Heavy-load mechanical arm man-machine cooperative control method based on double-layer game

Abstract

The invention belongs to the technical field of heavy-load mechanical arm man-machine cooperative control systems, and particularly relates to a heavy-load mechanical arm man-machine cooperative control method based on a double-layer game, which comprises the following steps: firstly, an operator and an automatic control system respectively send control signals according to the current environment; thirdly, the upper-layer game permission distribution system obtains the optimal control permission according to the control signals of the two cooperative control parties and the current environment state, and sends the optimal control permission to the lower-layer game man-machine interaction model; then, the man-machine interaction model optimizes control signals of an operator and an automatic control system in real time by solving Nash balance; and finally, the optimal control signals are fused through the optimal control authority, the fused control signals are output to the heavy-load mechanical arm, and heavy-load mechanical arm man-machine cooperative control based on the double-layer game is achieved. According to the method, the influence of man-machine conflicts on the man-machine cooperative control performance of the heavy-load mechanical arm can be effectively reduced, and the working efficiency and safety of the heavy-load mechanical arm are improved to the maximum extent.

Description

Technical Field

[0001] The present invention relates to the technical field of heavy-duty manipulator man-machine collaborative control systems, and specifically to a heavy-duty manipulator man-machine collaborative control method based on double-layer game. Background Art

[0002] Heavy-duty robotic arms have been widely used in unstructured environments such as mining, emergency rescue, and construction due to their excellent efficiency in high-load tasks. However, compared with conventional robotic arms in industrial scenarios, heavy-duty robotic arms have large motion inertia, multiple degrees of freedom, and frequent large-load impacts, which not only increase the workload of operators, but also easily lead to the risk of operating errors, posing a huge challenge to the operating efficiency and safety of heavy-duty robotic arms. To this end, researchers have tried to apply automation technology to heavy-duty robotic arms to reduce the workload of operators and improve the operating efficiency and safety of heavy-duty robotic arms. However, in the face of complex and changeable unstructured environments, the dynamic adaptability and rapid decision-making capabilities of existing heavy-duty robotic arm automatic control systems are insufficient, making it difficult to effectively respond to highly dynamic changes in the environment.

[0003] Human-machine collaborative control technology integrates the operator's ability to adapt to complex environments and the high-precision control capabilities of the automatic control system. Through the complementary advantages of both parties, it is expected to greatly improve the operating efficiency and safety of heavy-duty manipulators. Existing research on heavy-duty manipulators mainly achieves human-machine collaborative control by considering environmental risks and operator status, but rarely pays attention to the conflict between the operator and the automatic control system. In an unstructured working environment, operators usually face a high workload and are prone to distraction and fatigue, which leads to differences in their understanding of the task environment and the automatic control system, thus causing human-machine conflicts, which not only affects the human-machine collaborative control performance of the heavy-duty manipulator, but may even cause potential safety hazards to the heavy-duty manipulator. Therefore, there is an urgent need for a human-machine collaborative control method for heavy-duty manipulators that can effectively eliminate human-machine conflicts, so as to give full play to the advantages of both parties and improve the operating efficiency and safety of heavy-duty manipulators.

[0004] Game theory has significant advantages in dealing with issues involving mutual influence or conflicts of interest among multiple participants. In human-machine conflict scenarios, the interaction between the operator and the automatic control system is consistent with the characteristics of differential games. Therefore, game theory is widely used in the modeling of interactive behaviors under conflict conditions of multi-agent systems, and can provide a theoretical basis for designing safer and more efficient human-machine collaborative control systems. At present, the human-machine collaborative control method based on game mainly constructs the human-machine interaction relationship between the operator and the automatic control system through the game model, optimizes the control signals between the operator and the automatic control system, and thus reduces human-machine conflicts. However, these studies usually adopt a fixed allocation strategy for the setting of human-machine collaborative control authority, and cannot perform adaptive adjustments in complex and changeable unstructured environments, resulting in the inability to maximize the human-machine collaborative control performance of heavy-duty robotic arms. Summary of the invention

[0005] 1. Technical issues to be resolved In view of the deficiencies of the prior art, the present invention provides a method for human-machine collaborative control of a heavy-duty manipulator based on a two-layer game, which comprehensively considers the human-machine conflict, the degree of participation of the operator and the automatic control system, and the risk of collision avoidance, constructs an upper-layer game model for human-machine collaboration of a heavy-duty manipulator, and adaptively obtains human-machine collaborative control authority; the lower layer constructs a human-machine interaction model for a heavy-duty manipulator based on game theory, and provides assistance that is more in line with the characteristics of the operator by understanding the interactive behavior between the operator and the automatic control system, thereby effectively solving the problem of human-machine conflict while achieving human-machine collaborative control. Through the upper-layer game and the lower-layer game, the influence of human-machine conflict on the performance of human-machine collaborative control is eliminated to the maximum extent, and the optimal effect of human-machine collaborative control of the heavy-duty manipulator is achieved. On the basis of reducing the workload of the operator, the operating efficiency and operating safety of the heavy-duty manipulator are maximized, and the problem of low working efficiency and safety hazards caused by human-machine conflict in the human-machine collaborative control system of the heavy-duty manipulator is solved.

[0006] (II) Technical solution In order to achieve the above-mentioned purpose, the present invention specifically adopts the following technical solutions: A human-machine collaborative control method for a heavy-duty manipulator based on a double-layer game comprises the following steps: S1. The operator and the automatic control system send control signals to the heavy-loaded robotic arm according to the current environment. , ; S2. The upper-level game authority allocation system constructs the utility function of the operator and the automatic control system based on the control signals of the operator and the automatic control system and the current environmental status. , , solve the optimal control authority of the current operator and automatic control system through game theory ( , ) and sent to the lower-level game human-computer interaction model; S3. The lower-level game human-computer interaction model combines the control authority of the current operator and the automatic control system, and constructs a cost function that conforms to the control characteristics of the operator and the automatic control system based on the distributed model predictive control algorithm. The human-computer interaction behavior of the operator and the automatic control system is constructed based on the Nash game theory, and the Nash optimal control signal of the operator and the automatic control system is solved through the Nash equilibrium. , ; S4. Integrate the human-machine collaborative control authority of the heavy-duty robotic arm and the Nash optimal control signals of the operator and the automatic control system, and output the integrated control signals to the heavy-duty robotic arm to achieve human-machine collaborative control of the heavy-duty robotic arm based on a two-layer game.

[0007] Furthermore, the control signals of the operator and the automatic control system are combined with the current environmental state to construct the collision avoidance risk sub-utility, human-machine conflict sub-utility and participation sub-utility about control authority. Function of Before constructing the utility function, the discrete space state equation of the heavy-duty manipulator human-machine collaborative control is first constructed as follows: (1) Where: is the system state vector, The system output vector includes the position information of the end of the robot arm. is the system state matrix, is the system input matrix, is the system output matrix, Control input of automatic control system, Control input for the operator.

[0008] The collision avoidance risk subutility function is as follows: Keeping the current control signal and control authority unchanged, iterative formula (1) constructs the future The position status of the heavy-duty robot arm end of the step is related to the control authority Functional relationship ; (2); Construct the collision avoidance risk subutility function: (3) Where: , are the collision avoidance risk subutility functions of the operator and the automatic control system, It is the obstacle location information.

[0009] The human-machine conflict subutility function is as follows: Considering the deviation between the operator and the control signal of the automatic control system, the corresponding human-machine conflict sub-utility function is constructed as follows: (4) Where: , They represent the human-machine conflict sub-utility functions of the operator and the automatic control system respectively.

[0010] The participation subutility function is as follows: In order to optimize the control process and improve safety, it is hoped that both the operator and the automatic control system will participate in the collaborative control, and neither party will be given complete control authority. The participation sub-utility function of the operator and the automatic control system is constructed as follows: (5) Where: , are the participation sub-utility functions of the operator and the automatic control system, respectively. is the coefficient; Furthermore, the sub-utility functions established above are integrated to construct the utility function of the operator and the automatic control system: (6) Where: , are the utility functions of the operator and the automatic control system, respectively. is the normalization coefficient; According to formula (6), Nash product is constructed , and solve the optimal control authority of heavy-duty manipulator human-machine collaboration : (7).

[0011] Furthermore, in the process of human-machine collaborative control, both the operator and the automatic control system will do their best to make the heavy-loaded robot arm track their respective target trajectories, and will consider the intervention of the other party in collaborative control before executing the control action; By iterating formula (1), we can get the future The prediction output expression of step: (8) in, Depend on The value composition at each prediction step is, , , , and are the vectors and matrices obtained through iteration; With the goal of minimizing the deviation between the control signal and the actual position and the target trajectory, the cost functions of the operator and the automatic control system can be constructed: (9) Where: and are the penalty coefficient matrices for target trajectory deviation and control amount, respectively. and Represent the cost functions of the automatic control system and the operator respectively; In non-cooperative games, there is a set of control combinations that prevents participants from gaining more benefits by unilaterally changing the control input. Similarly, in this study, there is a Nash equilibrium solution for the operator and the automatic control system. The final Nash equilibrium strategy can be solved by using the distributed model predictive control method: (10) in, It represents the Nash equilibrium strategy of the human-machine collaborative control system of the heavy-duty manipulator; By integrating the optimal control authority allocated at the current moment And the Nash equilibrium solution for both humans and machines , obtain the optimal coordinated control signal of the heavy-duty manipulator , realize the human-machine collaborative control of heavy-duty manipulator based on double-layer game; (11) in, It is the optimal collaborative control signal of the heavy-load robot arm at the current moment.

[0012] (III) Beneficial effects Compared with the prior art, the present invention provides a human-machine collaborative control method for a heavy-duty manipulator based on a double-layer game, which has the following beneficial effects: The present invention comprehensively considers the human-machine conflict, participation and collision risk between the operator and the automatic control system, obtains the optimal control authority through the upper-level game, optimizes the control signals of the operator and the automatic control system based on the lower-level Nash game human-machine interaction model, and integrates the optimal control signals of the lower-level operator and the automatic control system with the human-machine collaborative control authority, thereby realizing human-machine collaborative control of the heavy-duty robotic arm based on the double-layer game, which can not only effectively solve the human-machine conflict problem in the human-machine collaborative control of the heavy-duty robotic arm, but also improve the operating efficiency and safety of the heavy-duty robotic arm. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 It is a research roadmap of the human-machine collaborative control method of the heavy-duty manipulator based on double-layer game of the present invention; Figure 2 It is a research route for the upper-level human-machine collaborative control authority allocation based on game theory of the present invention; Figure 3 This is a schematic diagram of the human-computer interaction model of the lower-level heavy-load robotic arm based on game theory of the present invention. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] Example like Figure 1 , Figure 2 and Figure 3 As shown, an embodiment of the present invention proposes: a method for human-machine collaborative control of a heavy-duty manipulator based on a double-layer game, comprising the following steps: S1. The operator and the automatic control system send control signals to the heavy-loaded robotic arm according to the current environment. , ; S2. The upper-level game authority allocation system constructs the utility function of the operator and the automatic control system based on the control signals of the operator and the automatic control system and the current environmental status. , , solve the optimal control authority of the current operator and automatic control system through game theory ( , ) and sent to the lower-level game human-computer interaction model; S3. The lower-level game human-computer interaction model combines the control authority of the current operator and the automatic control system, and constructs a cost function that conforms to the control characteristics of the operator and the automatic control system based on the distributed model predictive control algorithm. The human-computer interaction behavior of the operator and the automatic control system is constructed based on the Nash game theory, and the Nash optimal control signal of the operator and the automatic control system is solved through the Nash equilibrium. , ; S4. Integrate the human-machine collaborative control authority of the heavy-duty robotic arm and the Nash optimal control signals of the operator and the automatic control system, and output the integrated control signals to the heavy-duty robotic arm to achieve human-machine collaborative control of the heavy-duty robotic arm based on a two-layer game.

[0016] First, the control signals of the operator and the automatic control system are combined with the current environmental state to construct the collision avoidance risk sub-utility, human-machine conflict sub-utility and participation sub-utility about control authority. Function of Before constructing the utility function, the discrete space state equation of the heavy-duty manipulator human-machine collaborative control is first constructed as follows: (1) Where: is the system state vector, The system output vector includes the position information of the end of the robot arm. is the system state matrix, is the system input matrix, is the system output matrix, Control input of automatic control system, Control input for the operator.

[0017] The collision avoidance risk sub-utility function, human-machine conflict sub-utility function, and participation sub-utility function are as follows: (1) Collision avoidance risk subutility function: Keeping the current control signal and control authority unchanged, iterative formula (1) constructs the future The position status of the heavy-duty robot arm end of the step is related to the control authority Functional relationship ; (2); Construct the collision avoidance risk subutility function: (3) Where: , are the collision avoidance risk subutility functions of the operator and the automatic control system, It is the obstacle location information.

[0018] (2) Human-machine conflict sub-utility function: Considering the deviation between the operator and the control signal of the automatic control system, the corresponding human-machine conflict sub-utility function is constructed as follows: (4) Where: , They represent the human-machine conflict sub-utility functions of the operator and the automatic control system respectively.

[0019] (3) Participation sub-utility function: In order to optimize the control process and improve safety, it is hoped that both the operator and the automatic control system will participate in the collaborative control, and neither party will be given complete control authority. The participation sub-utility function of the operator and the automatic control system is constructed as follows: (5) Where: , are the participation sub-utility functions of the operator and the automatic control system, respectively. is the coefficient; The utility functions of the operator and the automatic control system are constructed by integrating the sub-utility functions established above: (6) Where: , are the utility functions of the operator and the automatic control system, respectively. is the normalization coefficient; According to formula (6), Nash product is constructed , and solve the optimal control authority of heavy-duty manipulator human-machine collaboration : (7).

[0020] In the process of human-machine collaborative control, both the operator and the automatic control system will do their best to make the heavy-loaded robot arm track their respective target trajectories, and will consider the intervention of the other party in collaborative control before executing the control action; By iterating formula (1), we can get the future The prediction output expression of the step is: (8) in, Depend on The value composition at each prediction step is, , , , and are the vectors and matrices obtained through iteration; With the goal of minimizing the deviation between the control signal and the actual position and the target trajectory, the cost functions of the operator and the automatic control system can be constructed: (9) Where: and are the penalty coefficient matrices for target trajectory deviation and control amount, respectively. and Represent the cost functions of the automatic control system and the operator respectively; In non-cooperative games, there is a set of control combinations that prevents participants from gaining more benefits by unilaterally changing the control input. Similarly, in this study, there is a Nash equilibrium solution for the operator and the automatic control system. The final Nash equilibrium strategy can be solved by using the distributed model predictive control method: (10) in, It represents the Nash equilibrium strategy of the human-machine collaborative control system of the heavy-duty manipulator; By integrating the optimal control authority allocated at the current moment And the Nash equilibrium solution for both humans and machines , obtain the optimal coordinated control signal of the heavy-duty manipulator , realize the human-machine collaborative control of heavy-duty manipulator based on double-layer game; (11) in, It is the optimal collaborative control signal of the heavy-load robot arm at the current moment.

[0021] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A human-machine collaborative control method for a heavy-duty manipulator based on a double-layer game, characterized in that: The steps include: S1. The operator and the automatic control system send control signals to the heavy-loaded robotic arm according to the current environment. , ; S2. The upper-level game authority allocation system constructs the utility function of the operator and the automatic control system based on the control signals of the operator and the automatic control system and the current environmental status. , , solve the optimal control authority of the current operator and automatic control system through game theory ( , ) and sent to the lower-level game human-computer interaction model; S3. The lower-level game human-computer interaction model combines the control authority of the current operator and the automatic control system, and constructs a cost function that conforms to the control characteristics of the operator and the automatic control system based on the distributed model predictive control algorithm. The human-computer interaction behavior of the operator and the automatic control system is constructed based on the Nash game theory, and the Nash optimal control signal of the operator and the automatic control system is solved through the Nash equilibrium. , ; S4. Integrate the human-machine collaborative control authority of the heavy-duty robotic arm and the Nash optimal control signals of the operator and the automatic control system, and output the integrated control signals to the heavy-duty robotic arm to achieve human-machine collaborative control of the heavy-duty robotic arm based on a two-layer game.

2. According to claim 1, a method for human-machine collaborative control of a heavy-duty manipulator based on double-layer game, characterized in that: By combining the control signals of the operator and the automatic control system with the current environmental state, the collision avoidance risk sub-utility, the human-machine conflict sub-utility and the participation sub-utility are constructed for control authority. Function of Before constructing the utility function, the discrete space state equation of the heavy-duty manipulator human-machine collaborative control is first constructed as follows: (1) Where: is the system state vector, The system output vector includes the position information of the end of the robot arm. is the system state matrix, is the system input matrix, is the system output matrix, Control input of automatic control system, Provides control input for operators; The collision avoidance risk subutility function is as follows: Keeping the current control signal and control authority unchanged, iterative formula (1) constructs the future The position status of the heavy-duty robot arm end of the step is related to the control authority Functional relationship ; (2)； Construct the collision avoidance risk subutility function: (3) Where: , are the collision avoidance risk subutility functions of the operator and the automatic control system, is the obstacle location information; The human-machine conflict sub-utility function is as follows: Considering the deviation between the operator and the control signal of the automatic control system, the corresponding human-machine conflict sub-utility function is constructed as follows: (4) Where: , They represent the human-machine conflict sub-utility functions of the operator and the automatic control system respectively; The participation sub-utility function is as follows: In order to optimize the control process and improve safety, it is hoped that both the operator and the automatic control system will participate in the collaborative control, and neither party will be given complete control authority. The participation sub-utility function of the operator and the automatic control system is constructed as follows: (5) Where: , are the participation sub-utility functions of the operator and the automatic control system, respectively. is the coefficient; The utility functions of the operator and the automatic control system are constructed by integrating the sub-utility functions established above: (6) Where: , are the utility functions of the operator and the automatic control system, is the normalization coefficient; According to formula (6), Nash product is constructed , and solve the optimal control authority of heavy-duty manipulator human-machine collaboration : (7)。 3. According to claim 1, a method for human-machine collaborative control of a heavy-duty manipulator based on double-layer game, characterized in that: In the process of human-machine collaborative control, the operator and the automatic control system will do their best to make the heavy-loaded robot arm track their respective target trajectories, and will consider the intervention of the other party in the collaborative control before executing the control action; By iterating formula (1), we can get the future The prediction output expression of step: (8) in, Depend on The value composition at each prediction step is, , , , and are the vectors and matrices obtained through iteration; With the goal of minimizing the deviation between the control signal and the actual position and the target trajectory, the cost functions of the operator and the automatic control system can be constructed: (9) Where: and are the penalty coefficient matrices for target trajectory deviation and control amount, respectively. and Represent the cost functions of the automatic control system and the operator respectively; In non-cooperative games, there is a set of control combinations that prevents participants from gaining more benefits by unilaterally changing the control input. Similarly, in this study, there is a Nash equilibrium solution for the operator and the automatic control system. The final Nash equilibrium strategy can be solved by using the distributed model predictive control method: (10) in, It represents the Nash equilibrium strategy of the human-machine collaborative control system of the heavy-duty manipulator; By integrating the optimal control authority allocated at the current moment And the Nash equilibrium solution for both humans and machines , obtain the optimal coordinated control signal of the heavy-duty manipulator , realize the human-machine collaborative control of heavy-duty manipulator based on double-layer game; (11) in, It is the optimal collaborative control signal of the heavy-load robot arm at the current moment.

Images