Whole-body joint rehabilitation training device and control method thereof

Abstract

The present application relates to the technical field of rehabilitation equipment, and particularly relates to a whole-body joint rehabilitation training device and a control method thereof. The method of the present application comprises: collecting joint angles, IMU data and electromyographic signals when a user performs a plurality of standard actions; determining a joint range of motion risk level of a target joint according to the joint angles; determining a compensatory behavior risk level and a synergy efficiency score of the target joint according to the joint angles, the IMU data and the electromyographic signals; determining a training mode according to the compensatory behavior risk level, wherein the training mode at least comprises a general mode and a mode for compensatory behavior; determining a training parameter according to the joint range of motion risk level, wherein the training parameter comprises resistance; adjusting the training parameter according to the synergy efficiency score; and outputting the training mode and the adjusted training parameter. The method of the present application can improve rehabilitation efficiency and reduce compensatory behavior during training.

Description

A whole-body joint rehabilitation training device and its control method Technical Field

[0001] This invention relates to the field of rehabilitation equipment technology. More specifically, this invention relates to a whole-body joint rehabilitation training device and its control method. Background Technology

[0002] Joint range of motion impairment refers to limited or abnormal joint mobility caused by various reasons such as disease or injury, which seriously affects the patient's limb function and quality of life. Existing joint range of motion training programs often use a uniform approach, failing to adapt to the user's individual circumstances. Furthermore, during training, some patients are prone to compensatory behaviors, i.e., completing the training movements through abnormal movements of other joints or muscles. This not only fails to effectively improve the range of motion of the target joint but may also lead to new muscle strain or joint damage.

[0003] Therefore, how to conduct effective joint range of motion training and avoid compensatory behavior is a technical problem that urgently needs to be solved. Summary of the Invention

[0004] To address the aforementioned technical problems of ineffective joint range of motion training and the potential for compensatory behaviors during training, the present invention provides solutions in several aspects.

[0005] In a first aspect, the present invention provides a control method for a whole-body joint rehabilitation training device, comprising: acquiring joint angles, IMU data, and electromyographic signals when a user performs multiple standard movements; determining a joint range of motion risk level of a target joint based on the joint angles; determining a compensatory behavior risk level and a synergistic efficiency score of the target joint based on the joint angles, the IMU data, and the electromyographic signals, wherein the compensatory behavior risk level characterizes the user's tendency to utilize compensatory behavior, and the synergistic efficiency score characterizes the synergy between the target joint and other joints; determining a training mode based on the compensatory behavior risk level, wherein the training mode includes at least a general mode and a mode targeting compensatory behavior; determining training parameters based on the joint range of motion risk level, wherein the training parameters include resistance; adjusting the training parameters based on the synergistic efficiency score, wherein the synergistic efficiency score is positively correlated with the training parameters; and outputting the training mode and the adjusted training parameters.

[0006] Furthermore, determining the training mode based on the risk level of the compensatory behavior includes: determining it based on the preset mapping relationship between the risk level of the compensatory behavior and the training mode.

[0007] Further, determining training parameters based on the joint range of motion risk level includes: determining whether the joint range of motion risk level is a level 1 risk; if so, determining the resistance to be provided based on the user's weight, wherein the resistance is positively correlated with the weight; if not, determining the resistance to be provided based on the current joint angle of the target joint, wherein the resistance is positively correlated with the current joint angle.

[0008] Furthermore, the required resistance is determined based on the current joint range of motion, including:

[0009]

[0010] In the formula, F is the required resistance, k is the baseline coefficient, T is the time constant, t is the current training duration, and ROM is the distance from the target distance. curent This represents the current joint angle.

[0011] Further, adjusting the training parameters based on the collaborative efficiency score includes: adjusting the baseline coefficient based on the collaborative efficiency score to adjust the resistance, wherein the baseline coefficient is positively correlated with the collaborative efficiency score.

[0012] Furthermore, the training process also includes adjusting the training parameters at set intervals.

[0013] Further, based on the joint angle, the IMU data, and the electromyographic signal, the compensatory behavior risk level and synergistic efficiency score of the target joint are determined, including: fusing the joint angle and the IMU data to obtain a joint motion trajectory matrix; obtaining a muscle activation time sequence map based on the electromyographic signal; and inputting the joint motion trajectory matrix and the muscle activation time sequence map into a trained evaluation model to obtain the synergistic efficiency score and the compensatory behavior risk level; the evaluation model is a machine learning model.

[0014] Furthermore, based on the joint angle, the joint mobility risk level of the target joint is determined, including: matching the target joint to a standard range of motion; and determining the joint mobility risk level based on the difference between the user's target joint angle range and the standard range of motion.

[0015] Furthermore, it also includes: displaying virtual training scenes using AR technology and outputting corresponding prompts.

[0016] In a second aspect, a whole-body joint rehabilitation training device is provided, comprising a flexible sensor, an IMU array, and a high-density surface electromyography (SEMG), wherein the flexible sensor is used to acquire joint angles, the IMU array is used to acquire IMU data, and the high-density SEMG is used to acquire electromyographic signals; an exoskeleton frame is used to provide the resistance and assistance required for training; and a controller is connected to the flexible sensor, the IMU array, the high-density SEMG, and the exoskeleton frame to implement the control method of the whole-body joint rehabilitation training device described in the first aspect.

[0017] The beneficial effects of this invention are as follows: the method of this invention can provide corresponding training parameters according to the user's actual situation, assisting the user in carrying out effective joint range of motion improvement training, thereby improving the user's rehabilitation efficiency; by adjusting the user's training mode and training parameters according to the user's compensatory behavior risk level and coordination efficiency score, the occurrence of compensatory behavior can be reduced, thereby ensuring the rehabilitation efficiency and safety of the user's training; and by using AR technology for real-time error correction, the rehabilitation efficiency of training is further improved. Attached Figure Description

[0018] Figure 1 is a flowchart schematically illustrating a control method for a whole-body joint rehabilitation training device according to an embodiment of the present invention;

[0019] Figure 2 is a schematic structural block diagram illustrating a whole-body joint rehabilitation training device according to an embodiment of the present invention;

[0020] Figure 3 is a schematic diagram of an exoskeleton scaffold in the prior art. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0023] Figure 1 is a flowchart schematically illustrating the control method of a whole-body joint rehabilitation training device according to an embodiment of the present invention.

[0024] In a first aspect, the present invention provides a control method for a whole-body joint rehabilitation training device, as shown in FIG1. ​​The control method of the present invention includes S1 to S6.

[0025] S1. Collect joint angles, IMU data, and electromyographic signals when the user performs multiple standard movements.

[0026] In this embodiment, the IMU data includes angular velocity and acceleration. Specifically, joint angles of the main joints of the human body are collected using flexible sensors; angular velocity and acceleration are collected using an IMU (Inertial Measurement Unit) array (integrating gyroscope and accelerometer); and electromyographic signals (i.e., muscle activation intensity) of the target muscle group are collected using HD-sEMG electrodes (high-density surface electromyography).

[0027] In one embodiment, the major joints of the human body may include 14 joints: cervical joint, thoracic joint, lumbar joint, sacroiliac joint, shoulder joint, elbow joint, wrist joint, radioulnar joint, metacarpophalangeal joint, fingertip joint, hip joint, knee joint, ankle joint, and subtalar joint.

[0028] The system prompts the user to perform several preset standard movements (such as standing upright, squatting, raising arms, etc.), with each movement lasting 10 seconds, and collects joint angles, IMU data, and electromyographic signals during these movements. In one embodiment, Kalman filtering can be used to eliminate baseline drift of the sensors (including flexible sensors, IMU arrays, etc.), and then the user's motion baseline (the range of joint angles for each joint) can be established.

[0029] S2. Determine the joint mobility risk level, compensatory behavior risk level, and collaborative efficiency score of the target joint.

[0030] Joint range of motion risk level indicates the degree of difference between a user's joint range of motion and normal joint range of motion; compensatory behavior risk level indicates the user's tendency to use compensatory behavior; synergy efficiency score indicates the synergy between the target joint and other joints.

[0031] For any one of the 14 major joints, the joint range of motion risk level can be determined based on the joint angles of that joint. Specifically, the normal range of motion (i.e., standard range of motion) for that joint is searched from an international standard database (which contains the normal range of motion for each joint); then, the joint range of motion risk level is matched based on the difference between the joint angle range (composed of the minimum and maximum values ​​of the joint angles collected) and the standard range of motion for that joint.

[0032] In one embodiment, a risk score is obtained by dividing the span value of the joint angle range (maximum value minus minimum value) by the span value of the corresponding standard range of motion. Then, the corresponding joint range of motion risk level is matched based on this risk score. Specifically, a risk score less than 0.15 is classified as Level 1 risk; a risk score greater than or equal to 0.15 and less than 0.3 is classified as Level 2 risk; a risk score greater than or equal to 0.3 and less than 0.6 is classified as Level 3 risk; and a risk score greater than 0.6 is classified as Level 4 risk. This yields the joint range of motion risk levels for 14 major joints.

[0033] For example, if a user's shoulder joint external rotation angle range is 65-80°, and the standard range of shoulder joint external rotation found in the international standards database is 60-90°, then the user's shoulder joint risk is 0.5 (15 / 30 = 0.5), and the joint range of motion risk level is level three.

[0034] In one embodiment, a muscle activation heatmap (e.g., quadriceps activation intensity between 0-100%) can be generated based on electromyographic signals. The muscle activation heatmap is used to demonstrate the activation intensity and temporal characteristics of a specific muscle group during exercise. In one embodiment, the muscle activation heatmap is generated based on the electromyographic signals and the corresponding time. In this embodiment, the mathematical expression for the muscle activation heatmap H is:

[0035] H∈R M×T ;

[0036] In the formula, M represents the number of target muscle groups, T represents the time step (corresponding to the duration of the exercise), R represents the set of real numbers, and H represents the muscle activation time sequence matrix (M rows and T columns). ij Let H be an element representing the activation intensity of the i-th muscle at time j (normalized to the interval [0,1]).

[0037] In one embodiment, acceleration, angular velocity, and joint angles are fused (aligned via timestamps, e.g., synchronized using a precise time protocol) to generate a joint motion trajectory matrix (a core data structure describing the motion state of a multi-joint system, 14 rows and 3 columns, unit: angle / acceleration). Specifically, the mathematical expression for the joint motion trajectory matrix P is:

[0038] P∈R T×N×D ;

[0039] In the formula, T is the number of time steps (e.g., collecting 10 seconds of data at 200Hz corresponds to T=2000), N is the number of joints (in this embodiment, N is 14), R is the set of real numbers, and D is the feature of each joint (including joint angle, angular velocity, and acceleration). It can be understood that T also corresponds to the time dimension, N corresponds to the joint dimension, and D corresponds to the feature dimension.

[0040] Furthermore, the joint motion trajectory matrix and muscle activation timing map are input into the trained evaluation model to obtain the synergistic efficiency scores and compensatory behavior risk levels of 14 major joints. In this embodiment, the evaluation model is a GNN (Graph Neural Network) model.

[0041] After obtaining the user's coordination efficiency score, compensatory behavior risk level, and joint mobility level for 14 major joints, the joint with the lowest coordination efficiency score can be designated as the target joint (i.e., the joint that needs to be trained). In an optional embodiment, the user can also select the joint that needs to be trained.

[0042] By assessing a user's joint range of motion and compensatory behavior based on joint angles, angular velocities, and accelerations, the user's joint range of motion and compensatory behavior can be clearly identified. This ensures that the subsequent training parameters are matched with the user's actual situation, avoiding the situation where a uniform training program results in mediocre training effects, thereby improving the user's rehabilitation efficiency.

[0043] S3. Determine the training mode based on the risk level of compensatory behavior.

[0044] In this embodiment, the risk levels of compensation behavior include Level 1 risk (low risk), Level 2 risk (medium risk) and Level 3 risk (high risk). The higher the risk level of compensation behavior, the greater the user's tendency to use compensation behavior.

[0045] The training modes include a basic training mode (i.e., the general mode) and modes targeting compensatory behaviors (including weak chain reinforcement mode and forced dissociation mode). The basic training mode provides content related to joint range of motion training, such as isometric contraction maintenance within the target range of motion (e.g., 60-75°) (e.g., holding a 65° external rotation of the shoulder joint for 5-8 seconds) to enhance joint stability.

[0046] The weak link reinforcement mode involves adding resistance training to compensatory areas in addition to joint range of motion training. For example, during lumbar spine training, patients may exhibit compensatory behavior in the pelvis. In such cases, pelvic movement can be restricted, and the applied resistance can be increased (e.g., by 20%) during training to reduce compensatory behavior and improve rehabilitation efficiency.

[0047] The forced separation mode does not provide joint range of motion training (i.e., the user does not need to reach the target range during training), locks the abnormal joint, and forces the target joint to undergo rehabilitation training independently. For example, when training the lumbar spine, if the pelvis is an abnormal area (i.e., a compensatory area), then during training, the distance of pelvic movement is limited (in this embodiment, the movement range is within 2cm). The training goal of the forced separation mode is not to improve joint range of motion (i.e., to perform joint range of motion training), but to minimize compensatory behavior and avoid triggering pain to ensure the safety of the user during training. It should be noted that the forced separation mode can only be used with the assistance of medical personnel.

[0048] In one embodiment, the training mode corresponding to the user's compensation behavior risk level is determined based on a preset mapping relationship between compensation behavior risk levels and training modes. Specifically, if the compensation behavior risk level is Level 1, the basic training mode is used; if the compensation behavior risk level is Level 2, the weak link reinforcement mode is used; and if the compensation behavior risk level is Level 3, the forced separation mode is used.

[0049] By matching training modes according to the risk level of compensatory behavior of the user's target joint, users with compensatory behavior can avoid or limit their compensatory behavior during training. At the same time, the exoskeleton frame provides resistance and / or assistance to help users conduct effective training, thereby improving the safety of training and rehabilitation efficiency.

[0050] It should be noted that when some patients cannot meet the training requirements, exoskeleton assistance is needed.

[0051] S4. Determine training parameters based on the risk level of joint mobility.

[0052] In this embodiment, the joint range of motion risk level includes Level 1 (low risk), Level 2 (medium risk), Level 3 (high risk), and Level 4 (very high risk). Level 1 risk indicates that the target joint's functional activity is largely unrestricted, requiring primarily preventative training; Level 2 risk indicates partial restriction of daily activities, necessitating intensive range of motion (ROM) training; Level 3 risk indicates severe functional impairment with a risk of injury, requiring medical intervention and daily training; Level 4 risk indicates the possibility of surgery, in which case training should be discontinued.

[0053] In this embodiment, training parameters may include resistance, assistance, and training speed (a preset standard speed to assist the user in training). Specifically, during the eccentric phase of exercise, resistance is provided by pneumatic muscles (e.g., resistance during squatting); during the concentric phase of exercise, assistance is provided by a magnetorheological damper (e.g., assistance during standing). It should be noted that the method for determining the assistance is similar to that for resistance, but the direction of assistance is opposite to that of resistance.

[0054] Specifically, when the joint mobility risk level is Level 1, the required resistance (or assistance) is determined based on the user's weight. In this embodiment, the resistance (or assistance) is positively correlated with the user's weight. Specifically, the user's weight is multiplied by an adjustment factor (set to be less than 1, in this embodiment, 0.3) to obtain the required resistance (or assistance). It can be understood that Level 1 risk generally refers to a situation where the user's joint mobility is close to the minimum range of normal mobility. For example, the normal range of external rotation of the shoulder joint is 60-90°. If the user's range is exactly 60°, although it is within the normal range, without intervention, joint mobility impairment is likely to occur.

[0055] When the joint range of motion risk level is Level 2 or Level 3, the required resistance is determined based on the current joint angle of the target joint. Specifically, the formula for calculating the resistance is:

[0056]

[0057] In the formula, F is the resistance, k is the baseline coefficient, T is the time constant, t is the current training duration, and ROM is the ROM. curent This represents the current joint angle.

[0058] The baseline coefficients and time constants are obtained through deep learning (PPO algorithm) to ensure that the resistance can match the user's actual situation.

[0059] Based on the above formula for calculating resistance, it can be seen that when the user approaches the activity limit, the ROM current The increase in intensity, but the exponential term begins to saturate, thus providing a safe buffer for the user. This avoids sudden load damage to tissues and excessive traction injury, while ensuring that the user trains within the target intensity, thereby improving the safety of training and rehabilitation efficiency.

[0060] S5. Adjust the training parameters based on the collaborative efficiency score.

[0061] In this embodiment, the baseline coefficient is adjusted based on the collaborative efficiency score to adjust the required resistance. Specifically, the adjusted baseline coefficient is:

[0062]

[0063] In the formula, k is the corrected baseline coefficient, k_base is the original baseline coefficient, and C is the collaborative efficiency score.

[0064] Furthermore, the training speed is adjusted based on the collaborative efficiency score. Specifically, it is determined whether the collaborative efficiency score is greater than or equal to a score threshold (set to 85 in this embodiment). If so, the current speed is maintained; otherwise, the collaborative efficiency score is divided by the score threshold and then multiplied by the current speed to obtain the adjusted speed.

[0065] By adjusting resistance based on the co-efficiency score, ineffective compensations by users during training can be reduced; by adjusting training speed based on the co-efficiency score, the problem of speed mismatch leading to user injury can be avoided, thereby improving the safety of user training.

[0066] S6, Output training mode and adjusted training parameters.

[0067] It outputs the training mode and adjusted training parameters to assist users in conducting corresponding training.

[0068] During training, the training parameters are updated every set time interval (5 minutes in this embodiment). In one embodiment, the resistance can be updated by updating the baseline coefficient. Specifically, the current joint angle is divided by the current baseline coefficient, and then multiplied by a preset value (0.8 in this embodiment) to obtain the updated baseline coefficient.

[0069] In addition, if the activation intensity of the target muscle group does not reach the preset threshold during training, the resistance to output can be reduced.

[0070] In one embodiment, the method of the present invention further includes: displaying a virtual training scene using AR (augmented reality) technology and outputting prompts.

[0071] Specifically, a three-dimensional skeletal model of the user is constructed using data collected by a depth camera. The IMU data is then aligned with the three-dimensional skeletal model constructed by the depth camera to build a full-body kinetic chain.

[0072] Before training, the user's field of vision is calibrated using AR glasses, and the coordinates of the virtual training scene are bound. Then, based on the virtual scene selected by the user, the user's ROM threshold is determined. Specifically, the selected virtual scene is matched with a preset joint ROM requirement library to obtain a reference ROM threshold (the baseline threshold for normal individuals). For example, if the user selects a rock climbing scene, the shoulder joint external rotation is greater than 70° (ROM threshold). If the user's ROM does not reach 70°, the difficulty is automatically reduced (switching to an easier scene) / threshold.

[0073] During training, a virtual coach and a virtual target line (determined by a ROM threshold) are displayed through AR glasses. When the user deviates from the virtual target line, the virtual coach outputs prompts (e.g., a voice prompt such as "Right knee valgus 5°, please externally rotate to the green target line").

[0074] In one embodiment, the control method of the present invention further includes generating a training report, which includes the improvement in joint mobility, the reduction in compensatory movements, and training parameters.

[0075] Figure 2 is a schematic structural block diagram illustrating a whole-body joint rehabilitation training device according to an embodiment of the present invention.

[0076] In a second aspect, the present invention also provides a whole-body joint rehabilitation training device. As shown in Figure 2, the whole-body joint rehabilitation training device includes a flexible sensor, an IMU array, a high-density surface electromyography (HD-sEMG) device, an exoskeleton support, and a controller. Specifically, the flexible sensor is embedded in elastic fabric, covering 14 major joints of the human body, for collecting joint angles; the IMU array uses an MPU-9250 module (integrating an accelerometer and a gyroscope), deployed at bony prominences near the joints, for real-time acquisition of acceleration and angular velocity; the high-density surface electromyography (HD-sEMG) device has 16-channel electrode patches, attached to the target muscle group (such as the quadriceps femoris and deltoid), for collecting electromyographic signals of the target muscle group.

[0077] The exoskeleton scaffold (which may be an exoskeleton scaffold as shown in the prior art as in Figure 3) includes pneumatic artificial muscles (PAM) and magnetorheological dampers to provide the resistance and power required for training;

[0078] The controller is connected to a flexible sensor, an IMU array, a high-density surface electromyography device, and an exoskeleton scaffold to implement the control method of the whole-body joint rehabilitation training device described in the first aspect.

[0079] In alternative embodiments, AR glasses may also be included.

[0080] When in use, the user wears a flexible sensor suit that fits the joints and muscle groups. The exoskeleton frame adjusts its length according to the user's body shape. The AR glasses calibrate the user's field of vision and are bound to the coordinate system of the virtual training scene. The controller adjusts the training parameters based on the user's sensor data.

[0081] In the description of this specification, "multiple" means at least two, such as two, three or more, unless otherwise explicitly specified. Furthermore, the step division of the method described above is only for clarity of description; in implementation, it can be combined into one step or some steps can be split into multiple steps, as long as they include the same logical relationship.

[0082] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. A control method for a whole-body joint rehabilitation training device, characterized in that, include: Collect joint angles, IMU data, and electromyographic signals when the user performs multiple standard movements; The joint mobility risk level of the target joint is determined based on the joint angle. Based on the joint angle, the IMU data, and the electromyographic signal, the compensatory behavior risk level and synergistic efficiency score of the target joint are determined. The compensatory behavior risk level represents the user's tendency to use compensatory behavior, and the synergistic efficiency score represents the synergy between the target joint and other joints. The training mode is determined based on the risk level of the compensatory behavior, and the training mode includes at least a general mode and a mode for compensatory behavior. Training parameters, including resistance, are determined based on the joint range of motion risk level; the training parameters are adjusted based on the synergistic efficiency score, which is positively correlated with the training parameters. Output the training mode and the adjusted training parameters; Training parameters are determined based on the joint range of motion risk level, including: when the joint range of motion risk level is level two or three, the expression for calculating resistance is: In the formula, For the resistance that needs to be provided, As the benchmark coefficient, It is a time constant. For the current training duration, Given the current joint angle; adjust the training parameters according to the collaborative efficiency score, including: adjusting the baseline coefficient according to the collaborative efficiency score, wherein the adjusted baseline coefficient is: In the formula, The corrected benchmark coefficient. The baseline coefficient before correction. Scoring is given for collaborative efficiency.

2. The control method for the whole-body joint rehabilitation training device according to claim 1, characterized in that, Determining the training mode based on the risk level of the compensatory behavior includes: determining it based on the preset mapping relationship between the risk level of the compensatory behavior and the training mode.

3. The control method for the whole-body joint rehabilitation training device according to claim 1, characterized in that, Determining training parameters based on the joint range of motion risk level includes: determining whether the joint range of motion risk level is Level 1; if so, determining the resistance to be provided based on the user's weight, wherein the resistance is positively correlated with the weight; if not, determining the resistance to be provided based on the current joint angle of the target joint, wherein the resistance is positively correlated with the current joint angle.

4. The control method for the whole-body joint rehabilitation training device according to claim 1, characterized in that, The training process also includes adjusting the training parameters at set intervals.

5. The control method for the whole-body joint rehabilitation training device according to claim 1, characterized in that, Based on the joint angle, the IMU data, and the electromyographic signal, the risk level of compensatory behavior and the collaborative efficiency score of the target joint are determined, including: fusing the joint angle and the IMU data to obtain a joint motion trajectory matrix; obtaining a muscle activation time sequence map based on the electromyographic signal; and inputting the joint motion trajectory matrix and the muscle activation time sequence map into a trained evaluation model to obtain the collaborative efficiency score and the risk level of compensatory behavior; the evaluation model is a machine learning model.

6. The control method for the whole-body joint rehabilitation training device according to claim 1, characterized in that, Based on the joint angle, determine the joint mobility risk level of the target joint, including: matching the target joint to a standard range of motion; and determining the joint mobility risk level based on the difference between the user's target joint angle range and the standard range of motion.

7. The control method for the whole-body joint rehabilitation training device according to claim 1, characterized in that, Also includes: The system uses AR technology to display virtual training scenarios and output corresponding prompts.

8. A whole-body joint rehabilitation training device, characterized in that, The device includes a flexible sensor, an IMU array, and a high-density surface electromyography (SEMG), wherein the flexible sensor is used to acquire joint angles, the IMU array is used to acquire IMU data, and the high-density SEMG is used to acquire electromyographic signals; an exoskeleton frame is used to provide the resistance and assistance required for training; and a controller is connected to the flexible sensor, the IMU array, the high-density SEMG, and the exoskeleton frame, for implementing the control method of the whole-body joint rehabilitation training device according to any one of claims 1-7.

Images