A multi-limb collaborative control method and system for a bionic structure

Abstract

The present application provides a multi-limb collaborative control method and system for a bionic structure, which relates to the field of dynamic motion control technology, including: sequentially sorting out the tasks to be executed of the bionic robot and establishing a chain of tasks to be executed; making collaborative control decisions for N limbs and establishing a Q-dimensional robot control space; conducting inspection and optimization based on the robot control inspection channel to establish a Q-dimensional candidate space for robot control; introducing a robot control variation function and a collaborative fitness analytical model to perform variation, expansion and optimization on the robot control Q-dimensional candidate space to obtain a robot control optimization block; and executing multi-limb collaborative control. This application can solve the technical problem in the prior art that the multi-limb collaborative control of the robot is difficult to adapt to complex and changeable tasks and environments, resulting in low efficiency in the task execution of the bionic robot, enhance the adaptability of the multi-limb collaborative control strategy in complex environments, and improve the task execution efficiency of the bionic robot.

Description

Technical Field

[0001] The present application relates to the field of dynamic motion control technology, and in particular to a multi-limb collaborative control method and system of a bionic structure. Background Art

[0002] Bionic robots are robots that mimic the structure and function of living organisms. Their core concept is to achieve efficient operational capabilities and adaptability by designing systems that simulate biological motion and perception. Multi-limb collaborative control involves the coordinated operation of multiple robotic limbs (such as robotic arms and mobile platforms) to efficiently complete complex tasks. This typically requires consideration of multiple factors, including the mechanical relationships between limbs, task requirements, and execution sequence. Currently, most multi-limb collaborative control methods rely on pre-set, fixed control strategies, often employing optimization algorithms to coordinate the collaboration of multiple limbs. When task requirements change, existing control methods often require recalculation or adjustment of control strategies, resulting in significant computational overhead and impacting real-time performance and efficiency. Furthermore, existing technologies also suffer from unbalanced coordination among multiple limbs. Especially when faced with complex and changing tasks and environments, uneven loads and improper coordination can occur between limbs, leading to task failure or inefficiency.

[0003] In summary, the existing technology has a technical problem in which the efficiency of bionic robot task execution is low because the collaborative control of robot multi-limbs is difficult to adapt to complex and changing tasks and environments. Summary of the Invention

[0004] The purpose of this application is to provide a multi-limb collaborative control method and system for a bionic structure, so as to solve the technical problem in the prior art that the multi-limb collaborative control of the robot is difficult to adapt to complex and changeable tasks and environments, resulting in low efficiency in the task execution of bionic robots.

[0005] In view of the above problems, the present application provides a multi-limb collaborative control method and system of a bionic structure.

[0006] In the first aspect, the present application provides a multi-limb collaborative control method of a bionic structure, which is implemented by a multi-limb collaborative control system of a bionic structure, wherein the multi-limb collaborative control method of a bionic structure includes: timing-sequencing the tasks to be executed of the bionic robot and establishing a chain of tasks to be executed, wherein the bionic robot includes N limbs, and the chain of tasks to be executed includes Q node tasks, and N and Q are both positive integers greater than 1; making collaborative control decisions on the N limbs according to the chain of tasks to be executed, and establishing a Q-dimensional robot control space; testing and optimizing the Q-dimensional robot control space according to the robot control test channel, and establishing a Q-dimensional candidate space for robot control; introducing a robot control variation function and a collaborative fitness analytical model to perform variation, expansion and optimization on the Q-dimensional candidate space for robot control, and obtain a robot control optimization block; and executing multi-limb collaborative control of the bionic robot according to the robot control optimization block.

[0007] In the second aspect, the present application also provides a multi-limb collaborative control system of a bionic structure, which is used to execute a multi-limb collaborative control method of a bionic structure as described in the first aspect, wherein the multi-limb collaborative control system of a bionic structure includes: a task timing combing module, which is used to perform timing combing on the tasks to be executed of the bionic robot and establish a task chain to be executed, wherein the bionic robot includes N limbs, and the task chain to be executed includes Q node tasks, and N and Q are both positive integers greater than 1; a collaborative control decision module, which is used to make collaborative control decisions on the N limbs according to the task chain to be executed and establish a Q-dimensional robot control space; a test and optimization module, which is used to test and optimize the Q-dimensional robot control space according to the robot control test channel and establish a robot control Q-dimensional candidate space; a variation and expansion optimization module, which is used to introduce a robot control variation function and a collaborative fitness analytical model to perform variation and expansion optimization on the robot control Q-dimensional candidate space to obtain a robot control optimization block; a collaborative control execution module, which is used to execute multi-limb collaborative control of the bionic robot according to the robot control optimization block.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The method involves sequentially sorting out pending tasks of a bionic robot to establish a pending task chain, wherein the bionic robot comprises N limbs and the pending task chain comprises Q node tasks, where N and Q are both positive integers greater than 1; making collaborative control decisions for the N limbs based on the pending task chain to establish a Q-dimensional robot control space; performing test optimization on the Q-dimensional robot control space based on a robot control test channel to establish a Q-dimensional candidate robot control space; introducing a robot control variation function and a collaborative fitness analytical model to perform mutation, expansion, and optimization on the Q-dimensional candidate robot control space to obtain a robot control optimization block; and executing multi-limb collaborative control of the bionic robot based on the robot control optimization block. Specifically, by sequentially sorting out pending tasks and establishing a task chain, making collaborative control decisions for each limb based on the task chain, and selecting the optimal control strategy for the bionic robot's multi-limb collaborative control based on the robot control test channel, the robot control variation function, and the collaborative fitness analytical model, the method optimizes the collaborative movements between the limbs, enhances the adaptability of the multi-limb collaborative control strategy in complex environments, and improves the task execution efficiency of the bionic robot.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, which can be implemented in accordance with the contents of the description, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically listed below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in this application or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely exemplary, and a person of ordinary skill in the art can obtain other drawings based on the provided drawings without creative work.

[0012] Figure 1 This is a flow chart of a multi-limb collaborative control method for a bionic structure of the present application;

[0013] Figure 2 This is a structural diagram of a bionic multi-limb collaborative control system for this application.

[0014] Explanation of the accompanying symbols: task timing combing module 11, collaborative control decision module 12, inspection optimization module 13, variation expansion optimization module 14, collaborative control execution module 15. DETAILED DESCRIPTION

[0015] This application provides a multi-limb collaborative control method and system for a bionic structure, solving the technical problem in the prior art of low efficiency in bionic robot task execution due to the difficulty of adapting multi-limb collaborative control of robots to complex and changing tasks and environments. By sequentially sorting the tasks to be executed and establishing a task chain, collaborative control decisions are made for each limb based on the task chain. The optimal control strategy is selected through the robot control test channel, the robot control variation function, and the collaborative fitness analytical model to perform multi-limb collaborative control of the bionic robot, optimize the collaborative movements between the limbs, enhance the adaptability of the multi-limb collaborative control strategy in complex environments, and improve the task execution efficiency of the bionic robot.

[0016] Below, the technical solutions in this application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this application, rather than all the embodiments of this application. It should be understood that this application is not limited to the example embodiments described herein. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application. It should also be noted that, for the convenience of description, only the parts related to this application, rather than all of them, are shown in the accompanying drawings.

[0017] For example, see the attached Figure 1 The present application provides a multi-limb collaborative control method for a bionic structure, wherein the multi-limb collaborative control method for a bionic structure is applied to a multi-limb collaborative control system for a bionic structure, and the multi-limb collaborative control method for a bionic structure specifically comprises the following steps:

[0018] S100: Time-sequencing the tasks to be executed of the bionic robot to establish a task chain to be executed, wherein the bionic robot includes N limbs, the task chain to be executed includes Q node tasks, and N and Q are both positive integers greater than 1.

[0019] Specifically, all pending tasks for the bionic robot are identified, along with the nature, objectives, and execution conditions of each task. Based on their importance and dependencies, the tasks are sorted in order of execution, creating a pending task chain consisting of Q node tasks. Within the task chain, the inputs and outputs of each node task must satisfy certain logical relationships to ensure that the execution of each task does not interfere with each other and maximizes efficiency. The bionic robot consists of N limbs, each responsible for a specific function or task.

[0020] Bionic robots are robots that mimic the structure and function of living organisms, aiming to emulate their movement, perception, and control mechanisms. Bionic robots are generally composed of multiple limbs that work in coordination through sophisticated control systems to perform complex tasks. In robotics, a limb refers to the part of the robot that performs movement and operational tasks, similar to the arms, legs, or other moving parts of an organism. A bionic robot can have multiple limbs, each responsible for a specific function or task. Unexecuted tasks are tasks that have not yet been performed but need to be completed. They usually include a series of operational steps, such as grasping, carrying, assembly, etc. Each task may require the collaboration of multiple limbs to complete.

[0021] Task sequencing involves arranging and organizing pending tasks into a specific order to ensure that each task is executed on time and in order. A task chain is an ordered sequence of related tasks, where each task node depends on the execution results of the previous task. By sequencing the pending tasks of the bionic robot and establishing a task chain, we ensure that each task is executed in a reasonable order, thereby reducing unnecessary waiting and resource conflicts and improving the overall execution efficiency of the bionic robot.

[0022] S200: Making collaborative control decisions for the N limbs according to the task chain to be executed, and establishing a Q-dimensional robot control space.

[0023] Furthermore, the present application S200 includes:

[0024] According to the task chain to be executed, extract the qth node task, where 1≤q≤Q; collect the scene information of the qth node task to obtain the qth task scene; use the qth task scene as the collaborative control scene constraint and the qth node task as the collaborative control target to make control decisions for the N limbs and establish a qth node robot control domain; and add the qth node robot control domain to the Q-dimensional robot control space.

[0025] Specifically, from the established task chain to be executed, locate and extract the qth node task. The qth node task refers to the specific task of the qth node in the task chain. For example, if the task chain includes a handling operation, the qth node task may be to grab an object or place an object. According to the requirements of the task node, the relevant scene information of the qth node task is collected to obtain the qth task scene, including the position and status of the object, the position of obstacles, environmental constraints, etc. The scene information can be collected through sensors (such as lidar, depth camera sensors, etc.) to obtain external environment data related to the task. The qth task scene is the environmental information collected when executing the qth node task. The scene of each task node is related to the specific operation of the node.

[0026] Based on the requirements of the qth node task, the qth task scenario is used as a constraint for collaborative control. This means that during the multi-limb collaborative control process, the physical or operational limitations associated with the scenario must be observed. The qth node task is used as the collaborative control goal, meaning the goal the robot needs to achieve during the collaborative control process. The collaborative control goal for each task node is typically the operation to be completed at that node. Based on the collaborative control scenario constraints and collaborative control goals, control decisions are made for the N limbs, planning how these limbs will be used to complete the qth node task. The robot's specific action strategy for the qth node task is determined, including the coordination and control methods for each limb, and the qth node robot control domain is established.

[0027] The q-th node robot control domain is the space of all possible decisions for robot control when executing the q-th node task, including multiple robot control decisions corresponding to the q-th node task, that is, it includes all possible combinations of actions, strategies and decisions of the robot limbs. Each operation mode may lead to different task execution results.

[0028] The control domain of the qth node task is added to the Q-dimensional robot control space. The Q-dimensional robot control space is the set of control domains corresponding to all task nodes, including Q node control domains corresponding to Q node tasks. The control decision domain of each task node represents the possible control strategies for that node. The Q-dimensional control space integrates the decision information of all nodes to form a complete robot control decision space. By parsing the bionic robot's pending task chain and making control decisions for each task, efficient collaborative control of the robot's multiple limbs can be achieved, enabling comprehensive management of the robot's multi-limb collaborative control.

[0029] S300: testing and optimizing the Q-dimensional robot control space according to the robot control testing channel to establish a robot control Q-dimensional candidate space.

[0030] Furthermore, the present application S300 includes:

[0031] Traverse the q-th node robot control domain and extract the first robot control decision; simulate and control the bionic robot according to the first robot control decision to obtain a first simulated collaborative data set; input the first simulated collaborative data set into the robot control inspection channel to obtain a first robot control inspection result; when the first robot control inspection result is qualified, set the first robot control decision as the first robot control candidate solution, and add the first robot control candidate solution to the q-th node robot control candidate domain; when the first robot control inspection result is unqualified, eliminate the first robot control decision; continue to inspect and optimize the q-th node robot control domain according to the robot control inspection channel, construct the q-th node robot control candidate domain, and add the q-node robot control candidate domain to the robot control Q-dimensional candidate space.

[0032] Specifically, a node task is randomly selected in the Q-dimensional robot control space as the q-th node robot control domain. The q-th node robot control domain is traversed. Each control domain contains multiple possible control decisions, and the first robot control decision is randomly extracted from these. Based on the first robot control decision, the bionic robot is simulated and controlled. The execution process of the bionic robot under the first robot control decision is simulated to obtain the first simulated collaboration dataset, which includes the bionic robot's motion trajectory, grasping force, and limb collaboration effect. The first simulated collaboration dataset refers to the actual execution results obtained by simulating the bionic robot after executing the first decision, and is used to evaluate the effectiveness of the control strategy.

[0033] The first simulated collaborative dataset is fed into the robot control evaluation model in the robot control verification channel for multi-dimensional evaluation, resulting in a first robot control evaluation result, including task completion accuracy, limb collaboration efficiency, and limb collaboration reliability. This first robot control evaluation result is then fed into the control verification model, where the control verification operator determines whether the first robot control evaluation result satisfies the robot control verification constraints. If so, the first robot control verification result is considered qualified; otherwise, it is considered unqualified.

[0034] When the first robot control test result is qualified, the first robot control decision is set as the first robot control candidate solution and added to the q-th node robot control candidate domain. If the first robot control test result is unqualified, that is, the first robot control decision does not meet the quality standards for task execution, such as task accuracy, collaborative efficiency, or reliability, the control decision is automatically removed from the control decision space, that is, it is no longer used to avoid its negative impact on robot task execution. The robot control test channel continues to test and optimize other decisions in the q-th node robot control domain. In other words, all unqualified decisions in the q-th node robot control domain are eliminated, and all qualified decisions are retained to construct a complete q-th node robot control candidate domain. The q-th node robot control candidate domain is the candidate control decision that can be selected after all qualified decisions are screened out according to the test results during the test and optimization process.

[0035] The q-th node robot control candidate domain is added to the Q-dimensional robot control candidate space. This process repeats for each node task, resulting in Q node robot control candidate domains corresponding to each of the Q node tasks. Together, these domains constitute the Q-dimensional robot control candidate space. Each node task's control candidate domain represents all optimal control decisions for that node, and the candidate domains of multiple nodes constitute the overall optimization space for robot control. By verifying the feasibility of each control decision, the robot is ensured to successfully execute the actual task, improving the task success rate and control accuracy. Unsatisfactory decision solutions are eliminated, ensuring that the final selected control solution is adaptable to diverse environments and task conditions, avoiding unnecessary trial and error, and improving overall execution efficiency.

[0036] Furthermore, the present application further comprises the following steps:

[0037] The robot control inspection channel includes a robot control evaluation model and a control inspection model; the first simulated collaboration data set is input into the robot control evaluation model to obtain a first robot control evaluation result, wherein the robot control evaluation model includes a robot control multidimensional evaluation index, and the robot control multidimensional evaluation index includes task completion accuracy, limb collaboration efficiency and limb collaboration reliability; the first robot control evaluation result is input into the control inspection model, and the first robot control inspection result is output, wherein the control inspection model includes a control inspection operator, and the control inspection operator includes: if the first robot control evaluation result meets the robot control inspection constraint, the first robot control inspection result is qualified; if the first robot control evaluation result does not meet the robot control inspection constraint, the first robot control inspection result is unqualified, and the robot control inspection constraint includes a predetermined task completion accuracy, a predetermined limb collaboration efficiency and a predetermined limb collaboration reliability.

[0038] Specifically, the robot control verification channel uses a combination of a robot control evaluation model and a control verification model to gradually screen and verify whether the robot's control decisions meet the task requirements. The robot control evaluation model is used to evaluate the effectiveness of the robot's control decision execution. It measures the performance of control decisions based on multi-dimensional evaluation indicators and analyzes the robot's task accuracy, limb collaboration efficiency, and limb collaboration reliability. The first simulated collaboration dataset is input into the robot control evaluation model for processing. The indicators for each dimension are calculated according to the task requirements to obtain the first robot control evaluation result.

[0039] The multidimensional evaluation index for robot control measures the quality of robot control decisions across multiple dimensions. These indicators include task completion accuracy, limb coordination efficiency, and limb coordination reliability. Each indicator reflects a different aspect of the robot's performance during task execution. Task completion accuracy is the difference between the robot's actual operational results and the predetermined target when performing a task. The higher the accuracy, the closer the task completion is to the expected target. Limb coordination efficiency is the efficiency of collaboration between the robot's multiple limbs, typically measured by coordination time, the total number of actions performed, and other factors. Higher efficiency indicates smoother coordination between the robot's limbs and faster task completion. Limb coordination reliability measures the ability of the robot's limbs to maintain stability and successfully complete the task during collaboration. Higher reliability indicates that the robot can consistently perform the same task repeatedly.

[0040] Task completion accuracy is calculated by calculating the deviation between the robot's actual execution result and the target result. For example, assuming the initial position is (0,0), the target position is (5,5), and the actual position is (5.1,5.2), the task completion accuracy is calculated by calculating the ratio of the distance between the target position and the actual position to the distance between the target position and the initial position. The difference between 1 and the ratio is then calculated, resulting in a task completion accuracy of 96.84%. Limb collaboration efficiency can be measured by calculating the degree of coordination among multiple limbs during task execution, such as the coordination time of arm movements and the number of movements performed. For example, assuming the total collaboration time for the left and right arms is 5 seconds, and the optimal collaboration time required by the task is 6 seconds, the collaboration efficiency is 120%, indicating that the task was completed in a shorter time than expected, indicating high collaboration efficiency. Limb collaboration reliability can be determined by simulating multiple executions of the same task and calculating the task success rate. For example, if the robot successfully completes the task 80% of the time and fails 20% of the time, the reliability is 80%.

[0041] The first robot control evaluation result is input into the control verification model for final verification. The control verification operator compares the first robot control evaluation result with the robot control verification constraints to determine whether the requirements are met, that is, whether the first robot control verification result is qualified. The control verification operator is a mathematical tool or algorithm used to determine whether the robot control decision is qualified. It inputs the control evaluation result and outputs whether it is qualified. The robot control verification constraints are the requirements that the robot must meet when performing a task, including predetermined standards such as task completion accuracy, body coordination efficiency, and body coordination reliability. For example, task completion accuracy must reach or exceed 95%, coordination efficiency must reach or exceed 100%, and coordination reliability must reach or exceed 85%.

[0042] If the first control evaluation result satisfies the robot control verification constraints, the first robot control verification result is considered qualified; conversely, if the first robot control evaluation result does not satisfy the robot control verification constraints, the first robot control verification result is considered unqualified. In other words, a control decision is considered qualified only when all three control indicators meet the predetermined standards. By combining the control evaluation model with the control verification model, control decisions are analyzed and verified from multiple dimensions, and unqualified solutions are promptly eliminated. This ensures stable task execution under various environments and conditions, and avoids collaboration failures caused by unqualified decisions.

[0043] S400: introducing a robot control variation function and a collaborative fitness analytical model to perform variation expansion and optimization on the robot control Q-dimensional candidate space to obtain a robot control optimization block.

[0044] Furthermore, the present application S400 includes:

[0045] The robot control Q-dimensional candidate space is mutated according to the robot control mutation function to establish a robot control Q-dimensional mutation space; the robot control Q-dimensional mutation space is tested and optimized according to the robot control test channel to obtain a robot control Q-dimensional mutation optimization space; the robot control Q-dimensional candidate space is expanded according to the robot control Q-dimensional mutation optimization space to obtain a robot control Q-dimensional optimization space; the robot control Q-dimensional optimization space is optimized for collaborative fitness maximization according to the collaborative fitness analytical model to obtain Q-node robot control optimization results, wherein the collaborative fitness analytical model includes task completion accuracy weights, limb collaboration efficiency weights and limb collaboration reliability weights; the Q-node robot control optimization results are stored on-chain and off-chain to generate the robot control optimization block.

[0046] Specifically, the robot control mutation function is used to mutate the original Q-dimensional candidate space, and a new control scheme is generated by mutating the control schemes of the Q task nodes. Specifically, the robot control mutation function is used to evaluate the mutation value of the control evaluation results corresponding to each control candidate scheme to obtain the corresponding candidate scheme mutation value coefficient. According to the candidate scheme mutation value coefficient, the number of candidate scheme mutations is determined, and the control candidate domains of the Q task nodes are mutated, that is, the parameters of the control scheme are changed to obtain the robot control Q-dimensional mutation space. The specific process is described in detail in the subsequent corresponding explanation of the rights, and for the sake of brevity, it will not be described in detail here.

[0047] The robot control verification channel tests and optimizes the Q-dimensional robot control variation space, similar to the process of testing and optimizing the Q-dimensional robot control space using the robot control verification channel to establish the Q-dimensional candidate space for robot control. For the sake of brevity, this description will be briefly introduced here and not elaborated on in detail. Taking the first-node robot control variation space as an example, the first variation decision is extracted from it. Simulation control of the bionic robot is performed based on this first variation decision, and the data from the simulation is recorded to evaluate the effectiveness of the variation decision. The simulation data is input into the robot control evaluation model in the robot control verification channel to obtain the evaluation results of the first variation decision, including task completion accuracy, limb collaboration efficiency, and limb collaboration reliability. The evaluation results are then input into the control verification model in the robot control verification channel to determine whether the evaluation results meet the robot control verification constraints and determine whether they are qualified. Qualified solutions are retained and unqualified solutions are eliminated, thus obtaining the first-node robot control variation optimization space, which is then input into the robot control Q-dimensional variation optimization space. The above steps are repeated for other node tasks, thus forming the robot control Q-dimensional variation optimization space.

[0048] Based on the robot control Q-dimensional mutation optimization space, the robot control Q-dimensional candidate space is expanded. Specifically, the optimal control solutions obtained through mutation and verification are incorporated into the robot control Q-dimensional candidate space, expanding the range of candidate solutions and obtaining a new Q-dimensional optimization space, namely the robot control Q-dimensional optimization space. This robot control Q-dimensional optimization space includes not only the solutions in the original robot control Q-dimensional candidate space but also all control solutions that have undergone mutation and verification.

[0049] The Q-dimensional optimization space of robot control is input into the collaborative fitness analytical model to maximize fitness optimization. By weighting factors such as task completion accuracy, limb collaboration efficiency, and limb collaboration reliability, a comprehensive fitness index is calculated to help select the optimal control scheme. The collaborative fitness analytical model includes task completion accuracy weights, limb collaboration efficiency weights, and limb collaboration reliability weights, which are used to represent the degree of influence of each evaluation indicator on the final decision. By adjusting these weights, priority can be adjusted in different tasks. In the robot control test channel, the evaluation results of each control scheme in the Q-dimensional optimization space of robot control are retrieved and weighted with the task completion accuracy weights, limb collaboration efficiency weights, and limb collaboration reliability weights to obtain the collaborative fitness of each scheme in the Q node tasks.

[0050] The solution with the highest collaborative fitness among the Q node tasks is selected as the Q-node robot control optimization result. The Q-node robot control optimization results are stored using blockchain technology, generating a robot control optimization block. The most critical data is stored on the blockchain. Larger amounts of data (such as detailed control solution data and evaluation metrics) can be stored in an off-chain database. The data in the block is immutable; all robot control solutions for the task are recorded and can be queried and verified at any time.

[0051] On-chain storage involves storing data directly within the blockchain network. Blockchain's immutable and decentralized nature ensures data security and reliability. The advantages of on-chain storage include transparency, permanent storage, and public verification. Off-chain storage involves storing data in a storage system external to the blockchain, such as a traditional database or distributed storage system. While off-chain storage typically offers higher storage capacity and faster data access, it suffers from lower security and transparency compared to on-chain storage. A robot control optimization block is a data block stored within the blockchain that contains relevant data about the robot control optimization process, including optimization results such as the control plan for task execution, task completion accuracy, body collaboration efficiency, and reliability.

[0052] Through variation and optimization, the control scheme is continuously improved, which can cope with complex and changing tasks and environments, generate the control scheme that best suits the current task, improve the accuracy, efficiency and reliability of task completion, and especially show better collaborative capabilities in multi-robot collaboration.

[0053] Furthermore, the present application further comprises the following steps:

[0054] Connect the robot control inspection channel and retrieve the robot control evaluation results corresponding to the robot control candidate schemes in the q-th node robot control candidate domain; perform mutation value evaluation on the robot control candidate schemes according to the robot control evaluation results to obtain the mutation value coefficient of each candidate scheme; input the mutation value coefficient of each candidate scheme into the robot control mutation function to establish the q-th mutation constraint rule, wherein the q-th mutation constraint rule includes the number of mutations of each candidate scheme corresponding to the robot control candidate schemes; mutate the q-th node robot control candidate domain according to the q-th mutation constraint rule to generate the q-th node robot control mutation domain, and add the q-th node robot control mutation domain to the robot control Q-dimensional mutation space.

[0055] Specifically, the robot control inspection channel is connected to retrieve the robot control evaluation results corresponding to each robot control candidate solution within the q-th node robot control candidate domain, including each robot control candidate solution's task completion accuracy, limb collaboration efficiency, and limb collaboration reliability. Based on the robot control evaluation results, a variation value assessment is performed on each robot control candidate solution to obtain each candidate solution's variation value coefficient. The variation value coefficient is a coefficient calculated through the variation value assessment that characterizes the variation potential of each candidate control solution and is used to determine the magnitude of variation. A higher variation value coefficient indicates a greater potential and necessity for variation in the solution, potentially having a greater impact on task execution. The robot control evaluation results are standardized and normalized, and each indicator is assigned a different weight based on the importance and priority of the task. The variation value coefficient is then calculated through weighted averaging.

[0056] By inputting the mutation value coefficient of each candidate solution into the robot control mutation function and combining the mutation value coefficients, mutation constraints are generated, establishing the qth mutation constraint rule. The mutation constraint rule determines how many mutations are performed for each candidate solution, that is, the number of mutations for each robot control candidate solution. For example, solutions with higher mutation value coefficients will have more mutation operations. The mutation constraint rule ensures that the number and magnitude of mutation operations are appropriate, avoiding performance instability caused by excessive or insufficient mutations.

[0057] Based on the generated qth mutation constraint rule, the qth-node robot control candidate domain is mutated. This means that the control solution in the qth-node task is mutated. By adjusting control parameters (such as motion amplitude, timing, and speed), a new control strategy is generated, forming the qth-node robot control mutation domain. The qth-node robot control mutation domain refers to the set of new control solutions generated through mutation operations in the qth-node task. For example, if the number of mutations is determined to be 5 according to the mutation constraint rule, five new control solutions will be generated and added to the mutation domain.

[0058] The q-th node robot control variation domain is added to the Q-dimensional robot control variation space. The above steps are repeated for the remaining node tasks within the Q-node task, resulting in the Q-node robot control variation domains corresponding to the Q-node tasks. Together, these domains constitute the Q-dimensional robot control variation space. The Q-dimensional robot control variation space is a high-dimensional space consisting of all candidate control solutions generated through mutation of the Q-node tasks. Each dimension represents a node task, and the control solution is mutated along these dimensions. By evaluating and constraining the mutation value of candidate control solutions, more potential solutions are explored, increasing the likelihood of finding a more optimal solution, thereby comprehensively improving collaboration effectiveness and task completion accuracy.

[0059] Furthermore, the present application further comprises the following steps:

[0060] The robot control variation function is:

[0061] ; Among them, SDN represents the number of candidate solution variations, FLOOR refers to rounding down, SDK represents the predetermined number of variations, SXC represents the candidate solution variation value coefficient, and SXO represents the predetermined candidate solution variation value coefficient.

[0062] Specifically, the robot control variation function adjusts the predetermined number of variations, SDK, based on the comparison of the candidate solution's variation value coefficient, SXC, and the candidate solution's predetermined variation value coefficient, SXO, to determine the final candidate solution variation value, SDN. SDN represents the candidate solution variation value, indicating the number of times a candidate solution varies during the robot control strategy optimization process; FLOOR refers to rounding down, which means rounding a value down to the nearest integer; SDK represents the predetermined number of variations, i.e., the number of variations allowed in the initial settings; SXC represents the candidate solution variation value coefficient, indicating the degree of variation for each candidate control decision; and SXO represents the predetermined candidate solution variation value coefficient, a preset standard variation value coefficient used for comparison with the candidate solution's variation value coefficient.

[0063] When SXC < SXO, it indicates that the mutation value of the candidate solution is lower than expected. A reduction function is used to adjust the number of mutations, aiming to control the number of mutations so that it is not too drastic and maintain a certain stability. The number of mutations is rounded down by the FLOOR function to ensure that the number of mutations is an integer. When SXC = SXO, the mutation value of the candidate solution exactly meets the expectation, and the number of mutations remains the predetermined number of mutations SDK, that is, no additional mutation adjustment is performed, and the mutations are carried out according to the preset number of mutation times. When SXC > SXO, the mutation value of the candidate solution is higher than expected, and the number of mutations increases, meaning that the mutation value of the current candidate solution is relatively large, and a larger mutation amplitude is required, which helps to accelerate the exploration of more control strategies to adapt to possible new task requirements or environmental changes.

[0064] Exemplarily, assume that the predetermined number of mutations is 10 times, the predetermined mutation value coefficient of the candidate solution is 5, and the mutation value coefficient of the current candidate solution is 3. At this time, SXC < SXO, so the first formula is used for calculation. By dynamically adjusting the number of mutations, the problems of excessive mutations or insufficient mutations are avoided, ensuring that the optimization process can effectively explore the optimization space and find better solutions.

[0065] S500: Execute the multi-limb collaborative control of the bionic robot according to the robot control optimization block.

[0066] Specifically, the robot control optimization block contains the optimization results of the task execution control schemes of multiple nodes and stores the key control information of task execution (such as the selection of control schemes, task completion accuracy, collaboration efficiency, etc.). By executing the optimization results in the robot control optimization block, the best control scheme for each node task is provided for the bionic robot. According to the optimization results in the robot control optimization block, a suitable control scheme is selected for each node task, and the multi-limb robot needs to collaborate according to the control scheme.

[0067] According to the best control scheme of each task result, determine the specific parameters of each scheme, including limb movements, timings, force control, etc. Convert the best control scheme into an instruction format that the robot can understand and send it to the limb control modules of the bionic robot to ensure that the instructions are distributed to the corresponding limbs in the correct order and time nodes. Each limb starts to execute actions according to the received instructions, and the motion state of the limb is monitored in real time to ensure the accuracy and coordination of the actions. During the task execution, if real-time feedback or external environmental changes (such as changes in object weight, narrow space, etc.) affect the task progress, the robot will adjust the actions of each limb by referring to the control scheme in the optimization block. <After completing the actions of all task nodes, the overall task completion status is evaluated, including task completion accuracy, limb collaboration efficiency, and limb collaboration reliability. Multi-limb collaborative control is the coordination and cooperation of multiple limbs (such as arms and legs) in a multi-limb robot system when performing complex tasks. Each limb adjusts its movements based on the environment and task requirements to ensure that the bionic robot completes the task efficiently and accurately. By adopting an optimized control scheme, the bionic robot can precisely control the movements of each limb according to task requirements and environmental conditions, ensuring high-precision task completion. Multi-limb collaborative control can reduce ineffective or repetitive movements and improve the robot's overall task execution efficiency. By using the optimal collaboration scheme, the robot can complete the task in a shorter time and avoid redundant movements.

[0069] In summary, the multi-limb collaborative control method of a bionic structure provided by this application has the following technical effects:

[0070] The method involves sequentially sorting out pending tasks of a bionic robot to establish a pending task chain, wherein the bionic robot comprises N limbs and the pending task chain comprises Q node tasks, where N and Q are both positive integers greater than 1; making collaborative control decisions for the N limbs based on the pending task chain to establish a Q-dimensional robot control space; performing test optimization on the Q-dimensional robot control space based on a robot control test channel to establish a Q-dimensional candidate robot control space; introducing a robot control variation function and a collaborative fitness analytical model to perform mutation, expansion, and optimization on the Q-dimensional candidate robot control space to obtain a robot control optimization block; and executing multi-limb collaborative control of the bionic robot based on the robot control optimization block. Specifically, by sequentially sorting out pending tasks and establishing a task chain, making collaborative control decisions for each limb based on the task chain, and selecting the optimal control strategy for the bionic robot's multi-limb collaborative control based on the robot control test channel, the robot control variation function, and the collaborative fitness analytical model, the method optimizes the collaborative movements between the limbs, enhances the adaptability of the multi-limb collaborative control strategy in complex environments, and improves the task execution efficiency of the bionic robot.

[0071] Example 2: Based on the same inventive concept as the multi-limb collaborative control method of a bionic structure in the aforementioned Example 1, this application also provides a multi-limb collaborative control system of a bionic structure, please refer to the attached Figure 2 The multi-limb collaborative control system of the bionic structure includes:

[0072] The task timing combing module 11 is used to perform timing combing on the tasks to be executed of the bionic robot and establish a chain of tasks to be executed, wherein the bionic robot includes N limbs, and the chain of tasks to be executed includes Q node tasks, and N and Q are both positive integers greater than 1; the collaborative control decision module 12 is used to make collaborative control decisions on the N limbs according to the chain of tasks to be executed and establish a Q-dimensional robot control space; the inspection and optimization module 13 is used to inspect and optimize the Q-dimensional robot control space according to the robot control inspection channel and establish a Q-dimensional candidate space for robot control; the variation and expansion optimization module 14 is used to introduce the robot control variation function and the collaborative fitness analytical model to perform variation and expansion optimization on the Q-dimensional candidate space for robot control and obtain a robot control optimization block; the collaborative control execution module 15 is used to execute multi-limb collaborative control of the bionic robot according to the robot control optimization block.

[0073] Furthermore, the collaborative control decision module 12 in the multi-limb collaborative control system of the bionic structure is further used to:

[0074] According to the task chain to be executed, extract the qth node task, where 1≤q≤Q; collect the scene information of the qth node task to obtain the qth task scene; use the qth task scene as the collaborative control scene constraint and the qth node task as the collaborative control target to make control decisions for the N limbs and establish a qth node robot control domain; and add the qth node robot control domain to the Q-dimensional robot control space.

[0075] Furthermore, the inspection and optimization module 13 in the multi-limb collaborative control system of the bionic structure is also used for:

[0076] Traverse the q-th node robot control domain and extract the first robot control decision; simulate and control the bionic robot according to the first robot control decision to obtain a first simulated collaborative data set; input the first simulated collaborative data set into the robot control inspection channel to obtain a first robot control inspection result; when the first robot control inspection result is qualified, set the first robot control decision as the first robot control candidate solution, and add the first robot control candidate solution to the q-th node robot control candidate domain; when the first robot control inspection result is unqualified, eliminate the first robot control decision; continue to inspect and optimize the q-th node robot control domain according to the robot control inspection channel, construct the q-th node robot control candidate domain, and add the q-node robot control candidate domain to the robot control Q-dimensional candidate space.

[0077] Furthermore, the inspection and optimization module 13 in the multi-limb collaborative control system of the bionic structure is also used for:

[0078] The robot control inspection channel includes a robot control evaluation model and a control inspection model; the first simulated collaboration data set is input into the robot control evaluation model to obtain a first robot control evaluation result, wherein the robot control evaluation model includes a robot control multidimensional evaluation index, and the robot control multidimensional evaluation index includes task completion accuracy, limb collaboration efficiency and limb collaboration reliability; the first robot control evaluation result is input into the control inspection model, and the first robot control inspection result is output, wherein the control inspection model includes a control inspection operator, and the control inspection operator includes: if the first robot control evaluation result meets the robot control inspection constraint, the first robot control inspection result is qualified; if the first robot control evaluation result does not meet the robot control inspection constraint, the first robot control inspection result is unqualified, and the robot control inspection constraint includes a predetermined task completion accuracy, a predetermined limb collaboration efficiency and a predetermined limb collaboration reliability.

[0079] Furthermore, the variation expansion optimization module 14 in the multi-limb cooperative control system of the bionic structure is also used for:

[0080] The robot control Q-dimensional candidate space is mutated according to the robot control mutation function to establish a robot control Q-dimensional mutation space; the robot control Q-dimensional mutation space is tested and optimized according to the robot control test channel to obtain a robot control Q-dimensional mutation optimization space; the robot control Q-dimensional candidate space is expanded according to the robot control Q-dimensional mutation optimization space to obtain a robot control Q-dimensional optimization space; the robot control Q-dimensional optimization space is optimized for collaborative fitness maximization according to the collaborative fitness analytical model to obtain Q-node robot control optimization results, wherein the collaborative fitness analytical model includes task completion accuracy weights, limb collaboration efficiency weights and limb collaboration reliability weights; the Q-node robot control optimization results are stored on-chain and off-chain to generate the robot control optimization block.

[0081] Furthermore, the variation expansion optimization module 14 in the multi-limb cooperative control system of the bionic structure is also used for:

[0082] Connect the robot control inspection channel and retrieve the robot control evaluation results corresponding to the robot control candidate schemes in the q-th node robot control candidate domain; perform mutation value evaluation on the robot control candidate schemes according to the robot control evaluation results to obtain the mutation value coefficient of each candidate scheme; input the mutation value coefficient of each candidate scheme into the robot control mutation function to establish the q-th mutation constraint rule, wherein the q-th mutation constraint rule includes the number of mutations of each candidate scheme corresponding to the robot control candidate schemes; mutate the q-th node robot control candidate domain according to the q-th mutation constraint rule to generate the q-th node robot control mutation domain, and add the q-th node robot control mutation domain to the robot control Q-dimensional mutation space.

[0083] Furthermore, the variation expansion optimization module 14 in the multi-limb cooperative control system of the bionic structure is also used for:

[0084] The robot control variation function is:

[0085] ; Among them, SDN represents the number of candidate solution variations, FLOOR refers to rounding down, SDK represents the predetermined number of variations, SXC represents the candidate solution variation value coefficient, and SXO represents the predetermined candidate solution variation value coefficient.

[0086] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The multi-limb collaborative control method and specific examples of a bionic structure in Example 1 are also applicable to a multi-limb collaborative control system of a bionic structure in this embodiment. Through the detailed description of the multi-limb collaborative control method of a bionic structure, those skilled in the art can clearly understand the multi-limb collaborative control system of a bionic structure in this embodiment, so for the sake of brevity, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method section.

[0087] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present application. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application is not limited to the embodiments shown herein, but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

[0088] Obviously, those skilled in the art may make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A multi-limb collaborative control method for a bionic structure, characterized in that: include: Time-sequencing the tasks to be performed by the bionic robot to establish a task chain to be performed, wherein the bionic robot includes N limbs, the task chain to be performed includes Q node tasks, and N and Q are both positive integers greater than 1; Making collaborative control decisions on the N limbs according to the task chain to be executed, and establishing a Q-dimensional robot control space; Testing and optimizing the Q-dimensional robot control space according to a robot control test channel to establish a robot control Q-dimensional candidate space, wherein the robot control test channel includes a robot control evaluation model and a control test model; A robot control variation function and a collaborative fitness analytical model are introduced to perform mutation expansion optimization on the robot control Q-dimensional candidate space to obtain a robot control optimization block. The collaborative fitness analytical model includes a task completion accuracy weight, a limb collaboration efficiency weight, and a limb collaboration reliability weight. Executing multi-limb collaborative control of the bionic robot according to the robot control optimization block; The robot control variation function is: ； Among them, SDN represents the number of candidate solution variations, FLOOR refers to rounding down, SDK represents the predetermined number of variations, SXC represents the candidate solution variation value coefficient, and SXO represents the predetermined candidate solution variation value coefficient.

2. The multi-limb collaborative control method of a bionic structure according to claim 1, characterized in that: Making collaborative control decisions for the N limbs according to the task chain to be executed, and establishing a Q-dimensional robot control space, including: Extract the qth node task according to the task chain to be executed, where 1≤q≤Q; Collecting scene information of the qth node task to obtain the qth task scene; Taking the qth task scenario as the collaborative control scenario constraint and the qth node task as the collaborative control target, control decisions are made on the N limbs to establish a qth node robot control domain; Add the q-th node robot control domain to the Q-dimensional robot control space.

3. The multi-limb collaborative control method of a bionic structure according to claim 1, characterized in that: The Q-dimensional robot control space is tested and optimized according to the robot control test channel to establish a robot control Q-dimensional candidate space, including: Traverse the robot control domain of the qth node and extract the first robot control decision; According to the first robot control decision, simulate and control the bionic robot to obtain a first simulated collaboration data set; Inputting the first simulated collaborative data set into the robot control inspection channel to obtain a first robot control inspection result; When the first robot control test result is qualified, setting the first robot control decision as a first robot control candidate solution, and adding the first robot control candidate solution to the qth node robot control candidate domain; When the first robot control inspection result is unqualified, eliminating the first robot control decision; The q-th node robot control domain is continuously tested and optimized according to the robot control test channel, the q-th node robot control candidate domain is constructed, and the q-th node robot control candidate domain is added to the robot control Q-dimensional candidate space.

4. The multi-limb collaborative control method of a bionic structure according to claim 3, characterized in that: Inputting the first simulated collaborative data set into the robot control inspection channel to obtain a first robot control inspection result includes: Inputting the first simulated collaboration data set into the robot control evaluation model to obtain a first robot control evaluation result, wherein the robot control evaluation model includes a robot control multidimensional evaluation index, and the robot control multidimensional evaluation index includes task completion accuracy, limb collaboration efficiency, and limb collaboration reliability; The first robot control evaluation result is input into the control verification model, and the first robot control verification result is output, wherein the control verification model includes a control verification operator, and the control verification operator includes: if the first robot control evaluation result satisfies the robot control verification constraint, the first robot control verification result is qualified; if the first robot control evaluation result does not satisfy the robot control verification constraint, the first robot control verification result is unqualified, and the robot control verification constraint includes a predetermined task completion accuracy, a predetermined limb collaboration efficiency, and a predetermined limb collaboration reliability.

5. The multi-limb collaborative control method of a bionic structure according to claim 1, characterized in that: The robot control mutation function and the collaborative fitness analytical model are introduced to perform mutation expansion optimization on the robot control Q-dimensional candidate space to obtain the robot control optimization block, including: mutating the robot control Q-dimensional candidate space according to the robot control mutation function to establish a robot control Q-dimensional mutation space; Performing an inspection and optimization on the robot control Q-dimensional variation space according to the robot control inspection channel to obtain the robot control Q-dimensional variation optimization space; Expanding the robot control Q-dimensional candidate space according to the robot control Q-dimensional variation optimization space to obtain the robot control Q-dimensional optimization space; Perform collaborative fitness maximization optimization on the robot control Q-dimensional optimization space according to the collaborative fitness analytical model to obtain Q-node robot control optimization results; The control optimization results of the Q node robots are stored on and off the chain to generate the robot control optimization block.

6. The multi-limb collaborative control method of a bionic structure according to claim 5, characterized in that: Mutating the robot control Q-dimensional candidate space according to the robot control mutation function to establish a robot control Q-dimensional mutation space includes: Connecting to the robot control inspection channel, retrieving each robot control evaluation result corresponding to each robot control candidate solution in the q-th node robot control candidate domain; Performing a variation value evaluation on each candidate robot control scheme according to the control evaluation results of each robot, and obtaining a variation value coefficient of each candidate scheme; Inputting the variation value coefficient of each candidate solution into the robot control variation function to establish a qth variation constraint rule, wherein the qth variation constraint rule includes the variation quantity of each candidate solution corresponding to each robot control candidate solution; The q-th node robot control candidate domain is mutated according to the q-th mutation constraint rule to generate a q-th node robot control mutation domain, and the q-th node robot control mutation domain is added to the robot control Q-dimensional mutation space.

7. A bionic multi-limb collaborative control system, characterized in that: Steps for implementing a multi-limb collaborative control method of a bionic structure according to any one of claims 1 to 6, wherein the multi-limb collaborative control system of a bionic structure comprises: A task timing combing module is used to perform timing combing on the tasks to be executed of the bionic robot and establish a task chain to be executed, wherein the bionic robot includes N limbs, the task chain to be executed includes Q node tasks, and N and Q are both positive integers greater than 1; A collaborative control decision module is used to make collaborative control decisions on the N limbs according to the task chain to be executed, and establish a Q-dimensional robot control space; a test and optimization module, configured to test and optimize the Q-dimensional robot control space according to a robot control test channel, and establish a robot control Q-dimensional candidate space, wherein the robot control test channel includes a robot control evaluation model and a control test model; a mutation and expansion optimization module for introducing a robot control mutation function and a collaborative fitness analytical model to perform mutation and expansion optimization on the robot control Q-dimensional candidate space to obtain a robot control optimization block, wherein the collaborative fitness analytical model includes a task completion accuracy weight, a limb collaboration efficiency weight, and a limb collaboration reliability weight; A collaborative control execution module, configured to execute multi-limb collaborative control of the bionic robot according to the robot control optimization block; The robot control variation function is: ； Among them, SDN represents the number of candidate solution variations, FLOOR refers to rounding down, SDK represents the predetermined number of variations, SXC represents the candidate solution variation value coefficient, and SXO represents the predetermined candidate solution variation value coefficient.

Images