Exoskeleton system assistance control method and device based on man-machine co-fusion strategy

Abstract

The invention provides an exoskeleton system assistance control method and device based on a man-machine co-fusion strategy, and the method comprises the steps: collecting basic motion data of a human body and an exoskeleton system through various types of equipment, and initializing the motion state of the exoskeleton system; constructing a man-machine co-fusion kinetic model based on the basic motion data; on the basis of a man-machine co-fusion kinetic model, processing the collected real-time data through an EKF algorithm, and estimating various dynamic parameters of a human body and an exoskeleton system; determining a power-assisted control strategy of the exoskeleton system in combination with the dynamic parameters and a man-machine co-fusion kinetic model, and adjusting the power-assisted control strategy according to the personalized parameters of the user; and controlling the exoskeleton system to execute the adjusted power-assisted control strategy. According to the method, the man-machine collaborative motion intention prediction algorithm is adopted for power assisting control, the power assisting accuracy and flexibility of the exoskeleton system can be improved, and the method can dynamically adapt to individual differences of users.

Description

Technical Field

[0001] The present application relates to the field of exoskeleton system control technology, and in particular to an exoskeleton system power-assistance control method and device based on a human-machine integration strategy. Background Art

[0002] At present, the popularity of exoskeleton assistance systems in various fields such as rehabilitation training, physical labor assistance and motion analysis is gradually increasing. Exoskeleton assistance systems can assist users in completing related actions and reduce user output.

[0003] In related technologies, user-related data is generally collected through various sensors such as electromyogram (EMG) signal detection equipment, and then the corresponding power assistance mode is used to control the exoskeleton power assistance system to provide assistance based on the data analysis results.

[0004] However, in actual applications, since sensors are easily affected by environmental interference and other factors when collecting data, the exoskeleton assistance solutions in related technologies are difficult to accurately perceive the user's movement intentions, and generally use fixed preset assistance modes to provide assistance. This leads to defects in the exoskeleton assistance system, such as unnatural human-computer interaction, inaccurate assistance control, and insufficient adaptability to personalized needs. Summary of the Invention

[0005] The present application aims to solve one of the technical problems in the related art at least to a certain extent.

[0006] To this end, the first purpose of this application is to propose an exoskeleton system assistance control method based on a human-machine integration strategy. This method constructs a human-machine integration model and adopts a human-machine collaborative motion intention prediction algorithm for assistance control. It can improve the accuracy and flexibility of the assistance of the exoskeleton assistance system, and can dynamically adapt to the individual differences of users. It solves the problems of poor dynamic adaptability, insufficient robustness and limited natural support for user actions in the assistance control of exoskeleton robots during human-machine collaboration.

[0007] The second purpose of this application is to propose an exoskeleton system power-assistance control device based on a human-machine integration strategy.

[0008] A third object of the present application is to provide a non-transitory computer-readable storage medium.

[0009] To achieve the above objectives, the first aspect of the present application is to propose an exoskeleton system power-assistance control method based on a human-machine integration strategy, the method comprising the following steps:

[0010] Collect basic motion data of the human body and the exoskeleton system through various types of data detection equipment, and initialize the motion state of the exoskeleton system according to the basic motion data;

[0011] Constructing a human-machine synergy dynamics model based on the basic motion data, wherein the human-machine synergy dynamics model is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion;

[0012] Based on the human-machine collaborative dynamics model, the real-time data collected by the data detection device is processed using an extended Kalman filter (EKF) algorithm to estimate various dynamic parameters of the human body and the exoskeleton system.

[0013] Determining a power-assistance control strategy for the exoskeleton system based on the dynamic parameters and the human-machine collaborative dynamics model, and adjusting the power-assistance control strategy based on the user's personalized parameters, wherein the power-assistance control strategy includes power-assistance torque and motion trajectory planning for the exoskeleton system;

[0014] The exoskeleton system is controlled to execute the individually adjusted power-assistance control strategy to achieve synchronous operation of the exoskeleton system and the human body.

[0015] Optionally, in one embodiment of the present application, the basic motion data of the human body and the exoskeleton system are collected through various types of data detection equipment, including: collecting various motion state parameters of the human body joints through the inertial measurement unit IMU; collecting the torque applied by the human body on the exoskeleton system and the exoskeleton joint load torque through the torque sensor; and initializing the motion state of the exoskeleton system according to the basic motion data, including: setting the initial motion state parameters of the exoskeleton joints according to the various motion state parameters of the human body joints.

[0016] Optionally, in one embodiment of the present application, constructing a human-machine synergy dynamics model based on the basic motion data includes: performing dynamic analysis on the basic motion data to construct a human body dynamics model and an exoskeleton dynamics model; constructing the human-machine synergy dynamics model based on the human body dynamics model and the exoskeleton dynamics model, wherein the torque of the human-machine synergy dynamics model is equal to the sum of the torque applied by the human body on the exoskeleton system and the exoskeleton joint load torque, and is equal to the exoskeleton control torque.

[0017] Optionally, in one embodiment of the present application, the real-time data collected by the data detection device is processed by the extended Kalman filter EKF algorithm based on the human-machine collaborative dynamics model, including: determining the physical constraints of the EKF algorithm in the estimation process according to the motion state parameters in the human-machine collaborative dynamics model; under the physical constraints, performing state estimation in the Kalman filter prediction stage according to the dynamic equations in the human-machine collaborative dynamics model.

[0018] Optionally, in one embodiment of the present application, after estimating the dynamic parameters of the human body and the exoskeleton system, it also includes: feeding back the dynamic parameters to the human-machine synergy dynamics model, and correcting the inertia matrix and torque distribution in the human-machine synergy dynamics model according to the dynamic parameters.

[0019] Optionally, in one embodiment of the present application, the dynamic parameters and the human-machine synergy dynamics model are combined to determine the power assistance control strategy of the exoskeleton system, including: calculating the exoskeleton power assistance torque required for the exoskeleton system to assist according to the dynamic parameters and the human-machine synergy dynamics model, and adjusting the exoskeleton power assistance torque according to human-machine synchronization; estimating the joint motion trajectory of the human body and the exoskeleton system according to the human-machine synergy dynamics model and the dynamic parameters; designing an initial exoskeleton power assistance trajectory according to the joint motion trajectory and the position information of the human body and the exoskeleton system; based on the dynamic parameters, adjusting the initial exoskeleton power assistance trajectory in real time through an optimization control algorithm to obtain the motion trajectory planning of the exoskeleton system.

[0020] Optionally, in one embodiment of the present application, the power-assistance control strategy is adjusted according to the personalized parameters of the user, including: analyzing the physiological characteristic data of the current user to determine the cooperation mode of the exoskeleton system; adjusting the power-assistance parameters in the power-assistance control strategy according to the real-time motion data of the current user; obtaining the historical motion data of the current user, determining the current user's exercise habits according to the historical motion data, and obtaining the real-time feedback data of the current user, and optimizing the power-assistance parameters in combination with the exercise habits and the real-time feedback data.

[0021] Optionally, in one embodiment of the present application, controlling the exoskeleton system to execute the personalized adjusted power-assistance control strategy includes: adding the exoskeleton power-assistance torque to the control deviation torque to obtain the actual output torque of the exoskeleton; and driving the exoskeleton system through a real-time controller according to the actual output torque of the exoskeleton.

[0022] To achieve the above objectives, the second aspect of the present application further proposes an exoskeleton system power control device based on a human-machine integration strategy, comprising the following modules:

[0023] An acquisition module, configured to acquire basic motion data of the human body and the exoskeleton system through various types of data detection equipment, and initialize the motion state of the exoskeleton system according to the basic motion data;

[0024] A construction module for constructing a human-machine synergy dynamics model based on the basic motion data, wherein the human-machine synergy dynamics model is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion;

[0025] an estimation module for processing the real-time data collected by the data detection device using an extended Kalman filter (EKF) algorithm based on the human-machine collaborative dynamics model to estimate various dynamic parameters of the human body and the exoskeleton system;

[0026] a determination module, configured to determine a power-assistance control strategy for the exoskeleton system based on the dynamic parameters and the human-machine synergy dynamics model, and adjust the power-assistance control strategy according to the user's personalized parameters, wherein the power-assistance control strategy includes power-assistance torque and motion trajectory planning for the exoskeleton system;

[0027] The control module is used to control the exoskeleton system to execute the individually adjusted power-assistance control strategy to achieve synchronous operation of the exoskeleton system and the human body.

[0028] In order to implement the above embodiments, the third aspect of the present application further proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the exoskeleton system assistance control method based on the human-machine integration strategy in the above first aspect is implemented.

[0029] The technical solution provided by the embodiments of the present application brings at least the following beneficial effects: the present application combines the human-machine co-integration strategy to carry out the exoskeleton power-assistance system control based on multimodal information fusion and dynamic adaptation. The present application adopts a motion intention prediction algorithm based on human-machine collaboration, and can accurately identify the user's motion intention by real-time analysis of multimodal information such as electromyographic signals, inertial measurement data and torque sensor information. Adopting an adaptive control strategy, based on Kalman filtering and dynamic adjustment algorithm, the power-assistance output is optimized in real time to enhance the robustness of the system. The human-machine co-integration model constructed by the present application can be combined with personalized parameter configuration to achieve fine adjustment of the power-assistance intensity and direction, and can flexibly configure a suitable power-assistance control strategy according to the characteristics of each user. Therefore, the present application combines sensor data, multimodal interaction models and real-time control algorithms, which can dynamically adapt to the individual differences and motion states of users, improve the accuracy, pertinence and flexibility of the power-assistance of the exoskeleton power-assistance system, and provide users with a more efficient and comfortable power-assistance experience.

[0030] Additional aspects and advantages of the present invention will be set forth in part in the description which follows and, in part, will be obvious from the description which follows, or may be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0032] Figure 1 This is a flow chart of an exoskeleton system power-assistance control method based on a human-machine integration strategy proposed in an embodiment of the present application;

[0033] Figure 2 A flowchart of a method for generating a power assist control strategy for an exoskeleton system proposed in an embodiment of the present application;

[0034] Figure 3 A flowchart of a method for personalized adaptation of an exoskeleton system proposed in an embodiment of the present application;

[0035] Figure 4 This is a structural diagram of an exoskeleton system power-assistance control device based on a human-machine integration strategy proposed in an embodiment of the present application. DETAILED DESCRIPTION

[0036] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0037] It should be noted that the control scheme of the exoskeleton power-assistance system in the relevant embodiments mainly relies on the following methods: The first is a control method based on fixed rules. This method uses a preset power-assistance mode to provide fixed power assistance to the user. It does not consider the dynamic changes of the user's motion state and lacks flexibility. The second is an electromyographic signal-driven power-assistance method. This method evaluates the user's motion intention by collecting electromyographic signals and adjusts the power-assistance output, but is susceptible to electromyographic noise interference and has low accuracy and robustness. The third is motion detection based on data collected by an inertial measurement unit (IMU). This method uses an IMU sensor to detect the user's motion state and feeds back to the power-assistance system, but is susceptible to motion noise and device drift.

[0038] Therefore, the control scheme of the exoskeleton power assist system in the relevant embodiments still has the following deficiencies in complex application scenarios:

[0039] First, the anti-interference ability is weak. Sensor data is easily affected by environmental interference, resulting in unstable system response.

[0040] Second, human-computer interaction is unnatural. Existing assistance strategies have difficulty accurately sensing the user's movement intentions, resulting in a mismatch between the timing and magnitude of assistance.

[0041] Third, control accuracy is low. In fast dynamic scenarios (such as running or carrying weights), existing control methods are prone to delays or insufficient assistance.

[0042] Fourth, lack of adaptability: Fixed power parameters cannot meet the personalized needs of different users, limiting the wide applicability of exoskeleton devices.

[0043] To this end, this application proposes an exoskeleton system assistance control method and device based on a human-machine integration strategy to improve the accuracy, pertinence and flexibility of the assistance provided by the exoskeleton assistance system and dynamically adapt to the individual differences of users.

[0044] The following describes, with reference to the accompanying drawings, a control method and device for an exoskeleton assistance system based on a human-machine integration strategy proposed in an embodiment of the present application.

[0045] Figure 1 This is a flow chart of an exoskeleton system power control method based on a human-machine integration strategy proposed in an embodiment of the present application, such as Figure 1 As shown, the method includes the following steps:

[0046] Step S101 : basic motion data of the human body and the exoskeleton system are collected through various types of data detection equipment, and the motion state of the exoskeleton system is initialized according to the basic motion data.

[0047] Specifically, data collection and initial calibration of the exoskeleton system are performed. This step captures the motion state of the human body and exoskeleton, providing basic data for subsequent modeling and control. Using various types of data detection equipment, various basic motion data and mechanical states of the human body and exoskeleton system are collected, providing accurate input for subsequent modeling and control strategies.

[0048] In one embodiment of the present application, basic motion data of the human body and the exoskeleton system are collected through various types of data detection equipment, including: collecting various motion state parameters of the human body's joints through an inertial measurement unit (IMU); collecting the torque applied by the human body to the exoskeleton system and the load torque of the exoskeleton joints through a torque sensor; initializing the motion state of the exoskeleton system based on the basic motion data, including: setting the initial motion state parameters of the exoskeleton joints accordingly based on the various motion state parameters of the human body's joints.

[0049] Specifically, the inertial measurement unit (IMU) is used to collect various motion state parameters of the human joints, including the angle θ of the human joints. h , angular velocity and angular acceleration Then use the torque sensor to obtain the torque τ applied by the human body on the exoskeleton h and the exoskeleton joint load torque τ loadThen, the motion state parameters of the joints in the exoskeleton system are initialized based on the collected motion state parameters, including the angle θ of the exoskeleton joints. e , angular velocity and angular acceleration

[0050] In the present embodiment, the initial motion parameters of the exoskeleton joints are not initialized arbitrarily. Each motion state parameter of the exoskeleton joints, such as angle, angular velocity and acceleration, usually needs to be measured by a sensor. These motion parameters are based on data acquisition of sensors (such as IMU, encoder and force sensor, etc.). In addition, the motion state parameters of the exoskeleton joints have an initialization process at the beginning, which is usually set according to the initial posture of the human body. That is, the initial motion state parameters of each exoskeleton joint are set according to the motion state parameters of the corresponding measured human joints, thereby ensuring synchronization with the natural movement of the human body. Since the initial motion state parameters of the exoskeleton joints may be affected by factors such as the physiological characteristics and activity status of different users, they should be dynamically adjusted according to real-time measurement data and algorithm calculation.

[0051] Therefore, the basic motion data output in this step include: human joint angles and exoskeleton initial motion state parameters. These data will be used to build a human-machine collaboration model in the future, laying the foundation for analyzing the interactive relationship between the human body and the exoskeleton.

[0052] Step S102: constructing a human-machine synergy dynamics model based on basic motion data, wherein the human-machine synergy dynamics model is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion.

[0053] Specifically, the human-machine collaborative dynamics model is constructed. This step uses mechanical and dynamic analysis to establish a collaborative model between the human body and the exoskeleton, defining the relationship between torque and motion trajectory. Based on the data collected in the previous step, dynamic analysis is used to establish a mathematical model describing the collaborative relationship between the human body and the exoskeleton, clarifying the coupling relationship between various physical quantities.

[0054] It should be noted that the motion state parameters such as angle, angular velocity and acceleration in the above-mentioned embodiment can be directly measured by an inertial measurement unit (IMU) without relying on model calculation. However, some parameters, such as the torque applied by the human body on the exoskeleton (e.g., the torque in the human body dynamics model), may not be directly measured by an IMU. This torque is usually obtained by an external sensor (e.g., a force sensor or a torque sensor) or by an estimation method (e.g., based on the derivation of a dynamic model). Since the torque applied by the human body on the exoskeleton can be derived by a human body dynamics model (usually based on mechanics and kinematics equations), and these torques are usually related to the joint angles, angular velocities and accelerations of the human body collected, in practical applications, the torque can be estimated by combining the data collected by the force sensor and these dynamic models. Based on this, the present application constructs a comprehensive dynamic model of the collaboration between the human body and the exoskeleton based on the collected motion state parameters and the relevant dynamic models.

[0055] In one embodiment of the present application, a human-machine synergy dynamics model is constructed based on basic motion data, including: performing dynamic analysis on the basic motion data to construct a human body dynamics model and an exoskeleton dynamics model; constructing a human-machine synergy dynamics model based on the human body dynamics model and the exoskeleton dynamics model, wherein the torque of the human-machine synergy dynamics model is equal to the sum of the torque applied by the human body on the exoskeleton system and the exoskeleton joint load torque, and is equal to the exoskeleton control torque.

[0056] Specifically, in this embodiment, a human body dynamics model is first established. This model describes the mechanical behavior of the human body during natural movement and can be expressed by the following formula:

[0057]

[0058] Among them, M h is the inertia matrix of the human joint, which describes the human joint angle θ h The relationship between the inertia of the joint, C h is the human body Coriolis moment matrix, which describes the human body joint angular velocity θ h Effect on torque, G h is the human body gravity matrix, which describes the human body joint angle θ h The relationship between the torque exerted by gravity on the joint.

[0059] Furthermore, an exoskeleton dynamic model is established, which describes the response of the exoskeleton under force. The model can be expressed by the following formula:

[0060]

[0061] Among them, τ e1 represents the exoskeleton control torque, Me is the inertia matrix of the exoskeleton joint, which describes the exoskeleton joint angle θ e The relationship between the inertia of the exoskeleton joints, C e is the exoskeleton Coriolis moment matrix, which describes the exoskeleton joint angular velocity θ e Effects of exoskeleton, G e is the exoskeleton gravity matrix, which describes the exoskeleton joint angle θ e Relationship with exoskeleton weight.

[0062] It is understandable that through this separate modeling, the present application can achieve the collaborative work of the human body and the exoskeleton, achieving effective human-machine integration. The difference between the two is that the calculation model targets different objects, τ h Mainly for the physical parameters of the human body, τ e1 The physical parameters of the exoskeleton are used to achieve collaborative work between the exoskeleton and the human body through modeling and parameter sharing.

[0063] Furthermore, a comprehensive dynamic model of the collaboration between the human body and the exoskeleton, namely the human-machine collaborative dynamic model, can be constructed. The model can be expressed by the following formula:

[0064] τ total =τ h +τ load =τ e1

[0065] Among them, τ total The torque of the human-machine collaborative dynamics model is equal to the sum of the torque in the collaboration between the human body and the exoskeleton and the load torque, and is also equal to the exoskeleton control torque τ. e1 equal.

[0066] It should be noted that, in order to achieve synergy, the embodiment of the present application combines the human body torque and the exoskeleton load torque to form the control force that the exoskeleton needs to apply. The above formula represents the collaborative relationship between the human body and the exoskeleton, adds the torques of the two, and performs control and feedback through the dynamic model of the exoskeleton system. In order to achieve coordinated control, the embodiment of the present application simulates the collaborative work between the human body and the exoskeleton by establishing a comprehensive dynamic model. Among them, the design of the exoskeleton model not only considers the mechanical behavior of the exoskeleton, but also takes into account its collaboration with the human body. The movement described by this model is jointly participated by the human body and the exoskeleton, and control is achieved by collaboratively calculating the torque.

[0067] The combined calculation in establishing the human-machine co-integration dynamics model, namely τ h +τ load, can be understood as a component of the exoskeleton control torque, that is, the torque of the exoskeleton acting on the human body plus the load effect of the exoskeleton itself (such as gravity, friction, etc.). Therefore, when these torques are combined, they are consistent with the torque required for exoskeleton control, simplifying the model and forming a comprehensive dynamic model. The comprehensive dynamic model constructed in this application is not completely equal to the exoskeleton dynamic model, but by combining the respective torques of the human body and the exoskeleton system, representing the mechanical relationship between the human body and the exoskeleton, and supporting human movement through the exoskeleton control model.

[0068] The mathematical model of human-robot collaboration outputted in this step is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion. This model provides a theoretical basis for subsequent dynamic parameter estimation and can guide real-time state updates.

[0069] In step S103, based on the human-machine collaborative dynamics model, the real-time data collected by the data detection equipment is processed by the extended Kalman filter (EKF) algorithm to estimate various dynamic parameters of the human body and the exoskeleton system.

[0070] Specifically, the state parameters of the exoskeleton system are estimated in real time to ensure the accuracy of the control strategy. This step uses the extended Kalman filter (EKF) algorithm to update various dynamic parameters such as the motion state parameters and dynamic parameters of the human body and exoskeleton in real time to ensure the accuracy and robustness of the human-machine collaborative dynamic model.

[0071] The Extended Kalman Filter (EKF) algorithm is a nonlinear extension of the Kalman filter and is suitable for processing nonlinear dynamic systems. This application uses the EKF algorithm, combined with the dynamic model of the exoskeleton system and real-time measurement data, to estimate the operating state of the exoskeleton system at a later time.

[0072] In one embodiment of the present application, the EKF algorithm is used to process the data collected by various sensors in step S101 in real time to estimate the motion state parameters of the human body and exoskeleton system at the next moment, including: the angular velocity of the human joints and angular acceleration and the angular velocity of the exoskeleton joints and angular acceleration

[0073] When implementing the estimation, reference can be made to the Kalman filter algorithm in the relevant technology. As one possible implementation method, in the prediction stage, the Kalman filter first predicts the state and covariance matrix of the next moment based on the system dynamic equation. The predicted state comes from the estimated value of the previous moment and the state transfer matrix in the model. Then, the dynamic model predicts the motion state of the human body and exoskeleton (such as angular acceleration, angular velocity, etc.) through the measured input data (such as angle, angular velocity, etc.). In the update stage, when new measurement data is received, the Kalman filter combines the predicted state with the measurement data by updating the formula to correct the prediction result. The Kalman gain (Kk) is then used to balance the error between the predicted value and the new measurement value to generate a more accurate estimate.

[0074] As mentioned above, this application uses the human-machine collaborative dynamics model constructed in step S102 for estimation. This collaborative dynamics model of the human body and exoskeleton includes multiple influencing factors, such as the mass, joint angles, velocity, and acceleration of the human body and exoskeleton, which will form the basis of the above-mentioned EKF estimation.

[0075] In one embodiment of the present application, based on the human-machine collaborative dynamics model, the real-time data collected by the data detection device is processed by the extended Kalman filter EKF algorithm, including: determining the physical constraints of the EKF algorithm in the estimation process according to the motion state parameters in the human-machine collaborative dynamics model; under the physical constraints, performing state estimation in the Kalman filter prediction stage according to the dynamic equations in the human-machine collaborative dynamics model.

[0076] Specifically, in this embodiment, the human-machine collaborative dynamics model, serving as the basis for dynamic parameter estimation, is primarily reflected in the following aspects. First, the dynamics equations. In step S102, dynamics analysis is used to establish the dynamics equations for human-exoskeleton collaboration. These equations accurately describe the relationships between various physical quantities, particularly angles, angular velocities, and angular accelerations. These dynamics equations provide a system model for the Kalman filter, facilitating accurate state estimation during the prediction phase.

[0077] Second, the state transition model. The dynamic model of the human body and exoskeleton collaboration provides the EKF algorithm with motion state transition equations. The Kalman filter uses these equations to predict the state at the next moment. This process relies on the relationship established in the relevant embodiment of step S102.

[0078] Third, collaborative behavior modeling. The dynamic model of human-exoskeleton collaboration, including joint angles, exoskeleton torque, and load torque, provides additional physical constraints for the estimation process. These constraints help the Kalman filter better handle the effects of motion, leading to accurate estimation of dynamic motion parameters.

[0079] Therefore, the Kalman filter algorithm of the embodiment of the present application uses the transfer equations and physical constraints provided by the established dynamic model to accurately predict and estimate the motion state of the human body and exoskeleton.

[0080] In one embodiment of the present application, after estimating the dynamic parameters of the human body and the exoskeleton system, it also includes: feeding back the dynamic parameters to the human-machine synergy dynamics model, and correcting the inertia matrix and torque distribution in the human-machine synergy dynamics model according to the dynamic parameters.

[0081] Specifically, in this embodiment, the dynamic parameters updated in real time are used to correct the inertia matrix (for example, the inertia matrix of the joints of the human body and the exoskeleton system) and the torque distribution in the human-machine synergy dynamic model to reduce the influence of external interference. The present application realizes the closed-loop control of dynamic parameter estimation and machine synergy dynamic model, specifically including: first estimating the motion state of the human body and the exoskeleton through the established dynamic model, thereby obtaining preliminary parameters (such as angle, angular velocity and acceleration, etc.). Then, real-time updating and correction are performed, and the sensor data collected in real time is processed by the EKF algorithm to update the dynamic parameters. These updated parameters can reflect the influence of external interference and error, thereby improving the accuracy of the system. Then closed-loop correction is performed. After the parameters are updated in real time, the corrected parameters will be fed back to the dynamic model to update the state. This feedback mechanism realizes closed-loop control. Through this process, the system can correct the dynamic model in real time according to the new dynamic parameters, avoid the influence of external interference and error, and improve the accuracy and robustness of motion control.

[0082] The closed-loop control of dynamic parameter estimation and real-time updating of model parameters in this embodiment ensures the accuracy and stability of the power-assisted control strategy.

[0083] Therefore, this step outputs the dynamically estimated motion state parameters of the human body and exoskeleton system. These real-time estimated data will serve as input to provide an accurate basis for subsequent power-assisted control strategies.

[0084] In step S104, the exoskeleton system's power-assistance control strategy is determined based on the dynamic parameters and the human-machine collaborative dynamics model, and the power-assistance control strategy is adjusted according to the user's personalized parameters. The power-assistance control strategy includes the exoskeleton system's power-assistance torque and motion trajectory planning.

[0085] Specifically, the power-assistance control strategy of the exoskeleton system is designed. Based on the dynamic parameter estimation results and the symbiotic dynamics model in the previous step, this step designs the power-assistance torque distribution and trajectory planning strategy of the exoskeleton system and dynamically adjusts the response of the exoskeleton system.

[0086] In order to more clearly illustrate the detailed process of formulating the power assist control strategy of the present application, an example description is given below using a power assist control strategy generation method proposed in an embodiment of the present application. Figure 2 This is a flow chart of a method for generating a power assist control strategy for an exoskeleton system proposed in an embodiment of the present application. Figure 2 As shown, the method includes the following steps:

[0087] In step S201 , the exoskeleton assist torque required for the exoskeleton system to assist is calculated based on the dynamic parameters and the human-machine synergy dynamics model, and the exoskeleton assist torque is adjusted based on human-machine synchronization.

[0088] Specifically, the required exoskeleton assist torque is calculated based on the human-machine collaborative dynamics model. The calculation process can be expressed by the following formula:

[0089] τ e2 =τ total -τ load

[0090] Among them, τ e2 Represents the exoskeleton assist torque.

[0091] It should be noted that in the exoskeleton power control strategy of the present application, the exoskeleton power torque is generated by adjusting the load torque to optimize synchronization with the natural movement of the human body. e1 The load torque and joint torque of the exoskeleton are calculated based on the exoskeleton's angular velocity, angular acceleration and other parameters. Therefore, it is essentially estimated based on the dynamic state of the exoskeleton itself. e2 It is the result of adjustments based on dynamic parameter estimation, with the goal of compensating for the assistance required by the exoskeleton by reducing the load torque, thereby making the movement of the exoskeleton more synchronized with the natural movement of the human body.

[0092] Therefore, the two do not refer to exactly the same quantity. e1 is a parameter calculated based on the exoskeleton's own dynamic model, and τ in this embodiment e2 The assist torque is adjusted in real time by adjusting the load torque. Although they both involve the torque of the exoskeleton, their meanings are slightly different. e1 is the torque calculated based on the exoskeleton dynamics model, τ e2 The assist torque is adjusted based on the real-time estimated dynamic parameters and collaborative model.

[0093] When using the above formula to calculate the exoskeleton assist torque, the dynamic parameter estimation results obtained are used to calculate the τ in the formula. totalThe real-time values ​​of parameters such as the exoskeleton can be used to calculate the real-time exoskeleton assist torque.

[0094] Furthermore, the calculated exoskeleton assist torque is adjusted with the goal of synchronizing the movement of the exoskeleton system with the natural movement of the human body.

[0095] Step S202 : Estimate the joint motion trajectories of the human body and the exoskeleton system based on the human-machine collaborative dynamics model and dynamic parameters.

[0096] Specifically, by substituting the obtained dynamic parameters into the various dynamic models constructed in the above embodiments, the relevant torques of the human body and the exoskeleton system can be calculated, and then the calculated relevant torques are substituted into the human-machine synergistic dynamic model. The actual motion trajectory of the joint axis can be inferred through the human-machine synergistic dynamic model.

[0097] Step S203: Design an initial exoskeleton assistance trajectory based on the joint motion trajectory and the position information of the human body and the exoskeleton system.

[0098] Specifically, based on the real-time joint motion information obtained in step S202 and the relative position information of the human body and the exoskeleton, a more accurate motion trajectory can be obtained. Then, based on the joint motion trajectory of the human body and the exoskeleton, the exoskeleton's power-assisted trajectory, i.e., the initial exoskeleton power-assisted trajectory, is designed.

[0099] In step S204, based on the dynamic parameters, the initial exoskeleton assistance trajectory is adjusted in real time by optimizing the control algorithm to obtain the motion trajectory planning of the exoskeleton system.

[0100] Specifically, an optimization control algorithm is used to adjust the initial exoskeleton's assistance trajectory in real time, ensuring that the exoskeleton's assistance accurately matches the human body's movements. The control parameters in the optimization control algorithm can be set based on real-time dynamic parameter estimation results to improve the matching of the adjusted trajectory.

[0101] Based on the above embodiments, in order to explain the entire process of generating the power assist control strategy of the present application more clearly and intuitively from the overall logic, the process of generating the power assist control strategy based on dynamic parameter estimation of the present application is described in an overall manner below.

[0102] The first step is to estimate the dynamic parameters and obtain the motion trajectory. In the dynamic parameter estimation of this application, the extended Kalman filter EKF algorithm is used to estimate the motion state of the exoskeleton and the human body. These state parameters include: human angular velocity and angular acceleration, which are used to describe the posture changes of the human body during movement; exoskeleton angular velocity and angular acceleration, which are used to describe the posture changes of the exoskeleton during operation. The estimation of these dynamic parameters will provide accurate motion data for subsequent control strategies. The human motion trajectory is derived from the human body's dynamic model by combining the human body's angular velocity and angular acceleration with the synchronous motion information of the exoskeleton.

[0103] The second step is to generate a power-assisted control strategy. After dynamic parameter estimation is completed, the accurate motion state and torque requirements are obtained. In the power-assisted control strategy design, the estimated dynamic parameters are combined with the established human-exoskeleton collaboration model to determine the appropriate power-assisted control strategy. The specific steps are as follows:

[0104] First, the joint torque distribution is performed. The estimated parameters calculated by the human body dynamics model and the exoskeleton dynamics model are used to obtain the human body torque τ h and the exoskeleton's assist torque τ e2 τ also needs to be adjusted dynamically. h With τ e2 The ratio enables the exoskeleton's movements to be synchronized with the body's natural movements while avoiding unnecessary delays.

[0105] Then, trajectory planning and power adjustment are performed. Based on the joint motion trajectory of the human body and the exoskeleton, the exoskeleton's power trajectory is designed and the exoskeleton's movement pace is adjusted to provide the exoskeleton's power assistance in the optimal way, preventing the exoskeleton's movements from lagging behind the human body's natural movements.

[0106] Finally, real-time adjustments are made through control algorithms. Using an optimized control algorithm (e.g., PID control or model-based predictive control), the exoskeleton's trajectory is adjusted in real time based on the currently estimated dynamic parameters and trajectory information, ensuring that the exoskeleton's assistance precisely matches the human's movements.

[0107] The third step is to output the power assist control strategy. The output of the control strategy is the power assist torque τ applied by the exoskeleton. e2 This refers to the force applied by the exoskeleton to assist human movement. This torque is dynamically adjusted to ensure the exoskeleton effectively supports human movement while avoiding interference. During this process, the exoskeleton's response is synchronized with human movement, ensuring natural and smooth movement.

[0108] Based on the above embodiment, the specific process of generating the human body motion trajectory is described in detail below. The process includes the following steps:

[0109] The first step is to establish a human body dynamics model. In step S102, a mathematical model of the human body and exoskeleton collaboration is established using kinematic and dynamic analysis. The human body's motion trajectory is usually described by parameters such as joint angles, angular velocities, and angular accelerations. Through precise dynamic modeling, this application can calculate the motion trajectory of each joint and, in combination with the exoskeleton, perform real-time compensation for these movements. This trajectory information provides the angular changes in joint motion and also helps determine how the exoskeleton should respond to these changes, thereby providing a theoretical basis for the generation of exoskeleton control strategies.

[0110] The second step is to predict the motion by using the dynamic model. The motion of the human body is combined with the motion of the exoskeleton by using the comprehensive dynamic model of the human body and the exoskeleton established in step S102. h and the load torque τ of the exoskeleton load The actual axial motion trajectory of the joint can be calculated through this comprehensive dynamic model.

[0111] Furthermore, based on this joint motion information and combined with the relative positions of the human body and the exoskeleton, a more accurate motion trajectory can be obtained, which is beneficial for subsequent power-assisted control.

[0112] The third step is feedback and optimization. Using motion state estimates and trajectory data feedback, the EKF algorithm makes real-time corrections to the control model's parameters. This continuously updated motion data optimizes the exoskeleton's response, enabling it to provide accurate and timely assistance to the human body, ensuring that the exoskeleton's assistance closely matches the body's natural movements.

[0113] In summary, the embodiments of the present application, through dynamic parameter estimation, can provide accurate parameter basis for the exoskeleton's control strategy. Furthermore, through the collaborative model between the human body and the exoskeleton and real-time trajectory planning, the exoskeleton's motion trajectory can be highly consistent with human movements, avoiding delays and unnatural movements. The control strategy of this application not only improves the adaptability of the exoskeleton but also enhances its robustness and stability in complex environments, ensuring the comfort and safety of the user when using the exoskeleton.

[0114] Furthermore, the present application can also adjust the power assist control strategy according to the personalized parameters of different users, so as to combine the personalized parameter configuration to achieve fine-grained adjustment of the power assist intensity and direction, thereby improving the user experience.

[0115] In order to more clearly illustrate the detailed process of personalized adjustment of the present application, the personalized adjustment method of a control strategy proposed in an embodiment of the present application is exemplified below. Figure 3 The flowchart of a personalized adaptation method of an exoskeleton system proposed in the embodiment of the present application is as follows: Figure 3As shown, the method includes the following steps:

[0116] Step S301: Analyze the physiological characteristic data of the current user to determine the cooperation mode of the exoskeleton system.

[0117] Specifically, user data analysis is performed. In this step, the exoskeleton's collaborative mode is determined by analyzing each user's physiological characteristics (such as weight, height, joint flexibility, and athletic ability). Since each user has different needs, different parameters are configured for each user to ensure optimal collaboration between the exoskeleton and the user.

[0118] Step S302: adjusting the power assist parameters in the power assist control strategy according to the real-time motion data of the current user.

[0119] Specifically, personalized parameter adjustments can be performed based on the specific needs of different users. For example, the exoskeleton's power assistance parameters can be adjusted in real time based on the user's current motion data. Power assistance parameters include, but are not limited to, torque and motion trajectory planning as described in the above embodiments, ensuring that the exoskeleton provides appropriate power assistance during exercise.

[0120] Step S303: Obtain historical exercise data of the current user, determine the current user's exercise habits based on the historical exercise data, obtain real-time feedback data of the current user, and optimize the power parameters based on the exercise habits and real-time feedback data.

[0121] Specifically, the feedback mechanism and learning process involves continuously collecting user performance and feedback data. This allows the exoskeleton to "learn" from different users' exercise habits and continuously optimize parameter configurations to better meet individual needs. This adaptive adjustment, based on real-time feedback, allows the exoskeleton to provide optimal support in different environments and situations.

[0122] For example, a user can enter their account name into the exoskeleton system, which then reads their historical motion data stored in a data storage device. The system then analyzes this data using a pre-set deep learning network model, outputting information about their exercise habits, such as whether their movements are typically large, their movements are typically long, and their preferences for specific movements. This provides a reference for designing control strategies.

[0123] This embodiment can further enhance exoskeleton design to match individual user needs, enabling flexible configuration of appropriate power assist control strategies based on each user's characteristics. This not only improves comfort and efficiency, but also reduces over- or under-assistance, ensuring system stability and robustness.

[0124] The power-assistance control strategy output in this step, including the torque distribution scheme and trajectory planning scheme, can be executed by the real-time control module to ensure the real-time and accurate movement of the exoskeleton.

[0125] Step S105 , controlling the exoskeleton system to execute the personalized power-assistance control strategy to achieve synchronous operation of the exoskeleton system and the human body.

[0126] Specifically, the real-time control strategy is executed. In this step, the optimization algorithm can be used to drive the exoskeleton to execute the power-assisted control strategy obtained in the previous step. That is, based on the final power-assisted control strategy, the exoskeleton is driven to perform corresponding actions to achieve natural synchronization with human body movements.

[0127] In one embodiment of the present application, the exoskeleton system is controlled to execute a personalized power-assistance control strategy, including: adding the exoskeleton power-assistance torque to the control deviation torque to obtain the actual output torque of the exoskeleton; and driving the exoskeleton system through a real-time controller according to the actual output torque of the exoskeleton.

[0128] Specifically, in this embodiment, a real-time controller is used to control the exoskeleton system according to the following formula:

[0129] τ act =τ e2 +τ comp

[0130] Among them, τ act is the actual output torque of the exoskeleton, τ comp Torque to compensate for control deviations caused by noise or errors.

[0131] In this embodiment, a feedforward control method can be combined to further improve the system response speed and reduce the dynamic adjustment delay. The exoskeleton movement can also be monitored in real time to ensure the stability and safety of the control system.

[0132] This step then outputs a real-time drive signal, achieving precise synchronization between the exoskeleton's power-assisted control and the human's movements. The specific actions are executed according to the power-assisted control strategy, and real-time feedback is provided to the dynamic parameter estimation module, forming a closed-loop control system.

[0133] In summary, the control method of the exoskeleton power-assisting system based on the human-machine co-integration strategy of the embodiment of the present application, combined with the human-machine co-integration strategy, performs exoskeleton power-assisting system control based on multimodal information fusion and dynamic adaptation. The method adopts a motion intention prediction algorithm based on human-machine collaboration, and can accurately identify the user's motion intention by real-time analysis of multimodal information such as electromyographic signals, inertial measurement data and torque sensor information. Adopting an adaptive control strategy, based on Kalman filtering and dynamic adjustment algorithm, the power-assisting output is optimized in real time to enhance the robustness of the system. The human-machine co-integration model constructed in this application can be combined with personalized parameter configuration to achieve fine-grained adjustment of the power-assisting intensity and direction, and can flexibly configure a suitable power-assisting control strategy according to the characteristics of each user. Therefore, the method combines sensor data, multimodal interaction model and real-time control algorithm, can dynamically adapt to the individual differences and motion status of users, improve the accuracy, pertinence and flexibility of the power-assisting of the exoskeleton power-assisting system, and provide users with a more efficient and comfortable power-assisting experience.

[0134] In order to implement the above embodiment, the present application also proposes an exoskeleton system power-assistance control device based on a human-machine integration strategy. Figure 4 This is a schematic diagram of the structure of an exoskeleton system power-assistance control device based on a human-machine integration strategy proposed in an embodiment of the present application. Figure 4 As shown, the system includes: a collection module 100 , a construction module 200 , an estimation module 300 , a determination module 400 and a control module 500 .

[0135] The acquisition module 100 is used to collect basic motion data of the human body and the exoskeleton system through various types of data detection equipment, and initialize the motion state of the exoskeleton system according to the basic motion data.

[0136] The construction module 200 is used to construct a human-machine synergy dynamics model based on basic motion data, wherein the human-machine synergy dynamics model is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion.

[0137] The estimation module 300 is used to process the real-time data collected by the data detection equipment based on the human-machine collaborative dynamics model through the extended Kalman filter (EKF) algorithm to estimate various dynamic parameters of the human body and the exoskeleton system.

[0138] Determination module 400 is used to determine the power-assistance control strategy of the exoskeleton system by combining dynamic parameters and the human-machine collaborative dynamics model, and adjust the power-assistance control strategy according to the user's personalized parameters, wherein the power-assistance control strategy includes the power-assistance torque and motion trajectory planning of the exoskeleton system.

[0139] The control module 500 is used to control the exoskeleton system to execute the personalized power control strategy to achieve synchronous operation of the exoskeleton system and the human body.

[0140] It should be noted that the above explanation of the embodiment of the control method of the exoskeleton power assistance system based on the human-machine integration strategy is also applicable to the device of this embodiment. The principles of each module to achieve specific functions are the same and will not be repeated here.

[0141] To sum up, the exoskeleton system assistance control device based on the human-machine integration strategy of the embodiment of the present application, combined with sensor data, multimodal interaction model and real-time control algorithm, can dynamically adapt to the individual differences and movement status of the user, improve the accuracy, pertinence and flexibility of the assistance of the exoskeleton assistance system, and provide users with a more efficient and comfortable assistance experience.

[0142] In order to implement the above embodiments, the present application also proposes a non-temporary computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the exoskeleton system assistance control method based on the human-machine integration strategy as described in any one of the above-mentioned first aspect embodiments.

[0143] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0144] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of such features. Throughout the description of this application, "plurality" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0145] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, segment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed out of the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application belong.

[0146] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). Furthermore, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing it in another suitable manner if necessary, and then storing it in a computer memory.

[0147] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0148] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0149] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0150] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A method for controlling an exoskeleton system based on a human-machine synergy strategy, characterized in that: The following steps are involved: Collect basic motion data of the human body and the exoskeleton system through various types of data detection equipment, and initialize the motion state of the exoskeleton system according to the basic motion data; Constructing a human-machine synergy dynamics model based on the basic motion data, wherein the human-machine synergy dynamics model is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion; Based on the human-machine collaborative dynamics model, the real-time data collected by the data detection device is processed using an extended Kalman filter (EKF) algorithm to estimate various dynamic parameters of the human body and the exoskeleton system. Determining a power-assistance control strategy for the exoskeleton system based on the dynamic parameters and the human-machine collaborative dynamics model, and adjusting the power-assistance control strategy based on the user's personalized parameters, wherein the power-assistance control strategy includes power-assistance torque and motion trajectory planning for the exoskeleton system; The exoskeleton system is controlled to execute the individually adjusted power-assistance control strategy to achieve synchronous operation of the exoskeleton system and the human body.

2. The method according to claim 1, characterized in that The basic motion data of the human body and the exoskeleton system are collected through various types of data detection equipment, including: Collect various motion state parameters of human joints through inertial measurement unit (IMU); The torque sensor is used to collect the torque exerted by the human body on the exoskeleton system and the load torque of the exoskeleton joints; Initializing the motion state of the exoskeleton system according to the basic motion data includes: According to the multiple motion state parameters of the human body joints, the initial motion state parameters of the exoskeleton joints are correspondingly set.

3. The method according to claim 2, characterized in that The constructing of a human-machine collaborative dynamics model based on the basic motion data includes: Performing dynamic analysis on the basic motion data to construct a human body dynamics model and an exoskeleton dynamics model; The human-machine synergy dynamic model is constructed based on the human body dynamic model and the exoskeleton dynamic model, wherein the torque of the human-machine synergy dynamic model is equal to the sum of the torque applied by the human body on the exoskeleton system and the load torque of the exoskeleton joint, and is equal to the exoskeleton control torque.

4. The method according to claim 1, wherein The method of processing the real-time data collected by the data detection device based on the human-machine collaborative dynamics model by using the extended Kalman filter (EKF) algorithm includes: Determining the physical constraints of the EKF algorithm during the estimation process based on the motion state parameters in the human-machine collaborative dynamics model; Under the physical constraints, state estimation in the Kalman filter prediction stage is performed according to the dynamic equations in the human-machine collaborative dynamic model.

5. The method according to claim 1, wherein After estimating the dynamic parameters of the human body and the exoskeleton system, the method further includes: The dynamic parameters are fed back to the human-machine synergy dynamics model, and the inertia matrix and moment distribution in the human-machine synergy dynamics model are corrected according to the dynamic parameters.

6. The method according to claim 1, characterized in that Determining the power-assistance control strategy of the exoskeleton system by combining the dynamic parameters and the human-machine synergy dynamics model includes: Calculating the exoskeleton assist torque required for the exoskeleton system to assist based on the dynamic parameters and the human-machine synergy dynamics model, and adjusting the exoskeleton assist torque based on human-machine synchronization; estimating joint motion trajectories of the human body and the exoskeleton system based on the human-machine synergy dynamics model and the dynamic parameters; Designing an initial exoskeleton assistance trajectory based on the joint motion trajectory and position information of the human body and the exoskeleton system; Based on the dynamic parameters, the initial exoskeleton power-assisted trajectory is adjusted in real time through an optimization control algorithm to obtain a motion trajectory planning for the exoskeleton system.

7. The method according to claim 1, characterized in that The adjusting the power assist control strategy according to the user's personalized parameters includes: Analyzing physiological characteristic data of the current user to determine a collaboration mode of the exoskeleton system; adjusting the power assistance parameters in the power assistance control strategy according to the real-time motion data of the current user; Obtain historical exercise data of the current user, determine the exercise habits of the current user based on the historical exercise data, obtain real-time feedback data of the current user, and optimize the power assistance parameters in combination with the exercise habits and the real-time feedback data.

8. The method according to claim 6, characterized in that The step of controlling the exoskeleton system to execute the individually adjusted power-assistance control strategy includes: Adding the exoskeleton assist torque to the control deviation torque to obtain the actual output torque of the exoskeleton; The exoskeleton system is driven by a real-time controller according to the actual output torque of the exoskeleton.

9. An exoskeleton system power control device based on a human-machine integration strategy, characterized in that: include: An acquisition module, configured to acquire basic motion data of the human body and the exoskeleton system through various types of data detection equipment, and initialize the motion state of the exoskeleton system according to the basic motion data; A construction module for constructing a human-machine synergy dynamics model based on the basic motion data, wherein the human-machine synergy dynamics model is used to describe the torque distribution and coupling relationship between the human body and the exoskeleton system during motion; an estimation module for processing the real-time data collected by the data detection device using an extended Kalman filter (EKF) algorithm based on the human-machine collaborative dynamics model to estimate various dynamic parameters of the human body and the exoskeleton system; a determination module, configured to determine a power-assistance control strategy for the exoskeleton system based on the dynamic parameters and the human-machine synergy dynamics model, and adjust the power-assistance control strategy according to the user's personalized parameters, wherein the power-assistance control strategy includes power-assistance torque and motion trajectory planning for the exoskeleton system; The control module is used to control the exoskeleton system to execute the individually adjusted power-assistance control strategy to achieve synchronous operation of the exoskeleton system and the human body.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the exoskeleton system power-assistance control method based on the human-machine integration strategy as described in any one of claims 1 to 8 is implemented.

Images