operation on the chromosome individuals determined to be mutated in the chromosome population after the selection operation: randomly select two positions a and b in the chromosome individuals, and then exchange the gene at position a with the gene at position b, and the genes at the other positions remain unchanged. The mutation operation can improve the diversity of the chromosome population after the mutation operation and the local search ability of the genetic algorithm. In this embodiment, the mutation probability is set to 0.05.

[0058] In S2, the four neighborhood structures are: two-point exchange neighborhood structure, insertion neighborhood structure, reversed order neighborhood structure, and shuffled exchange neighborhood structure;

[0059] The variable neighborhood search algorithm uses four neighborhood structures to expand the search range and find the final optimal solution for the objective function (the sum of path costs) by increasing the diversity of the neighborhood structure.

[0060] S3, randomly generate m-1 breakpoint values ​​to divide the final optimal solution into m segments, and decode each segment of the final optimal solution from left to right. After decoding, the set Q is obtained. * , is the i-th robot arm R i The sequence of tasks to be performed; the set Q * Assign the m task sequences in the task sequence to the corresponding robot arm (assign the task sequence Assigned to robot arm R i ); Each manipulator performs tasks in a clockwise direction, and during the execution of the task, the cubic bounding box method (Yue Xu, Zhou Haibo, Shao Yanpeng, et al. Improved artificial potential field method for manipulator joint space obstacle avoidance planning [J]. Mechanical Transmission, 2023, 47(10): 23-30.) is used to complete collision-free motion path planning. The cubic bounding box method has a small amount of calculation and a short calculation time, which meets the requirements of real-time control and improves the operation efficiency of the manipulator.

[0061] In the multi-robot task allocation method of Example 1, the number of robots m=3 and the number of tasks n=30.

[0062] Example 2

[0063] Based on the m robotic arms performing n tasks in Example 1, multi-robotic arm task allocation is performed according to a genetic algorithm (GA).

[0064] Example 3

[0065] Based on the m robotic arms performing n tasks in Example 1, multi-robotic arm task allocation is performed according to the variable neighborhood search algorithm (VNS).

[0066] Under the same parameter conditions, the convergence speed and optimization ability of the variable neighborhood genetic algorithm (GAVNS), the genetic algorithm (GA) and the variable neighborhood search algorithm (VNS) are compared and simulated. The 30 tasks are represented by numbers 1 to 30 respectively. The iteration curves of the multi-manipulator task allocation method of Examples 1 to 3 are shown in Figure 2. Figure 1 As shown, from Figure 1 It can be seen that the multi-manipulator task allocation method based on the variable neighborhood genetic algorithm (GAVNS) of Example 1 of the present invention has a faster convergence speed, and when the number of iterations reaches the maximum, the corresponding objective function value is the lowest, and the optimization ability is stronger.

[0067] The simulation results of the multi-manipulator task allocation method of Examples 1 to 3 are as follows: Figure 2 , Figure 3 , Figure 4 The comparison results of the three multi-robot task allocation methods are shown in Table 1.

[0068] Table 1 Multi-manipulator task execution sequence table

[0069]

[0070]

[0071] From the above data, it can be seen that the objective function value (sum of path costs) of the task sequence solved by the multi-robot task allocation method based on the variable neighborhood genetic algorithm of the present invention is reduced by 16.8% and 12.5% ​​respectively compared with the genetic algorithm and the variable neighborhood search algorithm. The multi-robot task allocation method based on the variable neighborhood genetic algorithm (GAVNS) has the smallest objective function value, which is 5384.8.

[0072] The present invention is described above by way of example. It should be noted that, without departing from the core of the present invention, any simple deformation, modification or other equivalent replacement that can be made by those skilled in the art without inventive effort falls within the protection scope of the present invention.

Claims

1. A multi-manipulator task allocation method based on variable neighborhood genetic algorithm, characterized in that: The following steps are involved: S1, make m robotic arms perform n tasks, the initial positions of the m robotic arms are the same, n>m, randomly set the order of n tasks to obtain a task sequence, encode the task sequence based on a genetic algorithm to obtain an initial chromosome individual, set the population size and initialize the initial chromosome individual to obtain an initial chromosome population; S2, iterate in the order of S2-1, S2-2, S2-3 and S2-4 until the number of iterations is equal to the maximum number of iterations, terminate the iteration, and output the optimal solution as the final optimal solution; S2-1, calculate the fitness function values ​​of all chromosome individuals in the initial chromosome population, and perform a selection operation according to the fitness function values ​​of the chromosome individuals to obtain the chromosome population after the selection operation; set the mutation probability and perform a mutation operation on the chromosome population after the selection operation according to the mutation probability to obtain the chromosome population after the mutation operation; calculate the fitness function values ​​of all chromosome individuals in the chromosome population after the mutation operation, and take the chromosome individual with the largest fitness function value as the current optimal solution, wherein the fitness function value of each chromosome individual is the inverse of the objective function value of the chromosome individual; S2-2, determine the selected neighborhood structure: determine the number of current iterations, when it is the first iteration, set the initial weights of the four neighborhood structures to 1, and randomly select one of the four neighborhood structures as the selected neighborhood structure; when the number of iterations is greater than 1, select a neighborhood structure with a weight less than 4 and the largest weight among the four neighborhood structures as the selected neighborhood structure; S2-3, search for the current optimal solution based on the selection neighborhood structure, and obtain the searched solution; take the searched solution and the current optimal solution as chromosome individuals, calculate the objective function values ​​of the searched solution and the current optimal solution, and judge the size relationship between the objective function value of the searched solution and the objective function value of the current optimal solution: if the objective function value of the searched solution is greater than or equal to the objective function value of the current optimal solution, then discard the searched solution, output the current optimal solution as the optimal solution, and judge whether the weight of the selection neighborhood structure of this search is 1, if not 1, reduce the weight of the selection neighborhood structure of this search by 1; if the objective function value of the searched solution is less than the objective function value of the current optimal solution, then take the searched solution as the optimal solution and output it, and judge whether the weight of the selection neighborhood structure of this search is 4, if not 4, increase the weight of the selection neighborhood structure of this search by 1; S2-4, determine whether it is the maximum number of iterations: if it is the maximum number of iterations, terminate the iteration and output the optimal solution of this iteration as the final optimal solution; if it is not the maximum number of iterations, replace the chromosome individual with the smallest fitness function value in the initial chromosome population with the optimal solution and continue iterating; S3, randomly generate m-1 breakpoint values ​​to divide the final optimal solution into m segments, and decode each segment of the final optimal solution from left to right. After decoding, the set Q is obtained. * , is the i-th robot arm R i The sequence of tasks to be performed; the set Q * The m task sequences in are assigned to the corresponding robotic arms; each robotic arm performs the task in a clockwise direction and uses the cubic bounding box method to complete collision-free motion path planning during the execution of the task.

2. The multi-robot task allocation method according to claim 1, characterized in that: In S2, the method for calculating the objective function value of a chromosome individual is: Randomly generate m-1 breakpoint values ​​to divide the chromosome into m segments, and decode each segment of the chromosome from left to right. After decoding, the task sequence executed by the m robotic arms is a set Q, Q = {Q i |i=1,…m}, where Q i is the i-th robot arm R i The task sequence to be executed, Q i Including g i tasks, 1 <g i <n; Calculate the i-th robot arm R i Execute and complete the task sequence Q i The path cost C i , C i The calculation formula is as follows: In the formula, Represents the i-th robot arm R i From the initial position o to task q i1 Euclidean distance of the location; Indicates the robot arm R i From task q ia Location to task q i(a+1) Euclidean distance of the location; Represents the i-th robot arm R i From the task The Euclidean distance from the current position to the initial position o; all the above Euclidean distances can be calculated according to the task sequence Q i get; Calculate the objective function value Cost, the calculation formula of Cost is:

3. The multi-robot task allocation method according to claim 1 or 2, characterized in that: The fitness function value Fitness calculation formula is as follows:

4. The multi-robot task allocation method according to claim 3, characterized in that: In S2, the selection operation adopts the tournament selection strategy. The tournament selection strategy is to repeat the following operations until the size of the chromosome population after the selection operation is consistent with the size of the initial chromosome population: each time a certain number of chromosome individuals are randomly selected from the initial chromosome population, and the optimal chromosome individuals are selected according to the fitness function values ​​of the chromosome individuals to enter the chromosome population after the selection operation.

5. The multi-robot task allocation method according to claim 1, characterized in that: In S2, the mutation operation adopts the exchange mutation strategy. The exchange mutation strategy performs the mutation operation on the chromosome individuals determined to be mutated in the chromosome population after the selection operation: randomly select two positions a and b in the chromosome individuals, and then exchange the gene at position a with the gene at position b, while the genes at other positions remain unchanged.

6. The multi-robot task allocation method according to claim 1, characterized in that: In S2, there are four types of neighborhood structures: two-point exchange neighborhood structure, insertion neighborhood structure, reversed order neighborhood structure, and shuffled exchange neighborhood structure.

7. The multi-robot task allocation method according to claim 1, characterized in that: In S1, the task sequence is encoded using segmented sequence encoding.

Images