A massage robot control method and system based on variable impedance adaptive control

Abstract

The application discloses a massage robot control method and system based on variable impedance adaptive control, and relates to the technical field of robots. The method comprises the following steps: establishing a kinematics model of a multi-degree-of-freedom robot system; positioning a target acupoint according to a human body posture; determining a target pose of a massage head at the end of the multi-degree-of-freedom robot system according to the target acupoint; solving an inverse kinematics equation of the kinematics model according to the target pose to obtain a joint angle vector corresponding to the multi-degree-of-freedom robot system; constructing an overall control law according to the joint angle vector and an adaptive variable impedance control law; and controlling the multi-degree-of-freedom robot system according to the overall control law so that the massage head at the end massages the target acupoint. The overall control law is constructed by the joint angle vector and the adaptive variable impedance control law, and the multi-degree-of-freedom robot system is controlled based on the overall control law, so that the compliance and safety of massage are improved.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a control method and system for a massage robot based on variable impedance adaptive control. Background Technology

[0002] With the increasing demand for health management and rising labor costs, massage robots, as key equipment in the field of intelligent physiotherapy and rehabilitation, are receiving more and more attention. Compared with traditional manual massage, robots have inherent advantages such as high control precision, good operational consistency, and continuous operation, and are expected to provide users with standardized and reproducible massage services.

[0003] Currently, research on massage robots mainly focuses on mechanical structure design, acupoint trajectory planning, and basic position and force control. In recent years, collaborative robot technology based on vision and force sensors has been applied to the execution of preliminary massage movements. In terms of more refined interactive control, advanced strategies such as impedance / admittance control have demonstrated excellent compliance in surgical and rehabilitation robots. However, existing massage robot systems still have significant bottlenecks: First, they lack real-time and accurate perception of the user's muscle physiological state, making it impossible to distinguish between relaxed, tense, or fatigued muscle tissue, resulting in a lack of truly personalized massage strategies; second, their dynamic adaptability during interaction is insufficient, and fixed control parameters are difficult to cope with the dynamic changes in muscle stiffness during massage, easily generating excessive transient contact forces when muscles experience sudden tension, affecting comfort and safety; third, the massage effect is difficult to quantify and evaluate, and closed-loop feedback is difficult to achieve. Summary of the Invention

[0004] The main objective of this application is to propose a massage robot control method and system based on variable impedance adaptive control, so as to improve the massage comfort and safety of the massage robot.

[0005] To achieve the above objectives, one aspect of this application proposes a control method for a massage robot based on variable impedance adaptive control, the method comprising the following steps: Establish a kinematic model for a multi-degree-of-freedom robot system; Locate the target acupoints based on the human body posture; The target pose of the end effector massage head of the multi-degree-of-freedom robot system is determined based on the target acupoints. Based on the target pose, the inverse kinematic equations of the kinematic model are solved to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system. The overall control law is constructed based on the joint angle vector and the adaptive variable impedance control law. The multi-degree-of-freedom robot system is controlled according to the overall control law so that the end effector massage head massages the target acupoint.

[0006] In some embodiments, the coordinate system of the multi-degree-of-freedom robot system includes: Represents the robot's base coordinate system. Indicates the coordinate system of the corresponding end flange. Indicates the center coordinate system of the end massage head. This represents the camera coordinate system fixed at the end of the robot. This represents the coordinate system of acupoint markers on the user's body surface; The process of establishing a kinematic model for a multi-degree-of-freedom robot system includes the following steps: Define the closed chain from the base to the massage point as: ; The corresponding perception chain is constructed as follows: ; By employing a hand-eye calibration process, a fixed homogeneous transformation matrix is ​​obtained from the camera coordinate system {cam} to the end coordinate system {e}. ; The coordinate system of the end massage head is determined using a tool calibration method. Relative to the end flange coordinate system The fixed homogeneous transformation matrix under ; Using the chain rule, from each joint angle The position of the end flange under the base was determined by forward kinematics calculation. : ; Among them, the transformation matrix of adjacent links The modified Denavit-Hartenberg parameter method was used to establish: ; In the formula Describe the first i The joint angle, link offset, link length, and link torsion angle of each joint; The pose of the center of the end massage head in the base coordinate system is defined as follows: .

[0007] In some embodiments, solving the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system includes the following steps: By integrating the Newton-Raphson numerical iteration and analytical solution methods, and adhering to the joint motion space constraints and singularity avoidance principles, the inverse kinematic equations are solved to obtain the joint angle vectors. The inverse kinematic equation is: ; in, Let the target pose be... Let be the joint angle vector.

[0008] In some embodiments, locating the target acupoint based on human posture includes the following steps: The intrinsic parameter matrix and distortion coefficients of the camera are obtained using the Zhang Zhengyou calibration method; wherein, the multi-degree-of-freedom robot system includes the camera; ; in, K This is the intrinsic parameter matrix; In hand-eye calibration, the fixed transformation relationship between the camera and robot end-effector coordinate systems is calculated using the Tsai-Lenz method. ; A human pose estimation model is used to detect target regions of the human body; the model outputs two-dimensional pixel coordinates including predicted anatomical points. and three-dimensional coordinates ; A parameterized standard acupoint atlas is constructed based on traditional Chinese medicine theory. The standard acupoint atlas represents the spatial relationship between acupoints and candidate anatomical points. The standard acupoint map is spatially aligned with the predicted anatomical points using a nonlinear registration algorithm, and the coordinates of the target acupoint are calculated using affine transformation or thin-plate spline transformation. The depth information of the target acupoint is acquired using an RGB-D camera, and the three-dimensional coordinates of the target acupoint in the camera coordinate system are calculated by back-projection using the camera's intrinsic parameter matrix. ; The coordinates of the target acupoint in the base coordinate system are obtained through coordinate transformation: ; in, P 0 serves as the input for trajectory planning, guiding the end massage head to the target acupoint.

[0009] In some embodiments, the adaptive variable impedance control law is constructed through the following steps: The adaptive variable impedance control law is constructed as follows: ; in, The muscle stiffness is dynamically estimated and obtained through the fusion of multimodal sensor information; , which is the adaptive damping parameter; , which is the adaptive stiffness parameter; This is a muscle fatigue index; , These are nominal parameters; , It is an adaptive function; The differential gain coefficient of the contact force; , is a rectified linear unit function; This is a function of the direction of the contact force.

[0010] In some embodiments, constructing the overall control law based on the joint angle vector and the adaptive variable impedance control law includes the following steps: The overall control law for constructing the multi-degree-of-freedom robot system is as follows: ; in, The joint angle vector, The inertia matrix, Includes the Coriolis force and centripetal force matrix. For gravity, Indicates the joint control torque. It is a Jacobian matrix; The impedance relation in Cartesian space is mapped to joint space using the Jacobian matrix: ; The complete control torque is: .

[0011] In some embodiments, the method further includes the steps of estimating muscle state and defining a parameter adaptive strategy, specifically including: Muscle stiffness is estimated by fusing electromyographic signals and mechanical responses. : ; in, These are the weighting coefficients reflecting the degree of muscle activation, viscous properties, and elastic properties, respectively. The parameter adaptive strategy is defined using a combination of fuzzy logic and linear interpolation as follows: ; ; in, This is the baseline value for muscle stiffness in a relaxed state. This is the adaptive gain coefficient.

[0012] To achieve the above objectives, another aspect of this application proposes a massage robot control system based on variable impedance adaptive control, the system comprising: Kinematic modeling unit, used to build kinematic models of multi-degree-of-freedom robot systems; Acupoint positioning unit, used to locate target acupoints based on human posture; The pose determination unit is used to determine the target pose of the end-effector massage head of the multi-degree-of-freedom robot system based on the target acupoint. The joint angle solving unit is used to solve the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system. A control law construction unit is used to construct an overall control law based on the joint angle vector and the adaptive variable impedance control law. A massage control unit is used to control the multi-degree-of-freedom robot system according to the overall control law, so that the end effector massage head massages the target acupoint.

[0013] To achieve the above objectives, another aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0014] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0015] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a control method and system for a massage robot based on adaptive impedance control. The solution involves establishing a kinematic model of a multi-degree-of-freedom robot system; locating target acupoints based on human posture; determining the target pose of the end effector massage head based on the target acupoints; solving the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system; constructing an overall control law based on the joint angle vectors and the adaptive impedance control law; and controlling the multi-degree-of-freedom robot system according to the overall control law to enable the end effector massage head to massage the target acupoints. This application constructs an overall control law using joint angle vectors and the adaptive impedance control law, and controlling the multi-degree-of-freedom robot system based on this overall control law improves the compliance and safety of the massage. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart illustrating a massage robot control method based on variable impedance adaptive control, provided in an embodiment of this application; Figure 2 A schematic diagram of a massage robot system provided in an embodiment of this application; Figure 3 This is a block diagram of the adaptive variable proportional impedance control for a massage robot provided in an embodiment of this application; Figure 4 A schematic diagram of a massage robot control system based on variable impedance adaptive control provided in an embodiment of this application; Figure 5 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of systems and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0021] Before providing a detailed description of the embodiments of this application, some related technologies involved in the embodiments of this application will be described first, as follows: Current technologies cannot form a complete "perception-decision-execution-optimization" loop. Essentially, massage is a dynamic, two-way human-machine physical interaction process. There is a close dynamic coupling between the robot's movement and the forces / torques it applies to the human body. Although advanced algorithms such as Model Predictive Control (MPC) can handle such multivariate constrained problems, their massive computational demands pose a severe challenge to the system's real-time performance. Impedance / admittance control provides a more computationally efficient framework for achieving dynamic equilibrium between force and position, but traditional methods have fixed parameters and cannot adapt to the highly nonlinear and time-varying "environment" of human muscles. Therefore, how to enable the robot's control parameters to adapt online to the real-time physiological state of the muscles is the core scientific problem for achieving safe, comfortable, and efficient massage.

[0022] Based on the above analysis, inspired by the traditional Chinese medicine principle of "tonifying deficiency and purging excess," and drawing on advanced human-computer interaction control theory, this application proposes a variable admittance control scheme for a massage robot based on electromyography-force feedback. The core of this application lies in using surface electromyography signals as an advanced observer reflecting muscle activation and fatigue states, combining them with contact force information to construct an adaptive control law that dynamically adjusts admittance parameters according to muscle state. This not only fundamentally improves the smoothness and safety of the interaction but also lays a crucial technological foundation for achieving the leap from "mechanical execution" to "intelligent therapy."

[0023] Reference Figure 1 This application provides a control method for a massage robot based on variable impedance adaptive control. This method may include, but is not limited to, steps S100 to S150, as follows: S100: Establish the kinematic model of a multi-degree-of-freedom robot system; S110: Locate target acupoints based on human posture; S120: Determine the target pose of the end-effector massage head of the multi-degree-of-freedom robot system based on the target acupoint; S130: Based on the target pose, solve the inverse kinematic equations of the kinematic model to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system; S140: Construct the overall control law based on the joint angle vector and the adaptive variable impedance control law; S150: Control the multi-degree-of-freedom robot system according to the overall control law so that the end effector massage head massages the target acupoint.

[0024] Optionally, the coordinate system of the multi-degree-of-freedom robot system includes: Represents the robot's base coordinate system. Indicates the coordinate system of the corresponding end flange. Indicates the center coordinate system of the end massage head. This represents the camera coordinate system fixed at the end of the robot. This represents the coordinate system of acupoint markers on the user's body surface; The process of establishing a kinematic model for a multi-degree-of-freedom robot system includes the following steps: Define the closed chain from the base to the massage point as: ; The corresponding perception chain is constructed as follows: ; By employing a hand-eye calibration process, a fixed homogeneous transformation matrix is ​​obtained from the camera coordinate system {cam} to the end coordinate system {e}. ; The coordinate system of the end massage head is determined using a tool calibration method. Relative to the end flange coordinate system The fixed homogeneous transformation matrix under ; Using the chain rule, from each joint angle The position of the end flange under the base was determined by forward kinematics calculation. : ; Among them, the transformation matrix of adjacent links The modified Denavit-Hartenberg parameter method was used to establish: ; In the formula Describe the first i The joint angle, link offset, link length, and link torsion angle of each joint; The pose of the center of the end massage head in the base coordinate system is defined as follows: .

[0025] Optionally, the step of solving the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system includes the following steps: By integrating the Newton-Raphson numerical iteration and analytical solution methods, and adhering to the joint motion space constraints and singularity avoidance principles, the inverse kinematic equations are solved to obtain the joint angle vectors. The inverse kinematic equation is: ; in, Let the target pose be... Let be the joint angle vector.

[0026] Optionally, locating the target acupoint based on human posture includes the following steps: The intrinsic parameter matrix and distortion coefficients of the camera are obtained using the Zhang Zhengyou calibration method; wherein, the multi-degree-of-freedom robot system includes the camera; ; in, K This is the intrinsic parameter matrix; In hand-eye calibration, the fixed transformation relationship between the camera and robot end-effector coordinate systems is calculated using the Tsai-Lenz method. ; A human pose estimation model is used to detect target regions of the human body; the model outputs two-dimensional pixel coordinates including predicted anatomical points. and three-dimensional coordinates ; A parameterized standard acupoint atlas is constructed based on traditional Chinese medicine theory. The standard acupoint atlas represents the spatial relationship between acupoints and candidate anatomical points. The standard acupoint map is spatially aligned with the predicted anatomical points using a nonlinear registration algorithm, and the coordinates of the target acupoint are calculated using affine transformation or thin-plate spline transformation. The depth information of the target acupoint is acquired using an RGB-D camera, and the three-dimensional coordinates of the target acupoint in the camera coordinate system are calculated by back-projection using the camera's intrinsic parameter matrix. ; The coordinates of the target acupoint in the base coordinate system are obtained through coordinate transformation: ; in, P 0 serves as the input for trajectory planning, guiding the end massage head to the target acupoint.

[0027] Optionally, the adaptive variable impedance control law is constructed through the following steps: The adaptive variable impedance control law is constructed as follows: ; in, The muscle stiffness is dynamically estimated and obtained through the fusion of multimodal sensor information; , which is the adaptive damping parameter; , which is the adaptive stiffness parameter; This is a muscle fatigue index; , These are nominal parameters; , It is an adaptive function; The differential gain coefficient of the contact force; , is a rectified linear unit function; This is a function of the direction of the contact force.

[0028] Optionally, constructing the overall control law based on the joint angle vector and the adaptive variable impedance control law includes the following steps: The overall control law for constructing the multi-degree-of-freedom robot system is as follows: ; in, The joint angle vector, The inertia matrix, Includes the Coriolis force and centripetal force matrix. For gravity, Indicates the joint control torque. It is a Jacobian matrix; The impedance relation in Cartesian space is mapped to joint space using the Jacobian matrix: ; The complete control torque is: .

[0029] Optionally, the method further includes the steps of estimating muscle state and defining a parameter adaptive strategy, specifically including: Muscle stiffness is estimated by fusing electromyographic signals and mechanical responses. : ; in, These are the weighting coefficients reflecting the degree of muscle activation, viscous properties, and elastic properties, respectively. The parameter adaptive strategy is defined using a combination of fuzzy logic and linear interpolation as follows: ; ; in, This is the baseline value for muscle stiffness in a relaxed state. This is the adaptive gain coefficient.

[0030] The following sections will provide a detailed description and explanation of some optional embodiments of this application, using specific application examples.

[0031] This embodiment provides a variable admittance control method and system for a massage robot based on electromyography-force feedback, belonging to the field of intelligent robot control. The scheme first uses an autonomous localization method to obtain acupoint locations, and then uses surface electromyography sensors and a six-dimensional force sensor to acquire the user's muscle activation state and contact force information in real time. Furthermore, it proposes a variable admittance control strategy based on muscle fatigue estimation, dynamically adjusting the controller's admittance parameters so that the robot's massage intensity and speed can adapt to the real-time physiological state of the muscles. The system includes a signal acquisition module, a state estimator, a variable admittance controller, and a trajectory planner. Through comparisons in simulation and real-person experiments, this embodiment effectively demonstrates its superiority in improving massage comfort, safety, and relieving muscle fatigue.

[0032] 1. Kinematic modeling and acupoint localization of massage robots.

[0033] To achieve precise massage movements, it is essential to establish accurate mathematical relationships between the massage robot's base coordinate system and its end effector. This section will describe the system's kinematic model and its vision-based acupoint marker localization method.

[0034] A. Kinematic modeling: Coordinate system spatial relationships that can be used in multi-degree-of-freedom robotic systems for massage, such as Figure 2 As shown. Among them, Represents the robot's base coordinate system. Indicates the coordinate system of the corresponding end flange. Indicates the center coordinate system of the end massage head. This represents the camera coordinate system fixed at the end of the robot. This represents the coordinate system of acupoint markers on the user's body surface.

[0035] To achieve precise control from the base to the massage points, the following closed chain can be obtained: (1) Simultaneously, the corresponding perception chain is constructed as follows: (2) Through the hand-eye calibration process, a fixed homogeneous transformation matrix from the camera coordinate system {cam} to the end coordinate system {e} can be obtained. The coordinate system of the massage head tool can be determined using tool calibration methods. Relative to the end coordinate system The fixed homogeneous transformation matrix under .

[0036] For an -DOF's massage robot arm, the position of its end flange under the base. The chain rule can be used to determine the angles of each joint. Calculations based on forward kinematics yielded the following: (3) Among them, the transformation matrix of adjacent links The modified Denavit-Hartenberg parameter method was used to establish: (4) In the formula Describe the first i The joint angle, link offset, link length, and link torsion angle of each joint.

[0037] Based on this kinematic model, the pose of the massage head center in the base coordinate system can be expressed as: (5) Given the target pose of the massage head Then, by solving the inverse kinematic equations: (6) The corresponding joint angle vector can be obtained. To address the multiple solutions problem inherent in robotic arms with six degrees of freedom or more, this solution integrates the Newton-Raphson numerical iteration and analytical solution methods. While strictly adhering to joint motion space constraints and singularity avoidance principles, it calculates the optimal joint configuration in real time, ensuring the smoothness of the massage operation trajectory and operational safety.

[0038] B. Acupoint localization method based on human pose estimation and template registration: This system employs markerless acupoint location technology, eliminating the need for users to use any physical markers before massage. By integrating deep learning-based human pose estimation algorithms with traditional Chinese medicine anatomy knowledge, it achieves precise acupoint location.

[0039] The system calibration phase includes two key steps: first, the camera intrinsic parameter matrix is ​​obtained using Zhang Zhengyou's calibration method. K and distortion coefficient, where: (7) Secondly, in the hand-eye calibration, the fixed transformation relationship between the camera and the robot end effector coordinate system is calculated using the Tsai-Lenz method. .

[0040] In the human keypoint recognition stage, the system employs 2D / 3D human pose estimation models such as MMPose to perform real-time detection of target areas such as the back and neck. The model outputs two-dimensional pixel coordinates of key anatomical points, including scapular keypoints and spinal keypoints. and three-dimensional coordinates .

[0041] A parameterized standard acupoint atlas based on traditional Chinese medicine theory was constructed, establishing the spatial relationship between acupoints and anatomical landmarks. A nonlinear registration algorithm was used to spatially align the standard template with real-time identified key human body points, and affine transformation or thin-plate spline transformation was employed to calculate personalized acupoint coordinates.

[0042] The depth information of the acupoint area is obtained using an RGB-D camera, and the three-dimensional coordinates of the acupoint in the camera coordinate system are calculated by back projection using the camera's intrinsic parameters. (8) Finally, the coordinates of the acupoints in the base coordinate system are obtained through coordinate transformation: (9) These coordinates serve as precise input for trajectory planning, guiding the robot's end effector to accurately reach the target acupoint.

[0043] 2. Adaptive variable proportional impedance control system for massage robots.

[0044] During a massage, the dynamic interaction between the robot's end effector and the human muscle tissue generates complex contact mechanics responses. When using traditional fixed-parameter impedance control methods, the system often struggles to maintain ideal compliance when faced with sudden changes in muscle stiffness or tissue properties due to prolonged massage. Therefore, this study proposes an adaptive variable-proportional impedance control strategy to achieve dynamic force balance and personalized adaptation during the massage process.

[0045] A. Adaptive variable proportional impedance control during muscle tissue contact process: The standard impedance control model for massage robots can be expressed as: (10) in: These are the inertia, damping, and stiffness matrices, respectively. The deviation between the actual position and the desired position Let be the contact force vector between the robot and human tissue.

[0046] In deep tissue massage, when the massage head touches a muscle nodule or encounters a sudden muscle contraction, the contact force... The transient force can change drastically, generating harmful peak values. Traditional PID control is prone to causing system oscillations, while impedance control with fixed parameters suffers from slow response.

[0047] To address the aforementioned technical challenges, this embodiment introduces two key innovations based on the standard impedance model: a parameter adaptive mechanism based on muscle state estimation, and a variable proportional control term specifically designed for transient force suppression. The improved control law is expressed as follows: (11) This control rate comprises two core components: (a) Adaptive parameter mechanism: The muscle stiffness is estimated in real time and obtained by fusing multimodal sensor information. Adaptive damping parameters; : Adaptive stiffness parameter.

[0048] in This is a muscle fatigue index. , These are nominal parameters. , It is an adaptive function.

[0049] (b) Variable-proportion suppression term: : Differential gain coefficient of contact force; : Rectified linear unit function; : Direction function of contact force.

[0050] The adaptive mechanism enables the system to detect muscle stiffness. When the phase is increased, the corresponding controller parameters can be increased. and This enhances the robot's rigidity and ensures that the massage force is effectively transmitted to deep tissues.

[0051] The variable proportional suppression term is specifically designed to suppress the growth of transient forces when the rate of change of contact force... At that time, the inhibitory term is activated, and its inhibitory effect is related to the current muscle stiffness. and contact force It is proportional to the sudden contraction of stiff muscles, thus achieving enhanced inhibitory response and context-aware safety protection.

[0052] The function ensures that the system only works when the contact force increases, and does not affect the system's natural recovery when the contact force decreases. This ensures that the compensating force is always opposite in direction to the contact force, thus playing a suppressive role.

[0053] Based on Lyapunov stability theory, candidate Lyapunov functions are defined as follows: (12) in By differentiating with respect to time and substituting into the control law, under the condition that... and Under the conditions, it can be proven The system exhibits asymptotic stability. A complete proof of stability is provided below in this embodiment.

[0054] B. Overall control architecture of the massage robot: n The dynamic equations of a degree-of-freedom massage robot can be expressed as follows: (13) in, Joint angle vector, The inertia matrix, Includes the Coriolis force and centripetal force matrix. For gravity, Indicates the joint control torque. Jacobian matrix The impedance relation (2) in Cartesian space is mapped to joint space using the Jacobian matrix: (14) The complete control torque is given by the following formula: (15) The adaptive variable proportional impedance control block diagram based on this dynamic model is shown below. Figure 3 As shown.

[0055] To verify the superiority of the proposed method, the following quantitative indicators are defined: Transient force suppression index: (16) This indicator reflects the system's ability to suppress transient force peaks; the smaller the value, the better the performance.

[0056] Compliance Index: (17) This indicator evaluates the smoothness of the contact force; the smaller the value, the smoother the interaction process.

[0057] Comprehensive index of trajectory tracking and force adjustment: (18) in, The weighting coefficient reflects the balance between trajectory tracking and force control.

[0058] C. Muscle state estimation and parameter adaptation strategy: Muscle stiffness Estimation was performed by fusing electromyographic signals and mechanical responses: (19) in The weighting coefficients, determined through experiments, reflect the degree of muscle activation, viscous properties, and elastic properties, respectively.

[0059] The adaptive function uses a combination of fuzzy logic and linear interpolation. (20) (twenty one) in This is the baseline value for muscle stiffness in a relaxed state. This is the adaptive gain coefficient.

[0060] The control parameters were tuned using a combination of offline learning and online fine-tuning: first, experimental data were collected under different muscle conditions, and then particle swarm optimization algorithm was used to fine-tune the parameters. Parameters were optimized offline, and then real-time performance metrics were used during the online operation phase. Parameters are fine-tuned. This control system, while maintaining stability, achieves a rapid response to changes in muscle state, significantly improving the safety and comfort of the massage process.

[0061] This embodiment proposes a variable admittance control method and system for massage robots based on electromyography-force feedback, successfully solving the key problems of traditional massage robots, such as lack of physiological perception, interaction rigidity, and inability to personalize. By introducing surface electromyography signals as an advanced observer of muscle state and deeply fusing them with contact force information, this embodiment achieves the following core innovations: 1. A complete intelligent massage control architecture has been established: from multimodal biosignal sensing (sEMG, contact force) to muscle state estimation (stiffness) Fatigue From the design of variable admittance control laws, a complete closed loop of "perception-decision-execution-optimization" is formed.

[0062] 2. An innovative variable admittance control algorithm is proposed: by designing the admittance parameter as a function of muscle state. and This enables the robot to dynamically adjust its interactive characteristics based on the real-time physiological state of the muscles.

[0063] 3. Achieved true context-aware safety protection: Variable proportional inhibition term based on muscle stiffness estimation It can effectively suppress transient impact forces and provide active safety protection when encountering sudden tension in bones or muscles.

[0064] 4. The effectiveness and superiority of the system were verified: through the designed performance indicators (transient force suppression index) Compliance Index (etc.), comparative experiments have demonstrated the significant advantages of the proposed solution in improving massage comfort, safety, and relieving muscle fatigue.

[0065] This embodiment combines the traditional Chinese medicine concept of "treatment based on syndrome differentiation" with modern robotic compliant control theory, providing an effective technical solution for the field of intelligent physiotherapy robots and achieving a significant leap from "mechanical execution" to "intelligent physiotherapy." Future work will further explore multi-muscle group collaborative estimation, the application of deep learning in parameter self-tuning, and a quantitative evaluation system for long-term massage effects.

[0066] The following is proof of the system stability in this embodiment: A.1 System Model and Assumptions: Consider the adaptive variable proportional impedance control law proposed in this embodiment: (twenty two) in: This is the trajectory error vector; It is a positive definite symmetric constant inertial matrix; The damping matrix is ​​time-varying. The time-varying stiffness matrix; This is the gain coefficient. This is an estimate of muscle stiffness; For environmental contact force; Assumption 1: The environment is a passive system, satisfying: (twenty three) in For initial energy storage.

[0067] Assumption 2: The rate of change of the parameter is bounded, that is, there exists a constant. Make: (twenty four) A.2 Construction of Lyapunov functions: Consider the following Lyapunov function candidates: (25) The equivalent stiffness matrix is ​​defined as follows: (26) and It is a positive definite diagonal matrix used to compensate for the effects of time-varying parameters.

[0068] A.3 Calculation of the derivative of Lyapunov functions: right Differentiate: (27) The governing equations are rewritten as follows: (28) Substituting, we get: (29) A.4 Stability Condition Analysis: consider The derivative term: (30) Based on hypothesis 2 and the boundedness of muscle stiffness variation, there exists a constant. Make: (31) therefore: (32) choose satisfy ,but: (33) A.5 Final Stability Conclusion: Substitute the above results into: (34) in .

[0069] Based on hypothesis 1 (passive environment) and selection satisfy We can obtain: (35) in , .

[0070] A.6 Stability Theorem: Theorem 1: Under the conditions that Assumption 1 and Assumption 2 hold, if the control parameters are chosen to satisfy: 1. Zhengding; 2. and ; 3. and ; The closed-loop system is asymptotically stable, that is: (36) Depend on and (when (At time), according to Lyapunov's direct method, the system is asymptotically stable. Q.E.D.

[0071] Table 1 Parameter Tuning Table

[0072] Appendix C: Performance Indicator Definitions: 1. Transient force suppression index: ; 2. Compliance Index: ; 3. Comprehensive index of trajectory tracking and force control: ; 4. Muscle fatigue relief rate: .

[0073] Reference Figure 4 This application also provides a massage robot control system based on variable impedance adaptive control, which can implement the above-mentioned massage robot control method based on variable impedance adaptive control. The system includes: Kinematic modeling unit, used to build kinematic models of multi-degree-of-freedom robot systems; Acupoint positioning unit, used to locate target acupoints based on human posture; The pose determination unit is used to determine the target pose of the end-effector massage head of the multi-degree-of-freedom robot system based on the target acupoint. The joint angle solving unit is used to solve the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system. A control law construction unit is used to construct an overall control law based on the joint angle vector and the adaptive variable impedance control law. A massage control unit is used to control the multi-degree-of-freedom robot system according to the overall control law, so that the end effector massage head massages the target acupoint.

[0074] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0075] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method of this application. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0076] It is understood that the content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the methods of this application, and the beneficial effects achieved are the same as those achieved by the methods of this application.

[0077] Please see Figure 5 , Figure 5 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 501 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 502 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 502 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 502 and is called and executed by the processor 501. The input / output interface 503 is used to implement information input and output; The communication interface 504 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 505 transmits information between various components of the device (e.g., processor 501, memory 502, input / output interface 503, and communication interface 504); The processor 501, memory 502, input / output interface 503, and communication interface 504 are connected to each other within the device via bus 505.

[0078] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method of this application.

[0079] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0080] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0081] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0082] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0083] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0084] The system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0085] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0086] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0087] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0088] In the embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or units may be electrical, mechanical, or other forms.

[0089] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0090] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0091] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0092] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A control method for a massage robot based on variable impedance adaptive control, characterized in that, The method includes the following steps: Establish a kinematic model for a multi-degree-of-freedom robot system; Locate the target acupoints based on the human body posture; The target pose of the end effector massage head of the multi-degree-of-freedom robot system is determined based on the target acupoints. Based on the target pose, the inverse kinematic equations of the kinematic model are solved to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system. The overall control law is constructed based on the joint angle vector and the adaptive variable impedance control law. The multi-degree-of-freedom robot system is controlled according to the overall control law so that the end effector massage head massages the target acupoint. The adaptive variable impedance control law is constructed through the following steps: The adaptive variable impedance control law is constructed as follows: ； in, The muscle stiffness is dynamically estimated and obtained through the fusion of multimodal sensor information; , which is the adaptive damping parameter; , which is the adaptive stiffness parameter; This is a muscle fatigue index; , These are nominal parameters; , It is an adaptive function; The differential gain coefficient of the contact force; , is a rectified linear unit function; It is a function of the direction of the contact force; The process of constructing the overall control law based on the joint angle vector and the adaptive variable impedance control law includes the following steps: The overall control law for constructing the multi-degree-of-freedom robot system is as follows: ； in, The joint angle vector, The inertia matrix, Includes the Coriolis force and centripetal force matrix. For gravity, Indicates the joint control torque. It is a Jacobian matrix; The impedance relation in Cartesian space is mapped to joint space using the Jacobian matrix: ； The complete control torque is: 。 2. The massage robot control method based on variable impedance adaptive control according to claim 1, characterized in that, The coordinate system of the multi-degree-of-freedom robot system includes: Represents the robot's base coordinate system. Indicates the coordinate system of the corresponding end flange. Indicates the center coordinate system of the end massage head. This represents the camera coordinate system fixed at the end of the robot. This represents the coordinate system of acupoint markers on the user's body surface; The process of establishing a kinematic model for a multi-degree-of-freedom robot system includes the following steps: Define the closed chain from the base to the massage point as: ； The corresponding perception chain is constructed as follows: ； By employing a hand-eye calibration process, a fixed homogeneous transformation matrix is ​​obtained from the camera coordinate system {cam} to the end coordinate system {e}. ; The coordinate system of the end massage head is determined using a tool calibration method. Relative to the end flange coordinate system The fixed homogeneous transformation matrix under ; Using the chain rule, from each joint angle The position of the end flange under the base was determined by forward kinematics calculation. : ； Among them, the transformation matrix of adjacent links The modified Denavit-Hartenberg parameter method was used to establish: ； In the formula Describe the first i The joint angle, link offset, link length, and link torsion angle of each joint; The pose of the center of the end massage head in the base coordinate system is defined as follows: 。 3. The massage robot control method based on variable impedance adaptive control according to claim 2, characterized in that, The step of solving the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system includes the following steps: By integrating the Newton-Raphson numerical iteration and analytical solution methods, and adhering to the joint motion space constraints and singularity avoidance principles, the inverse kinematic equations are solved to obtain the joint angle vectors. The inverse kinematic equation is: ； in, Let the target pose be... Let be the joint angle vector.

4. The massage robot control method based on variable impedance adaptive control according to claim 1, characterized in that, The method of locating target acupoints based on human posture includes the following steps: The intrinsic parameter matrix and distortion coefficients of the camera are obtained using the Zhang Zhengyou calibration method; wherein, the multi-degree-of-freedom robot system includes the camera; ； in, K This is the intrinsic parameter matrix; In hand-eye calibration, the fixed transformation relationship between the camera and robot end-effector coordinate systems is calculated using the Tsai-Lenz method. ; A human pose estimation model is used to detect target regions of the human body; the model outputs two-dimensional pixel coordinates including predicted anatomical points. and three-dimensional coordinates ; A parameterized standard acupoint atlas is constructed based on traditional Chinese medicine theory. The standard acupoint atlas represents the spatial relationship between acupoints and candidate anatomical points. The standard acupoint map is spatially aligned with the predicted anatomical points using a nonlinear registration algorithm, and the coordinates of the target acupoint are calculated using affine transformation or thin-plate spline transformation. The depth information of the target acupoint is acquired using an RGB-D camera, and the three-dimensional coordinates of the target acupoint in the camera coordinate system are calculated by back-projection using the camera's intrinsic parameter matrix. ； The coordinates of the target acupoint in the base coordinate system are obtained through coordinate transformation: ； in, P 0 serves as the input for trajectory planning, guiding the end massage head to the target acupoint.

5. The massage robot control method based on variable impedance adaptive control according to claim 1, characterized in that, The method further includes steps of estimating muscle state and defining a parameter adaptive strategy, specifically including: Muscle stiffness is estimated by fusing electromyographic signals and mechanical responses. : ； in, These are the weighting coefficients reflecting the degree of muscle activation, viscous properties, and elastic properties, respectively. The parameter adaptive strategy is defined using a combination of fuzzy logic and linear interpolation as follows: ； ； in, This is the baseline value for muscle stiffness in a relaxed state. This is the adaptive gain coefficient.

6. A massage robot control system based on variable impedance adaptive control, characterized in that, The system is used to implement the massage robot control method based on variable impedance adaptive control as described in claim 1, and the system includes: Kinematic modeling unit, used to build kinematic models of multi-degree-of-freedom robot systems; Acupoint positioning unit, used to locate target acupoints based on human posture; The pose determination unit is used to determine the target pose of the end-effector massage head of the multi-degree-of-freedom robot system based on the target acupoint. The joint angle solving unit is used to solve the inverse kinematic equations of the kinematic model based on the target pose to obtain the joint angle vectors corresponding to the multi-degree-of-freedom robot system. A control law construction unit is used to construct an overall control law based on the joint angle vector and the adaptive variable impedance control law. A massage control unit is used to control the multi-degree-of-freedom robot system according to the overall control law, so that the end effector massage head massages the target acupoint.

7. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 5.

Images