Right-angle robot sorting method and system based on grey wolf search strategy

Abstract

The invention relates to the technical field of sorting equipment, in particular to a right-angle robot sorting method and system based on a grey wolf search strategy, and the sorting method comprises the following steps: numbering materials on a conveyor belt, and coding a population according to a double-strand chromosome method; performing population initialization according to a tent chaotic mapping method; a target function is initialized, wherein the target function is the total stroke of all the materials sorted by the mechanical arm; a grey wolf position updating formula in the grey wolf algorithm is used for updating the grey wolf position, variation and recombination operation in the genetic algorithm is used for changing the position of a grey wolf individual, and local optimum is avoided; and carrying out local search operation on the updated head wolf, retaining the optimal individual of the target function, and updating the population. According to the invention, the fine management and optimization of the sorting task are realized, a set of efficient and intelligent path optimization method is provided, the sorting efficiency and accuracy are improved, and the time cost and energy consumption in the sorting process are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of sorting equipment, and particularly to a right-angle robot sorting method and a right-angle robot sorting system based on a grey wolf search strategy. Background Art

[0002] In modern automated production lines, with the expansion of production scale and the increase in product types, the manipulator sorting operation faces increasingly complex challenges. Traditional sorting methods often rely on preset fixed paths or simple rules, resulting in the manipulator possibly making frequent unnecessary movements during the sorting process, with redundant walking paths and low efficiency.

[0003] In order to improve the sorting efficiency, the prior art has tried to introduce various algorithms to optimize the walking paths of individual manipulators. However, for multiple manipulators, even on the basis of path optimization, if there is a lack of a scientific and reasonable search strategy and coordination mechanism, problems such as path conflicts and increased waiting time may still occur when multiple manipulators work simultaneously, affecting the overall sorting efficiency.

[0004] The Grey Wolf Optimization (GWO) algorithm, as a newly emerging swarm intelligence search algorithm, has shown great potential in fields such as path optimization and function optimization due to its characteristics of few control parameters, fast convergence speed, and simple calculation. However, in the application of the manipulator sorting system, the traditional grey wolf algorithm may need to be adaptively improved for the specific scenario of the coordinated work of multiple right-angle robots to better meet the requirements of actual sorting operations. Summary of the Invention

[0005] The present invention aims to at least solve the technical problems existing in the prior art. For this purpose, the present invention proposes a right-angle robot sorting method and a right-angle robot sorting system based on a grey wolf search strategy, which realize the high-efficiency and intelligentization of the material sorting operation on the production line by optimizing the sorting walking path and coordinating the simultaneous work of multiple manipulators.

[0006] A right-angle robot sorting method based on a grey wolf search strategy according to some embodiments of the first aspect of the present invention includes the following steps:

[0007] S100. Initialize the basic parameters of the grey wolf algorithm;

[0008] S200. Number the materials on the conveyor belt and encode the population according to the double-chain chromosome method;

[0009] S300. Initialize the population according to the tent chaotic mapping method;

[0010] S400. Initialize the objective function, which is the total travel distance of the robot arm to sort all materials.

[0011] S500. Determine whether the termination condition of the grey wolf algorithm is satisfied: The termination condition is whether the current iteration number i is less than or equal to the maximum iteration number. If so, execute step S600; otherwise, execute step S800.

[0012] S600. Update the grey wolf positions using the grey wolf position update formula in the grey wolf algorithm, and use the mutation and recombination operations in the genetic algorithm to change the positions of grey wolf individuals to avoid falling into local optima.

[0013] S700. Perform a local search operation on the updated leading wolf, retain the individual with the optimal objective function, update the population, set the previous iteration number i = i + 1, and return to step S500.

[0014] S800. The grey wolf algorithm ends, output the optimal solution that meets the conditions, and decode through this optimal solution to obtain the sorting order of the materials.

[0015] A right-angle robot sorting method based on a grey wolf search strategy according to some embodiments of the first aspect of the present invention has at least the following beneficial effects:

[0016] In the present invention, special coding is performed on grey wolf individuals, and an innovative method of multi-chain chromosomes is adopted to achieve refined management and optimization of sorting tasks. The objective function is set as the total distance that all robot arms need to travel to complete the sorting task, and this is used as the optimization objective to achieve the shortest walking path. In the population initialization stage, the present invention introduces a chaotic mapping initialization method, which significantly improves the randomness and uniformity of the population and lays a solid foundation for subsequent search and optimization. During the grey wolf position update process, the present invention combines the grey wolf position update formula with operation methods such as mutation and recombination of the genetic algorithm. This innovative strategy effectively avoids the local optimum problem and makes the search process more comprehensive and in-depth. The present invention provides a set of efficient and intelligent path optimization methods, improving sorting efficiency and accuracy, and reducing time costs and energy consumption during the sorting process.

[0017] For a right-angle robot sorting method based on a grey wolf search strategy according to some embodiments of the first aspect of the present invention, the specific operation of numbering the materials on the conveyor belt is as follows: Number the materials on the conveyor belt along the x or y direction.

[0018] A right-angle robot sorting method based on the grey wolf search strategy according to some embodiments of the first aspect of the present invention. The specific encoding of the population according to the double-stranded chromosome method is as follows: Encoding grey wolf individuals, adopting a two-dimensional encoding form. The first row is divided into two parts. The first part is the serial number of the material, and the second part is the number of materials that each manipulator needs to sort. The second row represents the position information of the material box to which the material belongs.

[0019] A right-angle robot sorting method based on the grey wolf search strategy according to some embodiments of the first aspect of the present invention. The objective function calculates the total distance that each manipulator starts from the origin, sorts the materials according to the specified order and quantity in the encoding, and returns to the origin, and optimizes the sorting path by minimizing this objective function.

[0020] A right-angle robot sorting method based on the grey wolf search strategy according to some embodiments of the first aspect of the present invention. The specific objective function is: L = min(L1 + L2 + L i ... + L n );

[0021] Where n represents the total number of materials;

[0022]

[0023] Li represents the total distance of the i-th manipulator to sort the materials, and m represents the number of materials that the i-th manipulator needs to sort, which is calculated by the algorithm;

[0024]

[0025] When the i-th manipulator is sorting the j-th material, the distance includes two parts, namely the distance from the previous material box to this material and the distance from this material to the corresponding material box of this material.

[0026] A right-angle robot sorting method based on the grey wolf search strategy according to some embodiments of the first aspect of the present invention. Utilizing the mutation and recombination operations in the genetic algorithm to change the positions of grey wolf individuals and avoid falling into local optima includes: randomly exchanging and inserting genes according to a certain probability to change the encoding of grey wolf individuals.

[0027] A right-angle robot sorting method based on the grey wolf search strategy according to some embodiments of the first aspect of the present invention. The local search operation on the updated lead wolves includes that grey wolf α, β, δ individuals adopt the reverse neighborhood search and insertion neighborhood search methods in the variable neighborhood search algorithm, and retain the individual with the optimal objective function.

[0028] A right-angle robot sorting method based on the grey wolf search strategy according to some embodiments of the first aspect of the present invention. There are two manipulators.

[0029] A right-angle robot sorting system according to some embodiments of the second aspect of the present invention adopts the right-angle robot sorting method based on the grey wolf search strategy described in some embodiments of the first aspect, and includes a conveyor belt, two manipulators, and a plurality of material boxes, and the material boxes and the manipulators are both arranged on both sides of the conveyor belt.

[0030] A right-angle robot sorting system according to some embodiments of the second aspect of the present invention has beneficial effects similar to those of the right-angle robot sorting method based on the grey wolf search strategy described in some embodiments of the first aspect, and will not be elaborated here.

[0031] Additional aspects and advantages of the present invention will be given in part in the following description, become apparent in part from the following description, or be learned through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The above and / or additional aspects and advantages of the present invention will become apparent and be readily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0033] Figure 1 is a flowchart of an embodiment of the first aspect of the present invention.

[0034] Figure 2 is a schematic diagram of the execution of step S200 in an embodiment of the first aspect of the present invention.

[0035] Figure 3 is a schematic diagram of the execution of step S600 in an embodiment of the first aspect of the present invention.

[0036] Figure 4 is a schematic diagram of reversing elements in two randomly selected position intervals in an embodiment of the first aspect of the present invention.

[0037] Figure 5 is a schematic structural diagram of an embodiment of the second aspect of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] Embodiments of the present invention will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, in which the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the accompanying drawings are exemplary only for explaining the present invention and should not be construed as limiting the present invention.

[0039] In the description of the present invention, it should be understood that for the orientation description, such as the orientation or positional relationship indicated by up, down, left, right, front, back, etc., is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred module or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention.

[0040] In the description of the present invention, if the first and second are described only for the purpose of distinguishing technical features, it should not be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence relationship of the indicated technical features.

[0041] In the description of the present invention, unless otherwise clearly defined, words such as setting, installation, connection, etc. should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above words in the present invention in combination with the specific content of the technical solution.

[0042] As Figures 1-4 shown, an embodiment of the first aspect of the present invention provides a right-angle robot sorting method based on the grey wolf search strategy.

[0043] A right-angle robot sorting method based on the grey wolf search strategy includes the following steps:

[0044] S100. Initialize the basic parameters of the grey wolf algorithm;

[0045] S200. Number the materials on the conveyor belt and encode the population according to the double-chain chromosome method;

[0046] S300. Initialize the population according to the tent chaotic mapping method;

[0047] S400. Initialize the objective function, and the objective function is the total travel distance of the manipulator to sort all the materials;

[0048] S500. Determine whether the termination condition of the grey wolf algorithm is satisfied: the termination condition is whether the current iteration number i is less than or equal to the maximum iteration number. If so, execute step S600; otherwise, execute step S800;

[0049] S600. Update the positions of the grey wolves using the grey wolf position update formula in the grey wolf algorithm, and use the mutation and recombination operations in the genetic algorithm to change the positions of the grey wolf individuals to avoid falling into local optima;

[0050] S700. Perform a local search operation on the updated lead wolf, retain the individual with the optimal objective function, update the population, set the previous iteration number i = i + 1, and return to step S500;

[0051] The S800 and the gray wolf algorithm end, and the optimal solution meeting the conditions is output. Decoding is performed through this optimal solution to obtain the sorting order of the materials.

[0052] In the present invention, special coding is performed on gray wolf individuals, and an innovative method of multi-chain chromosomes is adopted to achieve refined management and optimization of sorting tasks. The objective function is set as the total distance that all manipulators need to walk to complete the sorting task, and this is used as the optimization objective to minimize the walking path. In the population initialization stage, the present invention introduces a chaotic mapping initialization method, which significantly improves the randomness and uniformity of the population and lays a solid foundation for subsequent search and optimization. During the gray wolf position update process, the present invention integrates the gray wolf position update formula with operation methods such as mutation and recombination of the genetic algorithm. This innovative strategy effectively avoids the local optimum problem and makes the search process more comprehensive and in-depth. The present invention provides a set of efficient and intelligent path optimization methods, which improve the sorting efficiency and accuracy and reduce the time cost and energy consumption during the sorting process.

[0053] For a right-angle robot sorting method based on a gray wolf search strategy described in this embodiment, there are two manipulators, namely manipulator 1 and manipulator 2. The specific method of numbering the materials on the conveyor belt is: numbering the materials on the conveyor belt along the x or y direction.

[0054] As Figure 3 shown, for a right-angle robot sorting method based on a gray wolf search strategy described in this embodiment, the specific method of encoding the population according to the double-chain chromosome method is: encoding gray wolf individuals, and the encoding adopts a two-dimensional encoding form. The first row is divided into two parts. The first part is the sequence number of the materials, and the second part is the number of materials that each manipulator needs to sort. The second row represents the position information of the material box to which the materials belong. Specifically, each chromosome contains the sorted material numbers, the number of materials sorted by each manipulator, and the position of the material box corresponding to the materials. This encoding method enables the algorithm to directly perform refined management and optimization of sorting tasks, improving the search efficiency and the quality of the solution.

[0055] For a right-angle robot sorting method based on a gray wolf search strategy described in this embodiment, the objective function calculates the total distance that each manipulator starts from the origin, sorts the materials in the order and quantity specified in the encoding, and returns to the origin, and optimizes the sorting path by minimizing this objective function.

[0056] For a right-angle robot sorting method based on a gray wolf search strategy described in this embodiment, the objective function is specifically: L = min(L1 + L2 + L i ... + L n );

[0057] where n represents the total number of materials;

[0058]

[0059] Let \(L_i\) represent the total distance for the \(i\)-th manipulator to sort materials, and \(m\) represent the number of materials that the \(i\)-th manipulator needs to sort, which is calculated by the algorithm;

[0060]

[0061] When the \(i\)-th manipulator is sorting the \(j\)-th material, the distance includes two parts, namely the distance from the previous material box to this material and the distance from this material to the material box corresponding to this material.

[0062] For a right-angle robot sorting method based on the gray wolf search strategy described in this embodiment, the use of mutation and recombination operations in the genetic algorithm to change the positions of gray wolf individuals and avoid falling into local optima includes: randomly swapping and inserting genes according to a certain probability to change the coding of gray wolf individuals. Specifically, as Figure 4 shown, randomly swapping and inserting genes according to a certain probability to change the coding of gray wolf individuals. During the process of updating the positions of gray wolves, the improved gray wolf algorithm incorporates operation methods such as mutation and recombination of the genetic algorithm, effectively avoiding the local optimum problem, making the search process more comprehensive and in-depth, and capable of exploring more potential optimal solutions.

[0063] For a right-angle robot sorting method based on the gray wolf search strategy described in this embodiment, the local search operation on the updated lead wolf includes that the gray wolf \(\alpha\), \(\beta\), and \(\delta\) individuals adopt the reverse neighborhood search and insertion neighborhood search methods in the variable neighborhood search algorithm to retain the individual with the optimal objective function. Specifically, as Figure 5 shown, randomly select two positions, then reverse the elements in this position interval, calculate the objective function, and retain the optimal individual, which can force the current optimal solution (i.e., the lead wolf) to continuously explore new possibilities, thereby obtaining a more superior position and path planning.

[0064] As Figure 5 shown, an embodiment of the second aspect of the present invention provides a right-angle robot sorting system that adopts the right-angle robot sorting method based on the gray wolf search strategy described in the first aspect embodiment, including a conveyor belt, two manipulators, and multiple material boxes. The material boxes and the manipulators are both arranged on both sides of the conveyor belt. Specifically, the two manipulators are respectively manipulator 1 and manipulator 2, and manipulator 1 and manipulator 2 are correspondingly arranged at the corners of the conveyor belt.

[0065] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and purposes of the present invention. The scope of the present invention is defined by the claims and their equivalents.

Claims

1. A right-angle robot sorting method based on a gray wolf search strategy, characterized in that, It includes the following steps: S100. Initialize the basic parameters of the grey wolf algorithm; S200. Number the materials on the conveyor belt and encode the population according to the double-chain chromosome method; S300. Initialize the population according to the tent chaotic mapping method; S400. Initialize the objective function, where the objective function is the total travel distance of the manipulator to sort all materials; S500. Determine whether the termination condition of the grey wolf algorithm is satisfied: the termination condition is whether the current iteration number i is less than or equal to the maximum iteration number. If so, execute step S600; otherwise, execute step S800; S600. Update the positions of the grey wolves using the grey wolf position update formula in the grey wolf algorithm, and use the mutation and recombination operations in the genetic algorithm to change the positions of the grey wolf individuals to avoid falling into local optima; S700. Perform a local search operation on the updated lead wolf, retain the individual with the optimal objective function, update the population, set the previous iteration number i = i + 1, and return to step S500; S800. The grey wolf algorithm ends, output the optimal solution that meets the conditions, and decode through this optimal solution to obtain the sorting order of the materials.

2. The sorting method of a right-angle robot based on the grey wolf search strategy according to claim 1, wherein: The specific operation of numbering the materials on the conveyor belt is: number the materials on the conveyor belt along the x or y direction.

3. A right-angled robot sorting method based on the grey wolf search strategy according to claim 1, characterized in that: The specific operation of encoding the population according to the double-chain chromosome method is: encode the grey wolf individuals. The encoding adopts a two-dimensional encoding form. The first row is divided into two parts. The first part is the sequence number of the materials, and the second part is the number of materials that each manipulator needs to sort. The second row represents the position information of the material box to which the material belongs.

4. A right-angle robot sorting method based on the grey wolf search strategy according to claim 1, characterized in that: The objective function calculates the total distance of each manipulator starting from the origin, sorting the materials in the order and quantity specified in the encoding, and returning to the origin, and optimizes the sorting path by minimizing this objective function.

5. The sorting method of a right-angle robot based on the grey wolf search strategy according to claim 4, wherein: The specific objective function is: L = min(L1 + L2 + L i ... + L n )); Where n represents the total number of materials; Li represents the total travel distance of the i-th manipulator to sort the materials, and m represents the number of materials that the i-th manipulator needs to sort, which is calculated by the algorithm; When the i-th manipulator is sorting the j-th material, the travel distance includes two parts, namely the distance from the previous material box to this material and the distance from this material to the material box corresponding to this material.

6. The sorting method of a right-angle robot based on the grey wolf search strategy according to claim 1, characterized in that: The operation of using the mutation and recombination operations in the genetic algorithm to change the positions of the grey wolf individuals to avoid falling into local optima includes: randomly swapping and inserting genes according to a certain probability to change the encoding of the grey wolf individuals.

7. A right-angle robot sorting method based on the grey wolf search strategy according to claim 1, characterized in that: The operation of performing a local search operation on the updated lead wolf includes that the grey wolf α, β, δ individuals adopt the reverse neighborhood search and insertion neighborhood search methods in the variable neighborhood search algorithm, and retain the individual with the optimal objective function.

8. A right-angle robot sorting method based on the grey wolf search strategy according to claim 1, characterized in that: There are two manipulators.

9. A right-angle robot sorting system, characterized in that, Adopt the right-angle robot sorting method based on the grey wolf search strategy according to any one of claims 1-8, including a conveyor belt, two manipulators, and multiple material boxes. The material boxes and the manipulators are both arranged on both sides of the conveyor belt.

Images