Multi-arm mobile robot cooperative control framework and multi-arm mobile robot system

Abstract

The invention provides a multi-arm mobile robot cooperative control framework and a multi-arm mobile robot system, and is applied to the technical field of mobile composite multi-arm robots. A mechanical arm tail end error estimation module obtains the tail end pose error of each mechanical arm; the multi-arm collaborative cost module obtains the state difference between the mechanical arms; the reinforcement learning module is used for dynamically and adaptively adjusting the collaborative cost weight of the multi-arm collaborative cost module by taking the difference value between the pose predicted value and the expected value of the tail end of each mechanical arm and the state difference between the mechanical arms as input; the mechanical arm tail end error estimation module and the multi-arm cooperative cost module are enabled to iteratively pursue minimization, and a plurality of mechanical arms of the multi-arm mobile robot are controlled to perform cooperative operation. On the basis of the cooperative control framework, action interference existing in cooperative operation control of the multi-arm robot can be avoided, the adaptability, motion precision and stability of the multi-arm robot are improved, and efficient cooperation among multiple arms is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of mobile composite multi-arm robots, and in particular to a multi-arm mobile robot collaborative control framework and a multi-arm robot system. Background Art

[0002] In many fields such as modern industrial production, logistics handling, emergency rescue, etc., higher requirements are placed on the operation ability and flexibility of robots. Mobile composite multi-arm robots, such as four-arm mobile robots with four arms installed on a mobile chassis, have attracted much attention because they can move and realize the coordinated operation of multiple robotic arms.

[0003] However, there are many problems in the collaborative operation control of four-arm mobile robots. For example, traditional control strategies make it difficult to achieve real-time coordination between multiple arms, resulting in interference between the actions of each arm when performing a task, making it impossible to complete the task efficiently.

[0004] Based on this, a new technical solution is needed. Summary of the invention

[0005] In view of this, the present application provides a multi-arm mobile robot collaborative control framework and a multi-arm mobile robot system.

[0006] This application provides the following technical solutions: A multi-arm mobile robot collaborative control framework provided in this application includes the following modules: Manipulator end error estimation module: calculates the difference between the predicted value and the expected value of the pose of each manipulator end to obtain the pose error of each manipulator end; Multi-arm collaborative cost module: obtains the state difference between each robotic arm and couples the state difference between each robotic arm through collaborative cost weight; Reinforcement learning module: using the difference between the predicted value and the expected value of the pose of each robotic arm and the state difference between each robotic arm as input, the collaborative cost weight of the multi-arm collaborative cost module is dynamically and adaptively adjusted; The robot end error estimation module and the multi-arm collaborative cost module are iteratively pursued to be minimized, and multiple robot arms of the multi-arm mobile robot are controlled to work collaboratively.

[0007] A multi-arm mobile robot system is also provided according to the present application, comprising: Task data analysis and allocation module: analyzes the motion of the multi-arm mobile robot and the robot arm operation tasks to obtain analysis data; Collaborative operation behavior planning and chassis motion coupling compensation unit: Apply the collaborative control framework of multi-arm mobile robots to perform chassis motion behavior prediction, multi-arm kinematic coupling, and multi-arm workspace constraints based on analytical data to generate control data; Mobile robot control solving unit: solves the generated control data, generates robot chassis motion planning instructions and each robotic arm control instructions, and sends them to the underlying motion controller after dynamic compensation, thereby controlling the actions of each actuator.

[0008] Preferably, the collaborative operation behavior planning and chassis motion coupling compensation unit includes: Chassis motion behavior prediction unit: According to the motion path planned by the mobile robot and based on the dynamic base model of the robot, the motion state parameters at the next moment are predicted; Multi-arm kinematic coupling unit: Based on the kinematic model of the robot arm, the robot arm motion planning is coupled to the chassis dynamic base coordinate system, eliminating the robot arm end positioning error caused by chassis movement, and realizing the real-time conversion of the end target posture of the robot arm based on the global coordinate system into the chassis dynamic coordinate system; Workspace constraint unit: optimizes the workspace and trajectory of multiple arms based on the robot arm perception fusion data and collaborative strategy.

[0009] Compared with the prior art, the beneficial effects that can be achieved by at least one of the above technical solutions adopted in the present application include at least: The present application calculates the difference between the predicted value and the expected value of the posture of each robot end through the robot end error estimation module to obtain the posture error of each robot end; obtains the state difference between each robot arm through the multi-arm collaborative cost module, and couples it through the collaborative cost weight; the reinforcement learning module uses the difference between the predicted value and the expected value of the posture of each robot end and the state difference between each robot arm as input, and dynamically and adaptively adjusts the collaborative cost weight; so that the robot end error estimation module and the multi-arm collaborative cost module iteratively pursue minimization, control the multiple robot arms of the multi-arm mobile robot to perform constrained collaborative operation, and form a multi-arm multi-modal collaborative control strategy for the multi-arm robot. Under the constraints of this collaborative framework, the multi-arm robots can realize mutual collaborative operation, avoid the motion interference of the multi-arm robots in collaborative operation control, improve the adaptability, motion accuracy and stability of the multi-arm robots, realize efficient collaboration between multiple arms, and improve the robot's ability to operate in complex environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0011] Figure 1 It is a schematic diagram of the process of collaborative control of a multi-arm mobile robot in this application; Figure 2 It is a schematic diagram of the process of error estimation of the end of the robot arm in this application; Figure 3 It is a flow chart corresponding to the input data of the multi-arm collaborative cost function in this application; Figure 4 It is a flowchart of the reinforcement learning algorithm in this application; Figure 5 Schematic diagram of the multi-arm mobile robot system in this application. DETAILED DESCRIPTION

[0012] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0013] The following describes the implementation methods of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, in the absence of conflict, the following embodiments and the features in the embodiments can be combined with each other. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0014] It should be noted that various aspects of the embodiments within the scope of the appended claims are described below. It should be apparent that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is merely illustrative. Based on the present application, it should be understood by those skilled in the art that an aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspect described herein can be used to implement the device and / or practice the method. In addition, other structures and / or functionalities other than one or more of the aspects described herein can be used to implement this device and / or practice this method.

[0015] It should also be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present application. The drawings only show components related to the present application rather than being drawn according to the number, shape and size of components in actual implementation. In actual implementation, the type, quantity and proportion of each component may be changed arbitrarily, and the component layout may also be more complicated.

[0016] Additionally, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the examples can be practiced without these specific details.

[0017] The applicant conducted in-depth research and improvement on the control of multi-arm composite mobile robots and found that: when faced with complex environments and task changes, the existing control strategy has poor adaptability and cannot quickly adjust the movements of each arm to meet new task requirements. In addition, the existing control method is insufficient in ensuring the accuracy and stability of multi-arm motion, which affects the robot's operating quality.

[0018] Based on this, the technical solutions provided by the embodiments of the present application are described below in conjunction with the accompanying drawings.

[0019] The embodiments of this specification propose a multi-arm mobile robot collaborative control framework, such as Figure 1 As shown, it includes the following modules: Manipulator end error estimation module: Calculate the difference between the predicted value and the expected value of the pose of each manipulator end to obtain the pose error of each manipulator end. When calculating the pose error of each manipulator end, the difference between the predicted value and the expected value of the pose of each manipulator end is used, not the difference between the actual value and the expected value. This method is conducive to the rapid iteration of this item, thereby accelerating the convergence speed and improving the performance of the system.

[0020] Multi-arm collaborative cost module: obtains the state difference between each robotic arm, and couples the state difference between each robotic arm through collaborative cost weights.

[0021] Reinforcement learning module: Taking the difference between the predicted value and the expected value of the posture of each robotic arm and the state difference between each robotic arm as input, the collaborative cost weight of the multi-arm collaborative cost module is dynamically and adaptively adjusted to accelerate or strengthen the iteration of the multi-arm collaborative cost module towards the minimum direction.

[0022] In order to iteratively pursue minimization of the error estimation module at the end of the robotic arm and the multi-arm collaborative cost module, multiple robotic arms of the multi-arm mobile robot are controlled to perform collaborative operations to improve the collaborative operation accuracy and multi-arm collaborative performance.

[0023] Among them, the objective function is based on the minimum cumulative sum of the end position error matrix and the multi-arm collaborative cost function matrix. The error estimation matrix of the end of the manipulator calculates the difference between the predicted value and the expected value of the pose of each end of the manipulator to obtain the pose error of each manipulator; the state difference between each manipulator and the adjacent manipulator is obtained through the multi-arm collaborative cost function matrix, and the state differences between all manipulators are coupled by collaborative cost weights.

[0024] In one embodiment, if Figure 1 As shown, the collaborative control framework also includes a multimodal data fusion calculation module: modal fusion calculation is performed based on the multimodal data of each robotic arm to obtain fused modal data. The multimodal data fusion calculation module sends the fused modal data to the controller of each robotic arm and the environmental coupling repulsive field model. Among them, for example, data alignment, time synchronization; anomaly detection / repair; dynamic weight calculation, etc.

[0025] The overall system adopts a multi-modal data layering and dynamic weighted fusion strategy to improve the operational robustness of each robotic arm. The multi-modal fusion calculation module implements modal fusion calculation based on the multi-sensory data of each robotic arm, such as IMU (Inertial Measurement Unit), vision, force data, etc.

[0026] The results of the multimodal fusion calculation are sent to the controller of each robotic arm to realize the data fusion of the modal data and the robotic arm solution data; on the other hand, they are sent to the environmental repulsive field model unit of each robotic arm as its input data.

[0027] In one embodiment, if Figure 1 and Figure 2 As shown, the controller of each robot arm performs robot arm kinematics solution on the robot arm joint encoder data to obtain solution data, fuses the solution data and fused modal data to obtain fused calculation data, performs extended Kalman prediction on the fused calculation data, and predicts and outputs the posture prediction value of each robot arm end.

[0028] In the process of obtaining the predicted value of the posture of the end of the robotic arm, a multi-modal data layering and dynamic weighted fusion strategy is adopted to realize the fusion processing of each robotic arm modal data (such as robotic arm joint encoder, visual positioning information, IMU data and force sensor information), and the kinematic coupling term between the robotic arms is introduced as the predicted value of the extended Kalman.

[0029] In one embodiment, if Figure 1 and Figure 2 As shown, the controller of each robotic arm estimates the predicted value of the posture of each robotic arm end using an extended Kalman filter based on the geometric constraints between the robotic arms; Among them, the geometric constraints satisfied by the relative posture of the ends of each pair of manipulators are: ; in, h c Represents geometric constraints; i represents a robotic arm, j represents another robotic arm; T i Represents the posture transformation matrix corresponding to a robotic arm; T j Represents the posture transformation matrix corresponding to the other robotic arm; represents the theoretical relative pose. i and j Represent different robotic arms, T i and T j is the pose transformation matrix.

[0030] Therefore, each robotic arm estimates the end pose value of each robotic arm based on its own multimodal data fusion results and under the geometric constraints between them using an extended Kalman filter.

[0031] In one embodiment, if Figure 1 and Figure 3 As shown, the environmental coupling repulsive field model of each robotic arm will fuse the modal data and environmental state perception data to form the environmental coupling repulsive field model data as the input of the multi-arm collaborative cost module to enable real-time calculation and minimize iteration of the multi-arm collaborative cost module.

[0032] Specifically, each robotic arm performs fusion calculations based on its own multimodal perception data, and uses its own environmental state perception data as input to form its own environmental coupling repulsive field model data as the input of the cost function.

[0033] By performing real-time task weight adjustment, nonlinear correction calculation, and environmental coupling repulsive field calculation on each robotic arm, the collaborative cost function calculation can meet the requirements. Based on the calculation of the established multi-arm collaborative cost function matrix, the real-time calculation and minimization iteration of the multi-arm collaborative cost function are realized, thereby maximizing the collaboration between the robotic arms and improving the collaborative performance and accuracy.

[0034] When adjusting the task weights, the weights of various cost items (such as position error, posture error, etc.) are adjusted in real time according to the dynamic changes in task requirements to balance the synergy between different arms. For example, in actual operations, the position error of some manipulators is more important than the posture error, while the posture error of other manipulators is more important in operation. Therefore, it is necessary to dynamically adjust the task weights according to the different requirements of the system tasks so that the iterative calculation results of the cost function are more in line with the expected requirements.

[0035] Since the dynamic modeling of the robot arm and environmental constraints will produce nonlinear errors, nonlinear errors need to be corrected to improve the accuracy of the model and the coordination of control. Therefore, for different robot arms, certain nonlinear corrections need to be made according to their dynamic models and motion constraints to make the pose estimation or calculation in the cost function more accurate.

[0036] The essence of the environmental coupling repulsive field model is to prevent collisions between manipulators during coordinated actions. The input of the environmental coupling repulsive field model calculation is multimodal fusion data and environmental perception data as input constraint data of the model. The output of the environmental coupling repulsive field model will affect the iterative calculation direction and results of the cost function together with the task weight and nonlinear correction calculation.

[0037] In one embodiment, if Figure 1 and Figure 4 As shown, the reinforcement learning module calculates synchronously with the robot end error estimation module and the multi-arm collaborative cost module, takes the state difference data set as the input state space, performs reinforcement training and learning based on the state difference data set, dynamically corrects the weight value in the multi-arm collaborative cost module, and performs dynamic adaptive adjustment of the dynamic weight coefficient matrix in the multi-arm collaborative cost function matrix.

[0038] Among them, the reinforcement learning algorithm, the input state space is the state difference between each robot in the collaborative cost matrix; reinforcement training and learning are carried out based on the state difference data set, and the rapid realization of its minimum value is its target task. The output of the reinforcement learning algorithm is the dynamic weight coefficient matrix in the collaborative cost function, and the weights in the collaborative cost function are dynamically adjusted. The reward function in the reinforcement learning algorithm can adopt a variety of combinations; for example Figure 4 In an embodiment, a parameter function of the end execution of the robot arm is used as a reward function, or a combination of multiple parameters, such as end error, force uniformity, energy consumption, etc., which are comprehensively considered as a reward function.

[0039] In one embodiment, if Figure 1 , Figure 2 as well as Figure 3 As shown, the robot end error estimation module includes the robot end posture error estimation matrix: ; in, Indicates the desired position of the end effector of the robot arm; Represents the predicted result value of the actual position and posture of the end effector of the robot arm; represents the pose error weight matrix; T Represents the transpose of a matrix.

[0040] The multi-arm coordination cost module includes a multi-arm coordination cost function matrix, that is, the difference between the state of each robotic arm and the state of the adjacent robotic arms: ; in, u i Represents the end state matrix of a robotic arm; u j represents the end state matrix of the other robot; R u Represents the dynamic weight matrix of the collaborative cost function. After the state differences between all arms are coupled by the collaborative cost dynamic weight, a multi-arm collaborative cost function is formed; the multi-arm collaborative cost function matrix is ​​the same as the aforementioned robot end error matrix in pursuing the minimum strategy, and the multi-arm collaborative work is realized on the premise of pursuing the minimum value.

[0041] In one embodiment, if Figure 1 As shown in the figure, the objective function consists of three parts: the error matrix of the end of the robot arm, the multi-arm collaborative cost function matrix, and the reinforcement learning algorithm. The expression of the objective function of the collaborative control framework is:

[0042] in, Represents the reinforcement learning algorithm term, which is the objective function of cumulative reward; The discount factor N The power is used to adjust the weight of future rewards, that is, to adjust the importance of future rewards. The larger the value, the greater the weight of future rewards. N Indicates the total number of steps or total time; t Indicates time or number of steps; is the reward function, which represents the immediate reward based on the instruction value and the feedback prediction value; represents the immediate feedback prediction value, Indicates the immediate instruction value; E is the expectation operator, which means taking the average value. In the end-of-arm posture error term, the predicted value of the actual end-of-arm posture is used instead of the traditional actual value of the end, in order to improve the convergence speed of the posture error term and reduce the actual posture error, thereby improving the collaborative accuracy.

[0043] The reinforcement learning algorithm term is also one of the objective functions, but it is embedded in the objective function in the calculation, and the cost coefficient in the multi-arm collaborative cost function matrix is ​​executed. R u Perform dynamic adaptive adjustments to enhance multi-arm collaborative performance and accelerate the convergence of the objective function.

[0044] The present application provides a coordinated operation control strategy and control architecture for a mobile composite multi-arm robot, which is applicable to composite multi-arm collaborative operation robots, forming a multi-arm multi-modal collaborative control strategy for multi-arm robots. Under the constraints of this collaborative framework, multi-arm robots can achieve mutual collaborative operation. It solves the problems of motion interference, poor adaptability, and insufficient motion accuracy and stability in the collaborative operation control of existing multi-arm robots, realizes efficient collaboration between multiple arms, and improves the robot's ability to operate in complex environments.

[0045] This application constrains the multi-arm mobile robot through the cooperative control framework objective function, and controls the multiple mechanical arms of the multi-arm mobile robot to work in coordination. Among them, the reinforcement learning algorithm is also included in the objective function, and is calculated synchronously with the other two items. The reinforcement learning calculation uses the state difference data set generated by the cost function matrix as the training sample data, and dynamically corrects the weight value in the multi-arm cooperative cost function, so as to make the multi-arm cooperative cost function converge faster and obtain a lower value, thereby improving the coordination accuracy.

[0046] The present specification also discloses a multi-arm mobile robot system. Figure 5 As shown, including: Task data analysis and allocation module: analyzes the motion and manipulator operation tasks of the multi-arm mobile robot to obtain analysis data. For example, the motion and manipulator operation tasks of the four-arm mobile robot are analyzed based on the content such as the robot order, and the data is sent to the collaborative operation behavior planning and chassis motion coupling compensation unit.

[0047] The collaborative operation behavior planning and chassis motion coupling compensation unit performs chassis motion behavior prediction, multi-arm kinematic coupling and multi-arm workspace constraints based on the analytical data to generate control data.

[0048] Mobile robot control solving unit: solves the generated control data, generates robot chassis motion planning instructions and each robotic arm control instructions, and sends them to the underlying motion controller after dynamic compensation, thereby controlling the actions of each actuator.

[0049] Specifically, the data generated by the above-mentioned collaborative operation and chassis coupling compensation unit are analyzed and solved, and become robot chassis motion planning instructions and each manipulator control instruction respectively, and are sent to the underlying motion controller after dynamic compensation to execute the motion instructions of each motor. For example, the predicted motion state parameters at the next moment are converted into the end target position of the manipulator in the chassis dynamic coordinate system in real time, as well as the optimized multi-arm workspace and trajectory data for solution.

[0050] In one embodiment, the collaborative operation behavior planning and chassis motion coupling compensation unit includes: Chassis motion behavior prediction unit: According to the motion path planned by the mobile robot and based on the dynamic base model of the robot, the motion state parameters at the next moment are predicted.

[0051] Multi-arm kinematic coupling unit: Based on the kinematic model of the robot arm, the dynamic base coordinate system of the chassis is coupled for the robot arm motion planning, the positioning error of the end of the robot arm caused by the chassis movement is eliminated, and the end target posture of the robot arm based on the global coordinate system is converted into the chassis dynamic coordinate system in real time.

[0052] Workspace constraint unit: Optimize the workspace and trajectory of multiple arms based on the robot perception fusion data and collaborative strategy to avoid interference between the robots and between the robot and chassis. The constraint unit may include robot singular point postures, collaborative strategy constraints, etc.

[0053] When the four arms of a four-arm mobile robot work collaboratively, they are also affected by the movement behavior of the mobile chassis. Therefore, the influence of chassis movement on the collaborative operation of the four arms should be considered in system control. Based on this idea, this application proposes a four-arm mobile robot system framework to compensate for the chassis movement in the collaborative control of the four arms.

[0054] In this specification, the same or similar parts between the various embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the embodiments described later, the description is relatively simple, and the relevant parts can be referred to the partial description of the previous embodiments.

[0055] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A collaborative control framework for a multi-arm mobile robot, characterized in that: Includes the following modules: Manipulator end error estimation module: calculates the difference between the predicted value and the expected value of the pose of each manipulator end to obtain the pose error of each manipulator end; Multi-arm collaborative cost module: obtains the state difference between each robotic arm and couples the state difference between each robotic arm through collaborative cost weight; Reinforcement learning module: using the difference between the predicted value and the expected value of the pose of each robotic arm and the state difference between each robotic arm as input, the collaborative cost weight of the multi-arm collaborative cost module is dynamically and adaptively adjusted; The robot end error estimation module and the multi-arm collaborative cost module are iteratively pursued to be minimized, and multiple robot arms of the multi-arm mobile robot are controlled to work collaboratively.

2. The multi-arm mobile robot collaborative control framework according to claim 1, characterized in that: The collaborative control framework also includes: a multimodal data fusion calculation module: performing modal fusion calculation based on the multimodal data of each robotic arm to obtain fused modal data; The multimodal data fusion calculation module sends the fused modal data to the controller of each robotic arm and the environmental coupling repulsive field model.

3. The multi-arm mobile robot collaborative control framework according to claim 2, characterized in that: The controller of each robot arm performs robot arm kinematics solution on the robot arm joint encoder data to obtain solution data, fuses the solution data with the fused modal data to obtain fused calculation data, performs extended Kalman prediction on the fused calculation data, and predicts and outputs the posture prediction value of each robot arm end.

4. The multi-arm mobile robot collaborative control framework according to claim 3, characterized in that: The controller of each robotic arm estimates the predicted value of the position and posture of each robotic arm end using an extended Kalman filter based on the geometric constraints between the robotic arms. Among them, the geometric constraints satisfied by the relative posture of the ends of each pair of manipulators are: ； in, h c Represents geometric constraints; i represents a robotic arm, j represents another robotic arm; T i Represents the posture transformation matrix corresponding to a robotic arm; T j Represents the posture transformation matrix corresponding to the other robotic arm; represents the theoretical relative pose.

5. The multi-arm mobile robot collaborative control framework according to claim 2, characterized in that: The environmental coupling repulsive field model of each robotic arm will fuse the modal data and environmental state perception data to form environmental coupling repulsive field model data as the input of the multi-arm collaborative cost module to enable real-time calculation and minimize iteration of the multi-arm collaborative cost module.

6. The multi-arm mobile robot collaborative control framework according to claim 1, characterized in that: The reinforcement learning module calculates synchronously with the robot end error estimation module and the multi-arm collaborative cost module, uses the state difference data set generated by the state difference of each robot arm as the input state space, performs reinforcement training and learning based on the state difference data set, and dynamically corrects the weight value in the multi-arm collaborative cost module.

7. The multi-arm mobile robot collaborative control framework according to claim 1, characterized in that: The manipulator end error estimation module includes a manipulator end posture error estimation matrix: ； in, Indicates the desired position of the end effector of the robot arm; Represents the predicted result value of the actual position and posture of the end effector of the robot arm; represents the pose error weight matrix; T Represents the transpose of a matrix; The multi-arm coordination cost module includes a multi-arm coordination cost function matrix: ； in, u i Represents the end state matrix of a robotic arm; u j represents the end state matrix of the other robot; R u Represents the dynamic weight matrix of the collaborative cost function.

8. The multi-arm mobile robot collaborative control framework according to claim 7, characterized in that: The objective function expression of the collaborative control framework is: ； in, Represents the reinforcement learning algorithm term; The discount factor N The power is used to adjust the weight of future rewards; N Indicates the total number of steps; is the reward function, which represents the immediate reward based on the instruction value and the feedback prediction value; represents the immediate feedback prediction value, Indicates the immediate instruction value; E is the expectation operator, which means taking the average value.

9. A multi-arm mobile robot system, characterized in that: include: Task data analysis and allocation module: analyzes the motion of the multi-arm mobile robot and the robot arm operation tasks to obtain analysis data; Collaborative operation behavior planning and chassis motion coupling compensation unit: applying the collaborative control framework of the multi-arm mobile robot described in any one of claims 1 to 8, performing chassis motion behavior prediction, multi-arm kinematic coupling and multi-arm workspace constraints according to analytical data to generate control data; Mobile robot control solving unit: solves the generated control data, generates robot chassis motion planning instructions and each robotic arm control instructions, and sends them to the underlying motion controller after dynamic compensation, thereby controlling the actions of each actuator.

10. The multi-arm mobile robot system according to claim 9, characterized in that: The collaborative operation behavior planning and chassis motion coupling compensation unit includes: Chassis motion behavior prediction unit: According to the motion path planned by the mobile robot and based on the dynamic base model of the robot, the motion state parameters at the next moment are predicted; Multi-arm kinematic coupling unit: Based on the kinematic model of the robot arm, the robot arm motion planning is coupled to the chassis dynamic base coordinate system, eliminating the robot arm end positioning error caused by chassis movement, and realizing the real-time conversion of the end target posture of the robot arm based on the global coordinate system into the chassis dynamic coordinate system; Workspace constraint unit: optimizes the workspace and trajectory of multiple arms based on the robot arm perception fusion data and collaborative strategy.

Images