Rehabilitation training system, rehabilitation training method, electronic equipment and medium

Abstract

The invention provides a rehabilitation training system, a rehabilitation training method, electronic equipment and a medium, and is applied to the technical field of rehabilitation training.The rehabilitation training system is characterized in that a rehabilitation robot is connected with a robot controller, and the rehabilitation robot is used for guiding a rehabilitation object to move; the measurement module is used for acquiring a measurement signal of a rehabilitation object; the control module is connected with the robot controller and the measuring module, and the control module is used for adjusting the spring coefficient and the applied force coefficient of the robot controller based on a preset rehabilitation training mode; determining a training state of the rehabilitation object based on the measurement signal; under the condition that the rehabilitation training mode is a challenge mode, force noise is increased for the robot controller, and a noise gain parameter of the force noise is adjusted based on the training state, so that the force disturbance amplitude of the rehabilitation robot on the rehabilitation object is adjusted through the noise gain parameter. According to the embodiment of the invention, continuous adjustment of rehabilitation training tasks can be realized, and the rehabilitation training effect is improved.

Description

Technical Field

[0001] The present application relates to the field of rehabilitation training technology, and in particular to a rehabilitation training system, a rehabilitation training method, an electronic device and a medium. Background Art

[0002] Stroke has become the leading cause of adult disability worldwide. About half of stroke patients will face the problem of long-term loss of arm function, which seriously affects their daily quality of life. The current rehabilitation robot system mainly adjusts the difficulty of tasks in a discrete manner by changing the nature of the task. For example, if the current task is point-to-point training, if the task difficulty is increased, the task will be changed to picking fruits. It cannot be adjusted continuously, the adjustability is insufficient, and the patient needs to re-adapt to the new training task, which increases the rehabilitation training time and has poor results. Summary of the invention

[0003] The main purpose of the embodiments of the present application is to propose a rehabilitation training system, a rehabilitation training method, an electronic device and a medium, aiming to achieve continuous adjustment of rehabilitation training tasks and improve the rehabilitation training effect.

[0004] To achieve the above objectives, a first aspect of an embodiment of the present application provides a rehabilitation training system, comprising:

[0005] A rehabilitation robot, the rehabilitation robot being connected to a robot controller, and the rehabilitation robot being used to guide a rehabilitation subject to move;

[0006] a measurement module, the measurement module being used to obtain a measurement signal of the rehabilitation subject;

[0007] A control module, wherein the control module is connected to the robot controller and the measurement module respectively, and the control module is used for:

[0008] Based on a preset rehabilitation training mode, adjusting a spring coefficient and an applied force coefficient of the robot controller;

[0009] determining a training state of the rehabilitation subject based on the measurement signal;

[0010] When the rehabilitation training mode is the challenge mode, force noise is added to the robot controller, and a noise gain parameter of the force noise is adjusted based on the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter.

[0011] In some embodiments, the control module is further configured to:

[0012] acquiring the training applied force of the rehabilitation subject from the measurement signal;

[0013] Determining a dynamic equation of the robot controller based on the training applied force, the spring coefficient, the applied force coefficient, and a noise gain parameter of the force noise;

[0014] Discretizing the dynamic equation to determine the target terminal velocity of the rehabilitation robot;

[0015] The target terminal velocity is inversely calculated using the inverse kinematics model of the rehabilitation robot to determine the operating parameters of the rehabilitation robot, so as to control the rehabilitation robot to operate with the operating parameters through the robot controller.

[0016] In some embodiments, the rehabilitation training system further includes a virtual reality device, and the control module is further configured to:

[0017] Get multiple input graphics;

[0018] Preprocessing the plurality of input graphics respectively to determine graphic trajectories corresponding to the input graphics;

[0019] For each of the graphic trajectories, using a minimum jerk trajectory method to determine an optimized trajectory corresponding to the graphic trajectory, and determining the graphic complexity of the optimized trajectory;

[0020] Determining a target difficulty based on the current display track of the virtual reality device and the training status;

[0021] Determine an optimized trajectory whose graphic complexity matches the target difficulty as a target display trajectory;

[0022] The virtual reality device is controlled to display the target display trajectory.

[0023] In some embodiments, the control module is further configured to:

[0024] Based on the optimized trajectory, determining a time series corresponding to the optimized trajectory and a trajectory length of the optimized trajectory;

[0025] Obtaining a drawing speed function and a drawing duration of the optimized trajectory from the time series;

[0026] Calculating the second-order derivative of the drawing speed function with respect to time;

[0027] Determining a logarithmic dimensionless jerk of the optimized trajectory based on the drawing duration, the trajectory length, and the second-order derivative;

[0028] Based on the logarithmic dimensionless jerk, a graphical complexity of the optimized trajectory is determined.

[0029] In some embodiments, the measurement module includes an eye tracking module, and the eye tracking module is disposed on the virtual reality device;

[0030] The control module is also used for:

[0031] obtaining an eye movement signal from the measurement signal;

[0032] Analyzing the eye movement signal using an intention detection model to obtain the gaze position of the rehabilitation subject;

[0033] Based on the line of sight position, a training state of the rehabilitation subject is determined.

[0034] In some embodiments, the virtual reality device is used to display the measurement module further comprising a position detection module;

[0035] The control module is also used for:

[0036] acquiring a position detection signal from the measurement signal;

[0037] determining an object position of the rehabilitation object in the virtual reality device based on the position detection signal;

[0038] When the rehabilitation training mode is an auxiliary mode, if the distance between the object position and the current displayed trajectory is greater than a preset distance threshold, a first target position is determined based on the line of sight position and the current displayed trajectory, and the spring coefficient is adjusted to control the rehabilitation robot through the robot controller to drive the rehabilitation object to move to the first target position.

[0039] In some embodiments, the control module is further configured to:

[0040] When the rehabilitation training mode is a passive mode, the applied force coefficient is set to 0;

[0041] Setting the spring coefficient based on a preset coefficient threshold;

[0042] Determining a second target position based on a tangent direction of the object position along the currently displayed trajectory;

[0043] The robot controller is controlled to control the rehabilitation robot to drive the rehabilitation object to move toward the second target position.

[0044] In some embodiments, the control module is further configured to:

[0045] Comparing the current display track of the virtual reality device with the sight line position to obtain a comparison result;

[0046] When the comparison result indicates that the time for which the current display trajectory and the sight line position are continuously in a non-overlapping state is greater than a preset time threshold, the rehabilitation robot is controlled to stop running.

[0047] In some embodiments, the control module is further configured to:

[0048] determining an evaluation parameter of the rehabilitation subject based on the measurement signal and the current displayed trajectory;

[0049] The virtual reality device is controlled to display the evaluation parameters.

[0050] In some embodiments, the control module is further configured to:

[0051] Obtaining optimization parameters corresponding to the current display trajectory;

[0052] determining a training parameter for the rehabilitation subject based on the measurement signal;

[0053] Based on the ratio of the training parameter to the optimization parameter, an evaluation parameter of the rehabilitation subject is determined.

[0054] To achieve the above-mentioned purpose, a second aspect of an embodiment of the present application proposes a rehabilitation training method, which is applied to a control module in a rehabilitation training system. The rehabilitation training system also includes a rehabilitation robot and a measurement module. The rehabilitation robot is connected to a robot controller. The rehabilitation training method includes:

[0055] Obtain preset rehabilitation training mode;

[0056] Based on the rehabilitation training mode, adjusting the spring coefficient and the applied force coefficient of the robot controller;

[0057] determining a training state of the rehabilitation subject based on a measurement signal from the measurement module;

[0058] When the rehabilitation training mode is the challenge mode, force noise is added to the robot controller, and a noise gain parameter of the force noise is adjusted based on the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter.

[0059] To achieve the above objectives, the third aspect of an embodiment of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor implements the rehabilitation training method described in the second aspect when executing the computer program.

[0060] To achieve the above objectives, the fourth aspect of an embodiment of the present application proposes a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the rehabilitation training method described in the second aspect.

[0061] The rehabilitation training system, rehabilitation training method, electronic device and medium proposed in the present application, the rehabilitation training system includes a rehabilitation robot, a measurement module and a control module, and the rehabilitation robot is connected to the robot controller. By setting the spring coefficient and the applied force coefficient of the robot controller, the rehabilitation training mode can be adjusted to adapt to the training needs of stroke patients at different stages. In addition, when the rehabilitation training mode is the challenge mode, force noise is added to the robot controller to increase force disturbance for the rehabilitation object, and the noise gain parameter of the force noise is adjusted according to the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter, thereby realizing adaptive adjustment of the difficulty of the training task. This adjustment method can realize continuous adjustment of the difficulty of the training task according to the training state of the rehabilitation object, and can be applied to the same training task. The rehabilitation object does not need to re-adapt to the new training task, which reduces the rehabilitation training time and improves the rehabilitation training effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] Figure 1 is a structural block diagram of a rehabilitation training system provided in an embodiment of the present application;

[0063] Figure 2 is a schematic diagram of a rehabilitation robot provided in an embodiment of the present application;

[0064] Figure 3 is a schematic diagram of force noise under different noise gain parameters provided in an embodiment of the present application;

[0065] Figure 4 It is a schematic diagram of a damping-spring-mass system corresponding to the robot controller provided in an embodiment of the present application;

[0066] Figure 5 is a schematic diagram of controlling a rehabilitation robot through a robot controller provided in an embodiment of the present application;

[0067] Figure 6 is a schematic diagram of determining image complexity provided by an embodiment of the present application;

[0068] Figure 7 is a schematic diagram of the comprehensive difficulty of the rehabilitation training tasks provided in the embodiments of the present application;

[0069] Figure 8 is a schematic diagram of an auxiliary training mode provided in an embodiment of the present application;

[0070] Fig. 9 is a schematic diagram of a first target position provided in an embodiment of the present application;

[0071] Fig.10 is a flow chart of the rehabilitation training method provided in the embodiment of the present application;

[0072] Fig.11 This is the hardware structure of the electronic device provided in the embodiment of the present application. DETAILED DESCRIPTION

[0073] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0074] It should be noted that, although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first", "second", etc. in the specification, claims and the above drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0075] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0076] Stroke has become the leading cause of adult disability worldwide. About half of stroke patients will face the problem of long-term loss of arm function, which seriously affects their daily quality of life. The current rehabilitation robot system mainly adjusts the difficulty of tasks in a discrete manner by changing the nature of the task. For example, if the current task is point-to-point training, if the task difficulty is increased, the task will be changed to picking fruits. It cannot be adjusted continuously, the adjustability is insufficient, and the patient needs to re-adapt to the new training task, which increases the rehabilitation training time and has poor results.

[0077] Based on this, the present application provides a rehabilitation training system, a rehabilitation training method, an electronic device and a medium. The rehabilitation training system provided in the embodiment of the present application can realize continuous adjustment of rehabilitation training tasks and improve the rehabilitation training effect.

[0078] The present application is further described below in conjunction with the accompanying drawings.

[0079] Reference Figure 1 A first aspect of an embodiment of the present application proposes a rehabilitation training system, including a rehabilitation robot, a measurement module and a control module.

[0080] The rehabilitation robot is connected to a robot controller, and is used to guide the rehabilitation object to move.

[0081] The measurement module is used to obtain the measurement signal of the rehabilitation object.

[0082] The control module is connected with the robot controller and the measuring module respectively.

[0083] The control module is specifically used for:

[0084] Based on the preset rehabilitation training mode, the spring coefficient and applied force coefficient of the robot controller are adjusted.

[0085] Based on the measurement signals, a training state of the rehabilitation subject is determined.

[0086] When the rehabilitation training mode is the challenge mode, force noise is added to the robot controller, and the noise gain parameter of the force noise is adjusted based on the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter.

[0087] It should be noted that the rehabilitation subjects are those who need rehabilitation training, and they are usually stroke patients. Figure 2 The rehabilitation robot provided in the embodiment of the present application is a planar rehabilitation robot, which includes a wrist support. When the rehabilitation subject is undergoing rehabilitation training, the wrist can be placed on the wrist support to perform rehabilitation training tasks. The position of the wrist support is controlled by an H-shaped drive mechanism, which includes two stepper motor pulleys, two driven pulleys, and a belt passing through these pulleys. The belt is fixed to a central platform, which is the platform on which the wrist of the rehabilitation subject is placed. When the two motors rotate in the same direction, the wrist support will move left and right, that is, along the Figure 2 The wrist bracket moves in the x-axis direction shown; when the two motors rotate in opposite directions, the wrist bracket moves up and down, that is, along the Figure 2 The rehabilitation robot is used to guide the rehabilitation subject to move. Specifically, the rehabilitation subject can move under the guidance of the rehabilitation robot or can move autonomously, thereby driving the rehabilitation robot to move.

[0088] The robot controller is a damper-spring-mass system. The robot controller follows the damper-spring-mass system dynamics along each axis, that is:

[0089]

[0090] Among them, M is the mass parameter, x(t) is the wrist position of the rehabilitation object, D is the damping parameter, K is the spring coefficient, f(t) is the force applied by the rehabilitation object, that is, the applied force, which can be measured by the measurement module, and H is the switch coefficient that controls whether to include the applied force, that is, the applied force coefficient. The robot controller follows the damping-spring-mass system dynamics along both the x-axis and the y-axis. The spring coefficient corresponds to the spring, which can pull the rehabilitation object to move. The damping parameter is represented by the damping applied by the movement of the rehabilitation object. The damping parameter can simulate tasks such as drawing and painting to increase the immersion of the rehabilitation training task. When the applied force coefficient is 0, the rehabilitation object has no applied force, and the control module controls the rehabilitation robot to pull the rehabilitation object to move through the robot controller. When the applied force coefficient is 1, the rehabilitation object actively moves, and the movement of the rehabilitation object then drives the rehabilitation robot to move.

[0091] The robot controller is connected to the control module, and the control module can control the rehabilitation object to move through the robot controller.

[0092] The specific type of robot controller can be set according to the requirements, as long as the system is a damping-spring-mass system. In the embodiment of the present application, an admittance controller is used as a robot controller. An admittance controller is a controller used to control the interaction between the robot end effector and the environment. It achieves compliant control by adjusting the dynamic properties of the robot.

[0093] It should be noted that the measurement module is used to measure the behavioral signals and physiological signals of the rehabilitation subject, where the behavioral signals can be eye gaze point, blinking, applied force, etc., and the physiological signals can be electrocardiogram, skin conductance, respiration, body temperature, pupil size, etc. These two types of signals can be analyzed to quantify the rehabilitation subject's concentration and emotional state, thereby determining the rehabilitation subject's training state, which can be used as feedback input for adjusting the difficulty of rehabilitation training tasks.

[0094] The measurement signal is a signal measured by the measurement module, and the measurement signal includes the behavioral signal and physiological signal of the rehabilitation subject. Based on the behavioral signal, the degree of concentration of the rehabilitation subject, the gaze position in the rehabilitation training task, etc. can be determined, which is convenient for determining the difficulty of the current rehabilitation training task for the rehabilitation subject. Based on the physiological signal, the emotional state and physical health state of the rehabilitation subject can be determined, which is convenient for determining whether the current rehabilitation subject is able to perform the rehabilitation training task, thereby ensuring the health state of the rehabilitation subject in the rehabilitation training task.

[0095] It should be noted that there are many types of rehabilitation training modes, such as passive mode, auxiliary mode, active mode, and challenge mode. The rehabilitation training mode can be set according to the needs of the rehabilitation subject. The control module sets the spring coefficient and the applied force coefficient by obtaining the preset rehabilitation training mode. Stroke patients at different stages have different upper limb strength and require different rehabilitation training modes. The setting of the rehabilitation training mode can meet the training needs of stroke patients at different stages and with different symptoms.

[0096] It should be noted that when the upper limb function of the rehabilitation subject has recovered to a large extent and entered the chronic stage, the difficulty of the training task can be appropriately increased, so that the rehabilitation subject can be trained at a task difficulty that matches his skills to improve the recovery speed. At this time, set the spring coefficient to 0 and the applied force coefficient to 1.

[0097] In order to adjust the difficulty of the task, the embodiment of the present application introduces force noise (Perlin Noise) into the damping-spring-mass system:

[0098]

[0099] Among them, n(t) is the introduced force noise, and s is the noise gain parameter. The force disturbance amplitude refers to the disturbance force set for the rehabilitation subject to perform the rehabilitation training task during the rehabilitation training process, which can also be understood as resistance. The larger the noise gain parameter, the greater the force disturbance amplitude for the rehabilitation subject. If the rehabilitation subject wants to move the same distance, it needs more strength, that is, it needs more applied force, which realizes the adjustment of the difficulty of the rehabilitation training task.

[0100] In the embodiment of the present application, Perlin Noise is used as force noise. Perlin Noise is an algorithm widely used in computer graphics to generate smooth random noise similar to natural phenomena. Perlin Noise is used to generate random force disturbances to change the difficulty of completing rehabilitation training tasks.

[0101] Reference Figure 3 , Figure 3 This is a schematic diagram of Perlin noise, i.e., force noise, under different noise gain parameters provided in the embodiments of the present application. It can be seen that the larger the noise gain parameter, the greater the force noise introduced by the damping-spring-mass system, the greater the force disturbance amplitude to the rehabilitation subject, and the greater the difficulty of completing the training.

[0102] The rehabilitation training system proposed in the present application includes a rehabilitation robot, a measurement module and a control module, and the rehabilitation robot is connected to a robot controller. By setting the spring coefficient and the applied force coefficient of the robot controller, the rehabilitation training mode can be adjusted to adapt to the training needs of stroke patients at different stages. In addition, when the rehabilitation training mode is a challenge mode, the control module adds force noise to the robot controller to increase force disturbance for the rehabilitation object, and adjusts the noise gain parameter of the force noise according to the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter, thereby realizing adaptive adjustment of the difficulty of the training task. This adjustment method can realize continuous adjustment of the difficulty of the training task according to the training state of the rehabilitation object, and can be applied to the same training task. The rehabilitation object does not need to re-adapt to the new training task, which reduces the rehabilitation training time and improves the rehabilitation training effect.

[0103] It is understood that the control module is also used to:

[0104] The training exerted force of the rehabilitation subject is obtained from the measurement signal.

[0105] The dynamic equations of the robot controller are determined based on the training applied force, spring coefficient, applied force coefficient, and noise gain parameters of the force noise.

[0106] The dynamic equations are discretized to determine the target terminal velocity of the rehabilitation robot.

[0107] The inverse kinematics model of the rehabilitation robot is used to perform inverse calculation on the target terminal velocity to determine the operation parameters of the rehabilitation robot, so as to control the rehabilitation robot to operate according to the operation parameters through the robot controller.

[0108] It should be noted that, refer to Figure 2 The measurement module includes a force sensor, which is arranged on the wrist support and can measure the magnitude of the force applied by the rehabilitation subject during the training process. Therefore, the training force applied by the rehabilitation subject can be obtained from the measurement signal.

[0109] The training applied force refers to the magnitude of the force applied by the rehabilitation subject to the rehabilitation robot and the robot controller during the training process.

[0110] Reference Figure 4 The robot controller is a damping-spring-mass system. Based on the training applied force, spring coefficient, applied force coefficient, and noise gain parameters of force noise, the dynamic equation of the robot controller is determined. The dynamic equation of the robot controller can be expressed as:

[0111]

[0112] Where M is the mass parameter, x(t) is the wrist position of the rehabilitation subject, D is the damping parameter, K is the spring coefficient, f(t) is the training force, and H is the force coefficient. n(t) is the force noise, and s is the noise gain parameter.

[0113] Reference Figure 5 After determining the dynamic equation of the robot controller, the dynamic equation can be discretized to determine the target terminal velocity of the rehabilitation robot. Specifically, the dynamic equation is discretized by the implicit Euler method to determine the target terminal velocity of the rehabilitation robot. The target terminal velocity can be expressed as:

[0114]

[0115] Among them, v(t) is the target terminal velocity, which is the velocity that the end of the rehabilitation robot wants to reach and is also the terminal velocity at time t. v(t-1) is the terminal velocity of the rehabilitation robot at time t-1, and Δt is the sampling period.

[0116] Assume that the training task in the embodiment of the present application is a task such as painting or drawing, and the task is implemented through a virtual reality device. Generally, the mass parameter M is set to 0.1 kg, the damping coefficient D is set to 0.1 k / s, and the spring coefficient K is set to 0 kg / s. 2 , so that the movement is neither too smooth nor too sticky, close to the feeling of drawing with a pen on paper, improving the realism and immersion of training tasks conducted through the virtual reality device.

[0117] It is necessary to make sure that the reference Figure 5 ,After determining the target terminal velocity, the terminal velocity is inversely calculated on the inverse kinematics model of the rehabilitation robot, the ,operation parameters of the rehabilitation robot are determined, and the rehabilitation robot is ,controlled to run with the operation parameters through the robot controller.

[0118] The rehabilitation robot includes two stepper motors, so the operating parameters are specifically the rotation angles of the two stepper motors.

[0119] The kinematic model of the rehabilitation robot is a model in which the speed of the robot's terminal end is determined by the rotation angle of the stepper motor. The inverse kinematic model of the rehabilitation robot is a model in which the rotation angle of the stepper motor is determined by the speed of the robot's terminal end.

[0120] It should be noted that the embodiment of the present application determines the training applied force, spring coefficient, applied force coefficient, and noise gain parameters of force noise, determines the dynamic equation of the robot controller, and then determines the target terminal speed and operating parameters of the rehabilitation robot, and controls the rehabilitation robot to operate with the operating parameters through the robot controller, thereby achieving precise control of the rehabilitation robot and improving the accuracy of rehabilitation training.

[0121] It is understandable that the rehabilitation training system also includes a virtual reality device, and the control module is also used for:

[0122] Get multiple input graphs.

[0123] Preprocessing is performed on multiple input graphics respectively to determine graphic trajectories corresponding to the input graphics.

[0124] For each graphic trajectory, the minimum jerk trajectory method is used to determine the optimal trajectory corresponding to the graphic trajectory, and the graphic complexity of the optimized trajectory is determined.

[0125] The target difficulty is determined based on the current display track of the virtual reality device and the training status.

[0126] The optimized trajectory whose graphics complexity matches the target difficulty is determined as the target display trajectory.

[0127] Control the virtual reality device to display the target display trajectory.

[0128] It should be noted that, refer to Figure 1 ,The rehabilitation training system also includes a virtual reality device which can be used to display ,rehabilitation training tasks. Compared with traditional training tasks, the virtual reality ,device is more convenient.

[0129] To facilitate rehabilitation training, the embodiment of the present application uses the line drawing task as a rehabilitation training task. The virtual reality device includes a head mounted device and a virtual reality controller. The head mounted device is worn on the head of the rehabilitation subject and can display the screen of the rehabilitation training task for the rehabilitation subject. The virtual reality controller is held by the rehabilitation subject and can perform the line drawing task on the screen displayed by the head mounted device through the virtual reality controller.

[0130] It should be noted that the input graphic may be a graphic obtained from a database, or may be any line drawing image uploaded by the object.

[0131] It should be noted that the graphic trajectory is a trajectory corresponding to the input image, which includes multiple trajectory lines.

[0132] Since the rehabilitation training task is a line drawing task, and the input graphics cannot meet the requirements of line drawing, it is necessary to preprocess the input image to obtain the graphic trajectory corresponding to the input image.

[0133] Reference Figure 6In the preprocessing process, the input image is first binarized to convert it into black and white, and then connectivity analysis is performed to identify connected areas in the input graph. Then the graph is skeleton extracted, that is, pixels outside the trajectory are iteratively removed until only the center line remains. On this basis, fitting and sampling are performed to restore a smoother curve or shape that is more consistent with the input graph, and the graph trajectory is obtained.

[0134] It should be noted that the purpose of the minimum jerk trajectory method is to minimize the rate of change of acceleration during the motion process, that is, the jerk. Then, by processing the graphic trajectory using the minimum jerk trajectory method, the time trajectory with the minimum jerk under the constraints of the graphic trajectory can be obtained. The minimum jerk trajectory method can be expressed as:

[0135]

[0136] Where J is the jerk, r is the graphic trajectory, s(t) is the optimized trajectory corresponding to the graphic trajectory, and the jerk corresponding to the optimized trajectory is the smallest, and T is the drawing time corresponding to the optimized trajectory. Usually, the drawing time corresponding to the optimized trajectory is the shortest time corresponding to drawing the graphic trajectory.

[0137] It should be noted that, refer to Figure 6 ,After determining the optimization trajectory, the graph complexity of the optimization trajectory is determined. The graph complexity also represents the difficulty of the rehabilitation training task. The higher the graph complexity, the greater the difficulty of the rehabilitation training task. Figure 6 The graphics complexity of the snail and pig in the game is obviously higher than that of the straight line and circle, so the corresponding rehabilitation training task will be more difficult.

[0138] It should be noted that the current display trajectory is the display trajectory corresponding to the rehabilitation training task that the rehabilitation subject is currently performing, and the target difficulty is the difficulty that needs to be adjusted for the rehabilitation training task.

[0139] The target difficulty is determined based on the current display track of the virtual reality device and the training status. If the training status is not good, the target difficulty is lower than the difficulty of the rehabilitation training task corresponding to the current display track. If the training status is good, the target difficulty is higher than the difficulty of the rehabilitation training task corresponding to the current display track.

[0140] Then, an optimized trajectory whose graphics complexity matches the target difficulty is determined as the target display trajectory, and the virtual reality device is controlled to display the target display trajectory.

[0141] Reference Figure 7, assuming that the current display trajectory is an apple, and its image complexity is 5.72. If the training status is poor, that is, the time taken by the rehabilitation subject to complete the current display trajectory is too long or the accuracy is low, then the target display trajectory is adjusted to a straight line with a graphic complexity of 2.68, or a circle with a graphic complexity of 3.94. If the training status is good, that is, the time taken by the rehabilitation subject to complete the current display trajectory is the drawing time corresponding to the minimum jerkiness trajectory and the accuracy is full marks, then the target display trajectory is adjusted to a snail with a graphic complexity of 7.25, or a bird with a graphic complexity of 7.73. If the training status is passing, the target difficulty can still be set to 5.72, or the target display trajectory can be adjusted to a banana with a graphic complexity of 5.69.

[0142] It should be noted that, in addition to force noise, the embodiment of the present application further adjusts the difficulty of the rehabilitation training task through image complexity. On the basis that the training task is a depiction task, the diversity of the task is enriched, and the task difficulty can be accurately adjusted through force noise and image complexity.

[0143] Reference Figure 7 ,The comprehensive difficulty of the rehabilitation training task is determined based on the image complexity and the force perturbation amplitude, i.e., the noise gain parameter. The comprehensive difficulty of the rehabilitation training task can be expressed as:

[0144] G=b1η LDJ +b2σ noise ,

[0145] Among them, G is the comprehensive difficulty of the rehabilitation training task, η LDJ is the image complexity, σ noise is the force perturbation amplitude, b1 is the impact factor of image complexity on the comprehensive difficulty of rehabilitation training tasks, and b2 is the impact factor of force perturbation amplitude on the comprehensive difficulty of rehabilitation training tasks. The larger the impact factor, the greater the impact on the comprehensive difficulty of rehabilitation training tasks.

[0146] It should be noted that the adjustment of graphic complexity is suitable for any rehabilitation training mode, while the adjustment of force noise is only suitable for the challenge mode. In other modes, the recovery effect of the rehabilitation subjects is not good, and it is not suitable to increase the force noise. The adjustment of graphic complexity can adjust the difficulty of the training task and realize continuous adjustment of the difficulty.

[0147] It is understood that the control module is also used to:

[0148] Based on the optimized trajectory, a time series corresponding to the optimized trajectory and a trajectory length of the optimized trajectory are determined.

[0149] Get the drawing speed function and drawing duration of the optimization trajectory from the time series.

[0150] Compute the second derivative of the plotted velocity function with respect to time.

[0151] Determine the logarithmic dimensionless jerk of the optimized trajectory based on the plotting duration, trajectory length, and second-order derivatives.

[0152] Based on the logarithmic dimensionless jerk, the graphical complexity of the optimized trajectory is determined.

[0153] It should be noted that the time series corresponds to the optimized trajectory, which includes the motion information of the optimized trajectory at each time point. Therefore, based on the time series, the drawing speed function and drawing duration of the optimized trajectory can be determined.

[0154] The drawing speed function refers to the function of the speed corresponding to the optimized trajectory at each time point. The drawing duration is the time required to draw the optimized trajectory.

[0155] In addition, the trajectory length is the total trajectory length of the optimized trajectory. Assuming that the optimized trajectory is a circle with a radius of 2 cm, the trajectory length is 4π cm.

[0156] The logarithmic dimensionless jerk of the optimized trajectory is calculated as:

[0157]

[0158] Among them, η LDJ is the logarithmic dimensionless jerk of the optimized trajectory, D is the drawing time of the optimized trajectory, S is the trajectory length of the optimized trajectory, v is the drawing speed function of the optimized trajectory, To plot the second derivative of velocity function with respect to time.

[0159] The logarithmic dimensionless jerk is positively correlated with the curvature of the optimized trajectory and is independent of the trajectory length. Therefore, the logarithmic dimensionless jerk can be used to measure the complexity of the trajectory. Figure 7 The images of the straight line, circle, banana, apple, snail, bird, etc. shown increase in complexity.

[0160] In addition, logarithmic dimensionless jerk is often used to measure the smoothness of a movement.

[0161] It should be noted that the embodiment of the present application measures the graphic complexity of the optimized trajectory by the dimensionless jerkiness of the object, quantifies the graphic complexity, and facilitates adjusting the difficulty of the rehabilitation training task by the graphic complexity.

[0162] It can be understood that the measurement module includes an eye tracking module, and the eye tracking module is arranged on the virtual reality device.

[0163] The control module is also used to:

[0164] Get the eye movement signal from the measurement signal.

[0165] The intention detection model is used to analyze the eye movement signals and obtain the gaze position of the rehabilitation subject.

[0166] Based on the gaze position, the training status of the rehabilitation subject is determined.

[0167] It should be noted that the eye tracking module is provided on the virtual reality device and can be used to measure the eye movement signals, blinking frequency, etc. of the rehabilitation subject.

[0168] The intention detection model is a model used to determine the gaze position of the rehabilitation subject based on the eye movement signal of the rehabilitation subject. The eye movement signal is input into the intention detection model to obtain the gaze position of the rehabilitation subject, and then the training state of the rehabilitation subject can be determined.

[0169] It should be noted that the embodiment of the present application uses eye movement signals to analyze the intention of the rehabilitation subject, which can more accurately determine the line of sight position of the rehabilitation subject and determine the training status of the rehabilitation subject.

[0170] It can be understood that the virtual reality device is used to display the measurement module and also includes a position detection module.

[0171] The control module is also used to:

[0172] A position detection signal is obtained from the measurement signal.

[0173] Based on the position detection signal, the object position of the rehabilitation object in the virtual reality device is determined.

[0174] When the rehabilitation training mode is the auxiliary mode, if the distance between the object position and the current displayed trajectory is greater than the preset distance threshold, the first target position is determined based on the line of sight position and the current displayed trajectory, and the spring coefficient is adjusted to control the rehabilitation robot through the robot controller to drive the rehabilitation object to move to the first target position.

[0175] It should be noted that the position detection module is used to detect the object position of the rehabilitation subject in the virtual reality device, that is, the pen tip position of the rehabilitation subject when performing the drawing task, and the pen tip position is the object position.

[0176] The auxiliary training mode is suitable for patients with mid-term stroke. At this time, the rehabilitation subjects can perform active training because their upper limbs have recovered some functions. However, due to the spasm of the upper limbs, the hands are prone to deviate from the trajectory, that is, the position of the object deviates from the current displayed trajectory corresponding to the rehabilitation training task. When the rehabilitation subject moves autonomously, the spring coefficient and noise gain parameters are set to 0, and the applied force coefficient is set to 1.

[0177] Reference Figure 8 and Fig. 9If the distance between the detected object position x(t) and the current displayed trajectory is greater than the preset distance threshold, the first target position x is determined based on the line of sight position and the current displayed trajectory. d (t). The first target position x d (t) is the point that the rehabilitation subject is expected to move to, and the first target position x d (t) is located on the current display trajectory. First, determine the point in the current display trajectory that is closest to the object position x(t), but the closest point is not necessarily the first target position x d (t), which may be a point that has been drawn. Therefore, the sight line position determined by the eye movement signal can be used to determine a point that is closer to the sight line position among the multiple closest points determined as the first target position x d (t). If multiple points are far from the sight line, the point closest to the sight line in the current displayed trajectory is taken as the first target position x d (t).

[0178] In order to correct the position of the rehabilitation object, the spring coefficient is adjusted so that the rehabilitation robot is controlled by the robot controller to drive the rehabilitation object to move toward the first target position.

[0179] The preset distance threshold can be set as needed, and can be specifically set according to the recovery status of the rehabilitation subject and the graphic complexity of the currently displayed trajectory.

[0180] It should be noted that the embodiment of the present application is suitable for subjects who need to recover some upper limb functions in the medium term by providing an auxiliary mode. When the rehabilitation subject deviates from the currently displayed trajectory, the object position of the rehabilitation subject can be corrected, thereby improving the rehabilitation training effect.

[0181] It is understood that the control module is also used to:

[0182] When the rehabilitation training mode is the passive mode, the applied force coefficient is set to 0.

[0183] Sets the spring coefficient based on a preset coefficient threshold.

[0184] A second target position is determined based on the tangent direction of the object position along the currently displayed trajectory.

[0185] The robot controller controls the rehabilitation robot to drive the rehabilitation object to move to the second target position.

[0186] It should be noted that the passive mode is suitable for subjects who have completely lost their upper limb motor function in the early stage. At this time, the rehabilitation subjects can only do passive traction training. Therefore, the applied force coefficient is set to 0.

[0187] Based on the preset coefficient threshold, the spring coefficient is set so that the spring coefficient is greater than the preset coefficient threshold. The preset coefficient threshold can be set according to the rehabilitation object and the rehabilitation robot, and it is necessary to satisfy that the rehabilitation robot can drive the rehabilitation object to move under the preset coefficient threshold.

[0188] Based on the object position and the current display trajectory, the current motion position is determined, that is, the object position is along the tangent direction of the current display trajectory, and the second target position is determined. The second target position refers to the target position where the rehabilitation robot drives the rehabilitation object to move. Assuming that the current display trajectory is a circle, the second target position is in the tangent direction of the circle. The tangent direction is simple and clear, and it is basically a linear motion. On the basis of meeting the rehabilitation training needs of the rehabilitation object, it can reduce the damage to the rehabilitation object caused by repeated turning and other actions due to overly complex patterns.

[0189] It should be noted that the embodiment of the present application is provided with a passive mode, which is suitable for subjects with complete loss of upper limb motor function in the early stage, thereby increasing the scope of application of the rehabilitation training system.

[0190] It is understood that the control module is also used to:

[0191] comparing the current display trajectory of the virtual reality device and the sight line position to obtain a comparison result;

[0192] When the comparison result indicates that the time for which the current displayed trajectory and the sight line position are continuously in a non-overlapping state is greater than a preset time threshold, the rehabilitation robot is controlled to stop running.

[0193] It should be noted that in order to reduce the distraction of the rehabilitation subjects during training or the occurrence of dangerous situations, if the rehabilitation subjects' line of sight deviates from the current display trajectory, the current display trajectory and the line of sight continue to be in a non-overlapping state, and the deviation lasts longer than the preset time threshold, the rehabilitation robot is controlled to stop running and a warning is issued.

[0194] The preset time threshold can be set as needed, that is, it can be set specifically according to the state of the rehabilitation subject.

[0195] It should be noted that the embodiment of the present application provides an emergency stop mechanism, that is, when the comparison result indicates that the current display trajectory and the line of sight position are continuously in a non-overlapping state for a time greater than a preset time threshold, the rehabilitation robot is controlled to stop running. This setting can improve the safety of the rehabilitation subject during rehabilitation training.

[0196] It should be noted that the rehabilitation training mode of the embodiment of the present application is also provided with an active mode. When the upper limb function of the rehabilitation subject recovers to a certain extent, unassisted active training can be performed, that is, autonomous training can be performed without any assistance. At this time, the spring coefficient is set to 0, the applied force coefficient is set to 1, and the noise gain parameter is set to 0.

[0197] It is understood that the control module is also used to:

[0198] Based on the measurement signals and the currently displayed trajectory, evaluation parameters of the rehabilitation subject are determined.

[0199] Control the virtual reality device to display the evaluation parameters.

[0200] It should be noted that after the rehabilitation training task is completed, that is, after the current display trajectory corresponding to the rehabilitation training task is drawn, the evaluation parameters of the rehabilitation object can be determined according to the measurement signal and the current display trajectory to quantify the training effect of the rehabilitation object.

[0201] The evaluation parameters of the rehabilitation subject may include speed, trajectory accuracy, movement fluency, movement completion efficiency, and force control ability. Speed ​​refers to the speed at which the rehabilitation subject draws the currently displayed trajectory, and trajectory accuracy refers to the overlap rate between the trajectory drawn by the rehabilitation subject and the currently displayed trajectory. Movement fluency refers to the smoothness of the movement of the rehabilitation subject when drawing the currently displayed trajectory. Movement completion efficiency refers to the efficiency of the movement of the rehabilitation subject in drawing the currently displayed trajectory, which can be determined based on speed and accuracy. Force control ability refers to the ability of the rehabilitation subject to control the force when drawing the currently displayed trajectory. Too much or too little force indicates poor force control ability.

[0202] After determining each evaluation parameter, the embodiment of the present application can draw a radar chart based on the evaluation parameters, that is, Figure 1 Therefore, the evaluation parameter needs to be normalized so that its value range is between 0 and 1. The larger the area enclosed by the five points of the radar chart determined based on the evaluation parameter, the higher the training effect of the rehabilitation object.

[0203] It should be noted that the embodiment of the present application quantifies the performance of the rehabilitation subject in the rehabilitation training task through evaluation parameters, provides personalized feedback for the rehabilitation subject, and can more accurately feedback the training effect of the rehabilitation subject.

[0204] It is understood that the control module is also used to:

[0205] Get the optimization parameters corresponding to the current displayed track.

[0206] Based on the measurement signals, training parameters for the rehabilitation subject are determined.

[0207] Based on the ratio of the training parameters to the optimized parameters, the evaluation parameters of the rehabilitation subject are determined.

[0208] It should be noted that the optimization parameter is the parameter corresponding to the currently displayed trajectory as the optimized trajectory. The training parameter is the parameter of the rehabilitation subject during the rehabilitation training process, which can be specifically determined according to the measurement signal. The evaluation parameter is determined based on the ratio of the training parameter and the optimization parameter, and can determine the training effect of the rehabilitation subject.

[0209] The speed of the rehabilitation object can be expressed as:

[0210]

[0211] Where Velocity is the velocity, a(i) is the object position at the i-th moment, a(i-1) is the object position at the i-1-th moment, I is the total number of points that the object position passes through the currently displayed trajectory, and Δt is the time step.

[0212] The normalized form of the velocity of the rehabilitation subject can be expressed as:

[0213]

[0214] Among them, Velocity actual is the actual speed, that is, the speed in the training parameters. ref is the reference speed, i.e. the speed in the optimization parameters.

[0215] The trajectory accuracy of the rehabilitation object first needs to calculate the average trajectory error, which is used to evaluate the accuracy of the motion trajectory corresponding to the training parameters. The average trajectory error can be expressed as:

[0216]

[0217] Among them, Error ave is the average error rate, N is the sequence length of the optimized trajectory corresponding to the current displayed trajectory, and D n is a set, which is represented by D n ={p k |p k (0) = n}, that is, D n Contains all p at time point n k , these points satisfy p k (0) = n. r(n) is the position coordinate point of the minimum jerk trajectory at time point n. a(p k (1)) is the trajectory position obtained by dynamic time planning, where p k (1) is the corresponding time point after time planning. And P is a set of paths, which is expressed as P = {p k ∈N 2 ,pk (0)∈[1,N],p k (1)∈[1,I],k=1,2,K,K},p k is a path point, p k (0) is the starting position of the path point in the time series, p k (1) is the end position of the path point in the time series, and K is the number of paths in the path set.

[0218] The normalized form of the trajectory accuracy of the rehabilitation subject is:

[0219]

[0220] Among them, Error actual is the average trajectory error in the training parameters, Error rref is the average trajectory error in the optimized parameters.

[0221] The formula for calculating the movement fluency of rehabilitation subjects is:

[0222]

[0223] Among them, v is the pen tip speed of the rehabilitation subject when drawing, T is the total duration of the trajectory movement, and S is the total length of the currently displayed trajectory.

[0224] The normalized form of the movement fluency of the rehabilitation subjects is:

[0225]

[0226] Among them, η ldj * is the logarithmic dimensionless jerk of the optimized trajectory corresponding to the current displayed trajectory, and is also the smoothness of the action in the optimization parameter, η ldj It is the logarithmic dimensionless jerkiness of the rehabilitation subject when drawing the current displayed trajectory, and is also the movement smoothness in the training parameters.

[0227] The calculation formula for the efficiency of movement completion of rehabilitation subjects is:

[0228]

[0229] Among them, PathLength actual is the actual motion, that is, the path length in the training parameters, PathLength theoretical is the path length in the optimization parameter, a(i) is the actual movement, that is, the coordinate point of the path during the rehabilitation training process, and r(n) is the coordinate point of the optimized trajectory corresponding to the current displayed trajectory.

[0230] The normalized form of the rehabilitation subject's movement completion efficiency is:

[0231]

[0232] The calculation formula for the force control ability of rehabilitation subjects is:

[0233]

[0234] FDE is the force control error, F(i) is the applied force of the rehabilitation object at time i, and X(i) is the tangent direction of the object position at time i along the currently displayed trajectory.

[0235] The normalized form of the force control ability of the rehabilitation subject is:

[0236]

[0237] It should be noted that the embodiment of the present application evaluates the training status of the rehabilitation subject through five aspects: speed, trajectory accuracy, movement fluency, movement completion efficiency, and force control ability, and uses the optimization parameters corresponding to the currently displayed trajectory as a measurement standard. This method can accurately reflect the training effect of the rehabilitation subject.

[0238] In addition, the embodiment of the present application proposes a rehabilitation training method, which is applied to a measurement module in a rehabilitation training system. The rehabilitation training system also includes a rehabilitation robot and a measurement module. The rehabilitation robot is connected to a robot controller. The rehabilitation training method includes:

[0239] Step S100: obtaining a preset rehabilitation training mode.

[0240] Step S200: adjusting the spring coefficient and applied force coefficient of the robot controller based on the rehabilitation training mode.

[0241] Step S300: Determine the training state of the rehabilitation subject based on the measurement signal from the measurement module.

[0242] Step S400: when the rehabilitation training mode is the challenge mode, force noise is added to the robot controller, and a noise gain parameter of the force noise is adjusted based on the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter.

[0243] The rehabilitation training method proposed in the present application is applied to the measurement module in the rehabilitation training system, and the rehabilitation training system also includes a rehabilitation robot and a measurement module. The rehabilitation robot is connected to the robot controller. By setting the spring coefficient and the applied force coefficient of the robot controller, the rehabilitation training mode can be adjusted to adapt to the training needs of stroke patients at different stages. In addition, when the rehabilitation training mode is the challenge mode, force noise is added to the robot controller to increase force disturbance for the rehabilitation object, and the noise gain parameter of the force noise is adjusted according to the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter, thereby realizing adaptive adjustment of the difficulty of the training task. This adjustment method can realize continuous adjustment of the difficulty of the training task according to the training state of the rehabilitation object, and can be applied to the same training task. The rehabilitation object does not need to re-adapt to the new training task, which reduces the rehabilitation training time and improves the rehabilitation training effect.

[0244] The specific implementation of the rehabilitation training method is substantially the same as the specific implementation of the above-mentioned rehabilitation training device, and will not be described in detail herein.

[0245] The embodiment of the present application also provides an electronic device, the electronic device includes a memory and a processor, the memory stores a computer program, and the processor implements the above-mentioned rehabilitation training method when executing the computer program. The electronic device can be any intelligent terminal including a tablet computer, a car computer, etc.

[0246] See also Fig.11 , Fig.11 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0247] The processor 901 can be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solution provided in the embodiments of the present application.

[0248] The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 902 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 902, and the processor 901 is called to execute the rehabilitation training method of the embodiment of this application.

[0249] The input / output interface 903 is used to implement information input and output.

[0250] The communication interface 904 is used to realize the communication interaction between this device and other devices. Communication can be realized through wired methods (such as USB, network cable, etc.) or wireless methods (such as mobile network, WI FI, Bluetooth, etc.).

[0251] The bus 905 transmits information between various components of the device (eg, the processor 901 , the memory 902 , the input / output interface 903 , and the communication interface 904 ).

[0252] The processor 901 , the memory 902 , the input / output interface 903 and the communication interface 904 are connected to each other in communication within the device via a bus 905 .

[0253] An embodiment of the present application further provides a computer-readable storage medium, which stores a computer program, and the computer program implements the above-mentioned rehabilitation training method when executed by a processor.

[0254] The memory, as a non-transient computer-readable storage medium, can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory may optionally include a memory remotely disposed relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0255] The rehabilitation training system, rehabilitation training method and related devices provided by the embodiments of the present application include a rehabilitation robot and a measurement module, and the rehabilitation robot is connected to a robot controller, and the robot controller is a damping-spring-mass system, and the damping-spring-mass system is convenient for adjusting the rehabilitation training mode by setting the spring coefficient and the applied force coefficient to adapt to the training needs of stroke patients at different stages. In addition, when the rehabilitation training mode is a challenge mode, force noise is added to the robot controller to increase force interference for the rehabilitation object, and the noise gain parameter of the force noise is adjusted according to the training state, so as to realize adaptive adjustment of the difficulty of the training task. This adjustment method can realize continuous adjustment of the difficulty of the training task according to the training state of the rehabilitation object, and can be applied to the same training task. The rehabilitation object does not need to re-adapt to the new training task, which reduces the rehabilitation training time and improves the rehabilitation training effect.

[0256] The embodiments described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Those skilled in the art will appreciate that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0257] Those skilled in the art will appreciate that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than shown in the figures, or a combination of certain steps, or different steps.

[0258] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0259] Those skilled in the art will appreciate that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices may be implemented as software, firmware, hardware, or a suitable combination thereof.

[0260] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0261] It should be understood that in the present application, "at least one (item)" means one or more, and "plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that three relationships may exist. For example, "A and / or B" can mean: only A exists, only B exists, and A and B exist at the same time, where A and B can be singular or plural. The character " / " generally indicates that the objects associated before and after are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, c can be single or multiple.

[0262] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0263] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0264] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0265] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including multiple instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory, referred to as RAM), disk or optical disk and other media that can store programs.

[0266] The preferred embodiments of the present invention are described above with reference to the accompanying drawings, but the scope of the rights of the present invention is not limited thereto. Any modification, equivalent substitution and improvement made by a person skilled in the art without departing from the scope and essence of the present invention should be within the scope of the rights of the present invention.

Claims

1. A rehabilitation training system, characterized in that: include: A rehabilitation robot, the rehabilitation robot being connected to a robot controller, and the rehabilitation robot being used to guide a rehabilitation subject to move; a measurement module, the measurement module being used to obtain a measurement signal of the rehabilitation subject; A control module, wherein the control module is connected to the robot controller and the measurement module respectively, and the control module is used for: Based on a preset rehabilitation training mode, adjusting a spring coefficient and an applied force coefficient of the robot controller; determining a training state of the rehabilitation subject based on the measurement signal; When the rehabilitation training mode is the challenge mode, force noise is added to the robot controller, and a noise gain parameter of the force noise is adjusted based on the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter.

2. The rehabilitation training system according to claim 1, characterized in that: The control module is also used for: acquiring the training applied force of the rehabilitation subject from the measurement signal; Determining a dynamic equation of the robot controller based on the training applied force, the spring coefficient, the applied force coefficient, and a noise gain parameter of the force noise; Discretizing the dynamic equation to determine the target terminal velocity of the rehabilitation robot; The target terminal velocity is inversely calculated using the inverse kinematics model of the rehabilitation robot to determine the operating parameters of the rehabilitation robot, so as to control the rehabilitation robot to operate with the operating parameters through the robot controller.

3. The rehabilitation training system according to claim 1, characterized in that: The rehabilitation training system also includes a virtual reality device, and the control module is further used for: Get multiple input graphics; Preprocessing the plurality of input graphics respectively to determine graphic trajectories corresponding to the input graphics; For each of the graphic trajectories, using a minimum jerk trajectory method to determine an optimized trajectory corresponding to the graphic trajectory, and determining the graphic complexity of the optimized trajectory; Determining a target difficulty based on the current display track of the virtual reality device and the training status; Determine an optimized trajectory whose graphic complexity matches the target difficulty as a target display trajectory; The virtual reality device is controlled to display the target display trajectory.

4. The rehabilitation training system according to claim 3, characterized in that: The control module is also used for: Based on the optimized trajectory, determining a time series corresponding to the optimized trajectory and a trajectory length of the optimized trajectory; Obtaining a drawing speed function and a drawing duration of the optimized trajectory from the time series; Calculating the second-order derivative of the drawing speed function with respect to time; Determining a logarithmic dimensionless jerk of the optimized trajectory based on the drawing duration, the trajectory length, and the second-order derivative; Based on the logarithmic dimensionless jerk, a graphical complexity of the optimized trajectory is determined.

5. The rehabilitation training system according to claim 3, characterized in that: The measurement module includes an eye tracking module, and the eye tracking module is arranged on the virtual reality device; The control module is also used for: obtaining an eye movement signal from the measurement signal; Analyzing the eye movement signal using an intention detection model to obtain the gaze position of the rehabilitation subject; Based on the line of sight position, a training state of the rehabilitation subject is determined.

6. The rehabilitation training system according to claim 5, characterized in that: The virtual reality device is used to display the measurement module and also includes a position detection module; The control module is also used for: acquiring a position detection signal from the measurement signal; determining an object position of the rehabilitation object in the virtual reality device based on the position detection signal; When the rehabilitation training mode is an auxiliary mode, if the distance between the object position and the current displayed trajectory is greater than a preset distance threshold, a first target position is determined based on the line of sight position and the current displayed trajectory, and the spring coefficient is adjusted to control the rehabilitation robot through the robot controller to drive the rehabilitation object to move to the first target position.

7. The rehabilitation training system according to claim 6, characterized in that: The control module is also used for: When the rehabilitation training mode is a passive mode, the applied force coefficient is set to 0; Setting the spring coefficient based on a preset coefficient threshold; Determining a second target position based on a tangent direction of the object position along the currently displayed trajectory; The robot controller is controlled to control the rehabilitation robot to drive the rehabilitation object to move toward the second target position.

8. The rehabilitation training system according to claim 5, characterized in that: The control module is also used for: Comparing the current display track of the virtual reality device with the sight line position to obtain a comparison result; When the comparison result indicates that the time for which the current display trajectory and the sight line position are continuously in a non-overlapping state is greater than a preset time threshold, the rehabilitation robot is controlled to stop running.

9. The rehabilitation training system according to claim 3, characterized in that: The control module is also used for: determining an evaluation parameter of the rehabilitation subject based on the measurement signal and the current displayed trajectory; The virtual reality device is controlled to display the evaluation parameters.

10. The rehabilitation training system according to claim 9, characterized in that: The control module is also used for: Obtaining optimization parameters corresponding to the current display trajectory; determining a training parameter for the rehabilitation subject based on the measurement signal; Based on the ratio of the training parameter to the optimization parameter, an evaluation parameter of the rehabilitation subject is determined.

11. A rehabilitation training method, characterized in that: A control module applied to a rehabilitation training system, wherein the rehabilitation training system further comprises a rehabilitation robot and a measurement module, wherein the rehabilitation robot is connected to a robot controller, and the rehabilitation training method comprises: Obtain preset rehabilitation training mode; Based on the rehabilitation training mode, adjusting the spring coefficient and the applied force coefficient of the robot controller; determining a training state of the rehabilitation subject based on a measurement signal from the measurement module; When the rehabilitation training mode is the challenge mode, force noise is added to the robot controller, and a noise gain parameter of the force noise is adjusted based on the training state, so as to adjust the force disturbance amplitude of the rehabilitation robot on the rehabilitation object through the noise gain parameter.

12. An electronic device, characterized in that: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the rehabilitation training method according to claim 11 when executing the computer program.

13. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the rehabilitation training method according to claim 11 is implemented.

Images