Robot tool switching methods, systems, storage media, and computers

Abstract

This invention provides a robot tool switching method, system, storage medium, and computer. The method includes: acquiring the robot's bus structure and resolving the bus structure to obtain the bus addresses of each end-effector of the robot; acquiring the sequence data of each end-effector, constructing a sequence calculation model based on a tool selection algorithm, and using the sequence calculation model to perform sequence calculations on each sequence data to obtain a tool sequence set corresponding to each sequence data; constructing a parsing archive set and using the parsing archive set to iteratively optimize the sequence calculation model to obtain a corresponding sequence probability model; analyzing each tool sequence set according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set; reconfiguring the valve islands for sequence data with sequence selection probabilities greater than a preset probability threshold to generate corresponding tool switching parameters, and controlling the robot to switch each end-effector according to the tool switching parameters.

Description

Technical Field

[0001] This invention relates to the field of robotics, and in particular to a method, system, storage medium, and computer for switching robotic tools. Background Technology

[0002] With the rapid development of technology and the improvement of people's living standards, automobiles have become an indispensable part of people's travel. In automobile production and processing, robotic manufacturing systems are usually used, which utilize robots' recognition, positioning, and inspection technologies to significantly improve production efficiency and product quality.

[0003] In automobile manufacturing, robots are often equipped with various end-effectors to enable them to adapt to different processes. However, with the increase in the types of end-effectors and the significant increase in production capacity, the complexity of information during production makes it difficult to control the robot's tool switching. Coordinated production and work plans are hard to achieve. Furthermore, with the increase in the types of tools, the time spent switching tools during the entire production process also gradually increases. Ultimately, this leads to problems such as failure to complete production within the delivery period, inability to guarantee production quality, and loss of economic benefits. Summary of the Invention

[0004] Based on this, the purpose of the present invention is to provide a robot tool switching method, system, storage medium, and computer to at least address the shortcomings of the aforementioned related technologies.

[0005] This invention proposes a robot tool switching method, comprising:

[0006] Obtain the robot's bus structure and perform address parsing on the bus structure to obtain the bus addresses of each end effector of the robot;

[0007] The sequence data of each of the terminal tools are obtained, a sequence calculation model is constructed based on the tool selection algorithm, and the sequence calculation model is used to perform sequence calculation on each of the sequence data to obtain the tool sequence set corresponding to each of the sequence data.

[0008] Construct a parsed archive set and use the parsed archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model;

[0009] The tool sequence set is analyzed one by one according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set;

[0010] The sequence data whose selection probability is greater than a preset probability threshold are reconfigured into valve islands to generate corresponding tool switching parameters, and the robot is controlled to switch each end tool according to the tool switching parameters.

[0011] Furthermore, the step of performing sequence calculations on each of the sequence data using the sequence calculation model to obtain the tool sequence set corresponding to each of the sequence data includes:

[0012] In the sequence calculation model, a tool is added to select the sequence matrix, and the tool is used to select the sequence matrix to perform iterative calculations on each sequence data to obtain the matching degree of each sequence data.

[0013] Based on the matching degree, each sequence data is uniformly distributed to obtain a set of tool sequences corresponding to each sequence data.

[0014] Furthermore, the steps of constructing a parsed archive set and using the parsed archive set to iteratively optimize the sequence computation model to obtain the corresponding sequence probability model include:

[0015] The parsing archive set is used to calculate all non-controlling solutions during the iterative search of the sequence computation model, and the newly acquired non-controlling solutions are recorded according to the optimization archive set corresponding to the parsing archive set to form an iterative solution set;

[0016] The sequence computation model is optimized based on the iterative solution set and all the non-controlling solutions to obtain the corresponding sequence probability model.

[0017] Furthermore, the step of analyzing each sequence in the tool sequence set according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set includes:

[0018] Initialize the parameters of the sequence probability model and mark the iteration count of the sequence probability model as 0;

[0019] The tool sequence set is randomly sampled to obtain preliminary sampled data, and the sequence probability model is updated using the mutation probability. The updated sequence probability model is then used to perform secondary sampling based on the same sampling parameters as the random sampling to obtain secondary sampled data.

[0020] The preliminary sampling data and the secondary sampling data are compared to obtain sampling difference data. The sampling difference data is then used to analyze the tool sequence set to obtain the sequence selection probability of each sequence data in the tool sequence set.

[0021] This invention also proposes a robot tool switching system, comprising:

[0022] The address acquisition module is used to acquire the robot's bus structure and perform address parsing on the bus structure to obtain the bus address of each end tool of the robot.

[0023] The sequence calculation module is used to acquire the sequence data of each of the terminal tools, construct a sequence calculation model based on the tool selection algorithm, and use the sequence calculation model to perform sequence calculation on each of the sequence data to obtain the tool sequence set corresponding to each of the sequence data.

[0024] An iterative optimization module is used to construct a parsed archive set and use the parsed archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model.

[0025] The sequence analysis module is used to analyze the tool sequence set one by one according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set;

[0026] The tool switching module is used to reconfigure the valve island for sequence data whose sequence selection probability is greater than a preset probability threshold, so as to generate corresponding tool switching parameters, and control the robot to switch each end tool according to the tool switching parameters.

[0027] Furthermore, the sequence calculation module includes:

[0028] An iterative calculation unit is used to add a tool selection sequence matrix to the sequence calculation model and use the tool selection sequence matrix to perform iterative calculations on each of the sequence data to obtain the matching degree of each of the sequence data.

[0029] A distribution processing unit is used to uniformly distribute each of the sequence data based on the matching degree to obtain a set of tool sequences corresponding to each of the sequence data.

[0030] Furthermore, the iterative optimization module includes:

[0031] The iterative processing unit is used to calculate all non-controlling solutions when performing iterative search on the sequence computation model using the parsed archive set, and to record the newly acquired non-controlling solutions in each iterative search according to the optimization archive set corresponding to the parsed archive set, so as to form an iterative solution set;

[0032] The model optimization unit is used to optimize the sequence computation model based on the iterative solution set and all the non-controlling solutions to obtain the corresponding sequence probability model.

[0033] Furthermore, the sequence analysis module includes:

[0034] The parameter configuration unit is used to initialize the parameters of the sequence probability model and mark the iteration count of the sequence probability model as 0;

[0035] The data sampling unit is used to randomly sample the tool sequence set to obtain preliminary sampling data, update the sequence probability model using the mutation probability, and perform secondary sampling based on the same sampling parameters as the random sampling using the updated sequence probability model to obtain secondary sampling data.

[0036] The sequence analysis unit is used to compare the preliminary sampling data and the secondary sampling data to obtain sampling difference data, and to analyze the tool sequence set using the sampling difference data to obtain the sequence selection probability of each sequence data in the tool sequence set.

[0037] The present invention also proposes a storage medium on which a computer program is stored, which, when executed by a processor, implements the above-described robot tool switching method.

[0038] The present invention also proposes a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above-described robot tool switching method.

[0039] Compared with the prior art, the beneficial effects of the present invention are as follows: by performing sequence calculations on the sequence data of the end-effectors, a corresponding set of tool sequences is obtained. The set of tool sequences is then analyzed one by one according to the sequence probability model to obtain the sequence selection probability. Sequence data with sequence selection probabilities greater than a preset probability threshold are reconfigured into valve islands to generate corresponding tool switching parameters. The robot is then controlled to switch each end-effector according to the tool switching parameters. By performing multi-objective optimization on the basis of single-objective optimization, using the sequence selection probability to construct the tool switching parameters, and completing the switching of the robot's end-effectors based on the tool switching parameters, the tool switching speed is improved, thereby increasing the working efficiency and production capacity of the production line. Attached Figure Description

[0040] Figure 1 This is a flowchart of the robot tool switching method in the first embodiment of the present invention;

[0041] Figure 2 for Figure 1 Detailed flowchart of step S102;

[0042] Figure 3 for Figure 1 Detailed flowchart of step S103;

[0043] Figure 4 for Figure 1 Detailed flowchart of step S104;

[0044] Figure 5 This is a structural block diagram of the robot tool switching system in the second embodiment of the present invention;

[0045] Figure 6 This is a structural block diagram of the computer in the third embodiment of the present invention.

[0046] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0047] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0049] Example 1

[0050] Please see Figure 1 The diagram illustrates a robot tool switching method according to a first embodiment of the present invention, the method specifically including steps S101 to S105:

[0051] S101, Obtain the bus structure of the robot and perform address parsing on the bus structure to obtain the bus address of each end tool of the robot;

[0052] In practice, the relevant software of the robot is turned on and its corresponding bus structure is obtained. The address of the bus structure is resolved to obtain the bus address of all end tools of the robot. It can be understood that when the robot needs to be adapted to the end tool, it will be adapted through the bus address.

[0053] S102, obtain the sequence data of each of the end tools, construct a sequence calculation model based on the tool selection algorithm, and use the sequence calculation model to perform sequence calculation on each of the sequence data to obtain the tool sequence set corresponding to each of the sequence data;

[0054] Please see Figure 2Step S102 specifically includes steps S1021 to S1022:

[0055] S1021, In the sequence calculation model, a tool is added to select the sequence matrix, and the tool is used to select the sequence matrix to perform iterative calculation on each sequence data to obtain the matching degree of each sequence data;

[0056] S1022, based on the matching degree, perform uniform distribution processing on each of the sequence data to obtain the tool sequence set corresponding to each of the sequence data.

[0057] In practical implementation, the sequence data of each end tool is obtained through the aforementioned bus address. This sequence data includes the type of end tool, assembly path, and assembly parameters. A sequence calculation model is constructed using a pre-defined tool selection algorithm. Before performing sequence calculation, a tool selection sequence matrix δ(x) is added to this model. The tool selection sequence matrix is ​​then used to iteratively calculate the matching degree of each sequence data. This tool selection sequence matrix δ(x) is a 2D matrix of size M*ts.

[0058]

[0059] In the formula, x represents the number of iterations.

[0060]

[0061] In the formula, δ m，t (x) represents the probability that the tool corresponding to the m-th sequence data selected by the robot based on the tool switching task in the x-th iteration is tool t, which indicates the matching degree between the switching operation and the tool.

[0062] Specifically, based on the calculated matching degree, the sequence data are uniformly distributed to obtain the tool sequence set corresponding to each sequence data. In this embodiment, all elements in the above matrix are processed using a roulette wheel method to obtain the corresponding tool sequence set.

[0063] S103, construct a parsing archive set, and use the parsing archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model;

[0064] Please see Figure 3 Step S103 specifically includes steps S1031 to S1032:

[0065] S1031, using the parsing archive set to calculate all non-controlling solutions during the iterative search of the sequence computation model, and recording the newly acquired non-controlling solutions during each iterative search according to the optimization archive set corresponding to the parsing archive set, so as to form an iterative solution set;

[0066] S1032, The sequence calculation model is optimized based on the iterative solution set and all the non-controlling solutions to obtain the corresponding sequence probability model.

[0067] In practical implementation, an external analytical archive set τ is constructed, and this analytical archive set τ is used to record all non-controlling solutions obtained by the sequence computation model during the iterative search process. A non-controlling solution is one in which x1 is better than x2 for all objectives, and x1 controls x2. If the solution of x1 is not controlled by other solutions, then x1 is called a non-controlling solution.

[0068] Furthermore, the optimization set τ corresponding to the analytical set τ is used to record the new non-controlling solution discovered in each iteration, forming an iterative solution set. Before each iteration search, the optimization set τ is initialized to an empty set. During the search, each individual I in the generated iterative solution set θ is... i Not controlled by any individual in the parsed archive set τ, and I i If it does not belong to the parsed archive set τ, then I will... i Add parsing archive set τ and optimizing archive set ∈, if individual I i Controlling the analysis of a specific individual K in the archive set τ j Then the individual K j Remove from the analytical archive set τ. After comparing the dominance relationships of individuals in the analytical archive set τ for all individuals in the iterative solution set θ, if the optimized archive set ∈ is a non-empty set, then use the optimized archive set ∈ to optimize the sequence calculation model to obtain the corresponding sequence probability model. If it is an empty set, continue to use the sequence calculation model of the previous generation as the sequence probability model.

[0069] S104, Analyze the tool sequence set one by one according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set;

[0070] Please see Figure 4 Step S104 specifically includes steps S1041 to S1043:

[0071] S1041, Initialize the parameters of the sequence probability model and mark the iteration count of the sequence probability model as 0;

[0072] S1042, Random sampling is performed on the tool sequence set to obtain preliminary sampling data, and the sequence probability model is updated using the mutation probability. The updated sequence probability model is then used to perform secondary sampling based on the same sampling parameters as the random sampling to obtain secondary sampling data.

[0073] S1043, compare the preliminary sampling data and the secondary sampling data to obtain sampling difference data, and use the sampling difference data to analyze the tool sequence set to obtain the sequence selection probability of each sequence data in the tool sequence set.

[0074] In practice, the parameters of the sequence probability model are initialized and the iteration count of the sequence probability model is marked as 0. The sequence probability model is used to randomly sample the tool sequence set to obtain preliminary sampled data. The sequence probability model is then updated based on the preset mutation probability. The updated sequence probability model is used to randomly sample the same sampling parameters for secondary sampling to obtain secondary sampled data. The sampling parameters include sampling order, sampling rules, etc.

[0075] The preliminary and secondary sampling data obtained above are compared to obtain sampling difference data. This sampling difference data is then used to analyze the tool sequence set to obtain the sequence selection probability of each sequence in the tool sequence set. The sequence selection probability is the probability that a tool sequence is correctly selected in both sampling processes.

[0076] S105, reconfigure the valve island for sequence data whose sequence selection probability is greater than a preset probability threshold to generate corresponding tool switching parameters, and control the robot to switch each end tool according to the tool switching parameters.

[0077] In practical implementation, sequence data with a selection probability greater than a preset probability threshold (in this embodiment, the probability threshold is 85%; in other embodiments, this probability threshold can be automatically set by the system or set by the user) are reconfigured for valve island reprocessing. This allows for the parsing of internal tool switching data, the generation of tool switching parameters using the corresponding tool switching data, and the control of the robot to switch each end-effector using these parameters. It is understood that sequence data with a probability greater than the preset threshold has relatively superior tool switching data; therefore, it is used as a reference to generate tool switching parameters, enabling the robot to learn from it and thereby improve the robot's end-effector switching rate, thus enhancing overall work efficiency.

[0078] In summary, the robot tool switching method in the above embodiments of the present invention performs sequence calculations on the sequence data of the end-effectors to obtain a corresponding tool sequence set. Then, it analyzes each tool sequence in the set according to a sequence probability model to obtain a sequence selection probability. Sequences with selection probabilities greater than a preset probability threshold are reconfigured into valve islands to generate corresponding tool switching parameters. The robot is then controlled to switch each end-effector using these parameters. By performing multi-objective optimization on top of single-objective optimization, using sequence selection probabilities to construct tool switching parameters, and completing the switching of the robot's end-effectors based on these parameters, the tool switching speed is improved, thereby increasing production line efficiency and production capacity.

[0079] Example 2

[0080] In another aspect, the present invention also proposes a robot tool switching system, please refer to [link to relevant documentation]. Figure 5 The image shows a robot tool switching system according to a second embodiment of the present invention, comprising:

[0081] Address acquisition module 11 is used to acquire the bus structure of the robot and perform address parsing on the bus structure to obtain the bus address of each end tool of the robot.

[0082] The sequence calculation module 12 is used to acquire the sequence data of each of the terminal tools, construct a sequence calculation model based on the tool selection algorithm, and use the sequence calculation model to perform sequence calculation on each of the sequence data to obtain the tool sequence set corresponding to each of the sequence data.

[0083] Furthermore, the sequence calculation module 12 includes:

[0084] An iterative calculation unit is used to add a tool selection sequence matrix to the sequence calculation model and use the tool selection sequence matrix to perform iterative calculations on each of the sequence data to obtain the matching degree of each of the sequence data.

[0085] A distribution processing unit is used to uniformly distribute each of the sequence data based on the matching degree to obtain a set of tool sequences corresponding to each of the sequence data.

[0086] The iterative optimization module 13 is used to construct a parsed archive set and use the parsed archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model.

[0087] Furthermore, the iterative optimization module 13 includes:

[0088] The iterative processing unit is used to calculate all non-controlling solutions when performing iterative search on the sequence computation model using the parsed archive set, and to record the newly acquired non-controlling solutions in each iterative search according to the optimization archive set corresponding to the parsed archive set, so as to form an iterative solution set;

[0089] The model optimization unit is used to optimize the sequence computation model based on the iterative solution set and all the non-controlling solutions to obtain the corresponding sequence probability model.

[0090] The sequence analysis module 14 is used to analyze the tool sequence set one by one according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set;

[0091] Furthermore, the sequence analysis module 14 includes:

[0092] The parameter configuration unit is used to initialize the parameters of the sequence probability model and mark the iteration count of the sequence probability model as 0;

[0093] The data sampling unit is used to randomly sample the tool sequence set to obtain preliminary sampling data, update the sequence probability model using the mutation probability, and perform secondary sampling based on the same sampling parameters as the random sampling using the updated sequence probability model to obtain secondary sampling data.

[0094] The sequence analysis unit is used to compare the preliminary sampling data and the secondary sampling data to obtain sampling difference data, and to analyze the tool sequence set using the sampling difference data to obtain the sequence selection probability of each sequence data in the tool sequence set.

[0095] The tool switching module 15 is used to reconfigure the valve island for sequence data whose sequence selection probability is greater than a preset probability threshold, so as to generate corresponding tool switching parameters, and control the robot to switch each end tool according to the tool switching parameters.

[0096] The functions or operation steps implemented by the above modules and units are largely the same as those in the above method embodiments, and will not be repeated here.

[0097] The robot tool switching system provided in this embodiment of the invention has the same implementation principle and technical effect as the aforementioned method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned method embodiment.

[0098] Example 3

[0099] This invention also proposes a computer, please refer to [link / reference]. Figure 6The computer shown in the third embodiment of the present invention includes a memory 10, a processor 20, and a computer program 30 stored in the memory 10 and executable on the processor 20. When the processor 20 executes the computer program 30, it implements the above-described robot tool switching method.

[0100] The memory 10 includes at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 10 can be an internal storage unit of a computer, such as the computer's hard disk. In other embodiments, the memory 10 can be an external storage device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Furthermore, the memory 10 can include both internal and external storage units of the computer. The memory 10 can be used not only to store application software and various types of data installed on the computer, but also to temporarily store data that has been output or will be output.

[0101] In some embodiments, the processor 20 may be an electronic control unit (ECU, also known as a vehicle computer), a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip, used to run program code stored in the memory 10 or process data, such as executing access restriction programs.

[0102] It should be pointed out that, Figure 6 The structure shown does not constitute a limitation on the computer. In other embodiments, the computer may include fewer or more components than shown, or combine certain components, or have different component arrangements.

[0103] This invention also proposes a storage medium storing a computer program that, when executed by a processor, implements the robot tool switching method described above.

[0104] Those skilled in the art will understand that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer storage medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0105] More specific examples of computer storage media (a non-exhaustive list) include: electrical connections (electronic devices) with one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer storage media can even be paper or other suitable storage media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other storage medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0106] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0107] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0108] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for switching robot tools, characterized in that, include: Obtain the robot's bus structure and perform address parsing on the bus structure to obtain the bus addresses of each end effector of the robot; The sequence data of each end tool is obtained, a sequence calculation model is constructed based on a pre-set tool selection algorithm, and the sequence calculation model is used to perform sequence calculation on each sequence data to obtain a tool sequence set corresponding to each sequence data. The sequence data includes the type of end tool, assembly path, and assembly parameters. Construct a parsed archive set and use the parsed archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model; The tool sequence set is analyzed one by one according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set; The sequence data with a selection probability greater than a preset probability threshold are reconfigured into valve islands to generate corresponding tool switching parameters, and the robot is controlled to switch each end tool according to the tool switching parameters; The step of performing sequence calculations on each of the sequence data using the sequence calculation model to obtain the tool sequence set corresponding to each of the sequence data includes: In the sequence calculation model, a tool is added to select the sequence matrix, and the tool is used to select the sequence matrix to perform iterative calculations on each sequence data to obtain the matching degree of each sequence data. Based on the matching degree, each sequence data is uniformly distributed to obtain a set of tool sequences corresponding to each sequence data. The steps of constructing a parsed archive set and using the parsed archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model include: An external analytical archive set τ is constructed, and all uncontrolled solutions are calculated using the analytical archive set τ during the iterative search of the sequence computation model. An uncontrolled solution is defined as x1 controlling x2 if x1 is better than x2 for all objectives, and x1 is not controlled by other solutions. The optimized file set ∈ corresponding to the analytical file set τ is used to record the newly acquired non-control solutions during each iteration search, so as to form an iterative solution set; Before each iteration of the search, the optimization archive set ∈ is initialized to be an empty set. During the search, each individual I in the currently generated iterative solution set θ is... i Not controlled by any individual in the parsed archive set τ, and I i If it does not belong to the parsed archive set τ, then I will... i Add parsing archive set τ and optimizing archive set ∈, if individual I i Controlling the analysis of a specific individual K in the archive set τ j Then the individual K j Remove from the analytical archive set τ; after comparing the dominance relationships of individuals in the analytical archive set τ for all individuals in the iterative solution set θ, if the optimized archive set ∈ is a non-empty set, then use the optimized archive set ∈ to optimize the sequence calculation model to obtain the corresponding sequence probability model; if it is an empty set, continue to use the previous generation's sequence calculation model as the sequence probability model.

2. The robot tool switching method according to claim 1, characterized in that, The steps of analyzing each sequence in the tool sequence set according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set include: Initialize the parameters of the sequence probability model and mark the iteration count of the sequence probability model as 0; The tool sequence set is randomly sampled to obtain preliminary sampled data, and the sequence probability model is updated using the mutation probability. The updated sequence probability model is then used to perform secondary sampling based on the same sampling parameters as the random sampling to obtain secondary sampled data. The preliminary sampling data and the secondary sampling data are compared to obtain sampling difference data. The sampling difference data is then used to analyze the tool sequence set to obtain the sequence selection probability of each sequence data in the tool sequence set.

3. A robot tool switching system, characterized in that, include: The address acquisition module is used to acquire the robot's bus structure and perform address parsing on the bus structure to obtain the bus address of each end tool of the robot. The sequence calculation module is used to acquire the sequence data of each of the end tools, construct a sequence calculation model based on a pre-set tool selection algorithm, and use the sequence calculation model to perform sequence calculation on each of the sequence data to obtain a tool sequence set corresponding to each of the sequence data. The sequence data includes the type of end tool, assembly path, and assembly parameters. An iterative optimization module is used to construct a parsed archive set and use the parsed archive set to iteratively optimize the sequence calculation model to obtain the corresponding sequence probability model. The sequence analysis module is used to analyze the tool sequence set one by one according to the sequence probability model to obtain the sequence selection probability of each sequence data in the tool sequence set; The tool switching module is used to reconfigure the valve island for sequence data whose sequence selection probability is greater than a preset probability threshold, so as to generate corresponding tool switching parameters, and control the robot to switch each end tool according to the tool switching parameters; The sequence calculation module includes: An iterative calculation unit is used to add a tool selection sequence matrix to the sequence calculation model and use the tool selection sequence matrix to perform iterative calculations on each of the sequence data to obtain the matching degree of each of the sequence data. A distribution processing unit is used to uniformly distribute each of the sequence data based on the matching degree to obtain a set of tool sequences corresponding to each of the sequence data. The iterative optimization module includes: An iterative processing unit is used to construct an external analytical archive set τ, and to calculate all uncontrolled solutions when the sequence computation model performs iterative search using the analytical archive set τ. An uncontrolled solution is defined as x1 controlling x2 if x1 is better than x2 for all objectives, and x1 is not controlled by other solutions if x1 is not controlled by other solutions. The optimized file set ∈ corresponding to the analytical file set τ is used to record the newly acquired non-control solutions during each iteration search, so as to form an iterative solution set; The model optimization unit is used to initialize the optimization archive set ∈ as an empty set before each iteration search. During the search, each individual I in the generated iterative solution set θ is used. i Not controlled by any individual in the parsed archive set τ, and I i If it does not belong to the parsed archive set τ, then I will... i Add parsing archive set τ and optimizing archive set ∈, if individual I i Controlling the analysis of a specific individual K in the archive set τ j Then the individual K j Remove from the analytical archive set τ; after comparing the dominance relationships of individuals in the analytical archive set τ for all individuals in the iterative solution set θ, if the optimized archive set ∈ is a non-empty set, then use the optimized archive set ∈ to optimize the sequence calculation model to obtain the corresponding sequence probability model; if it is an empty set, continue to use the previous generation's sequence calculation model as the sequence probability model.

4. The robot tool switching system according to claim 3, characterized in that, The sequence analysis module includes: The parameter configuration unit is used to initialize the parameters of the sequence probability model and mark the iteration count of the sequence probability model as 0; The data sampling unit is used to randomly sample the tool sequence set to obtain preliminary sampling data, update the sequence probability model using the mutation probability, and perform secondary sampling based on the same sampling parameters as the random sampling using the updated sequence probability model to obtain secondary sampling data. The sequence analysis unit is used to compare the preliminary sampling data and the secondary sampling data to obtain sampling difference data, and to analyze the tool sequence set using the sampling difference data to obtain the sequence selection probability of each sequence data in the tool sequence set.

5. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the robot tool switching method as described in any one of claims 1 to 2.

6. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the robot tool switching method as described in any one of claims 1 to 2.

Images