Rehabilitation robot motion state digital twin monitoring and dynamic compensation system

Abstract

The application belongs to the technical field of digital twinning, and discloses a rehabilitation robot motion state digital twinning monitoring and dynamic compensation system; the system acquires a patient limb surface deformation image and joint torque data through a multi-view depth camera, constructs a dynamic deformation field, filters a high stability deformation area based on deformation direction consistency and amplitude fluctuation analysis, extracts deformation characteristics and joint torque data to construct dynamic mechanical boundary conditions, and adopts a low-order finite element grid to update a digital twinning model in real time. The system calculates a deviation vector based on the digital twinning model, generates a dynamic compensation instruction in combination with impedance control parameters, and realizes accurate adjustment of a rehabilitation robot motion trajectory. The application enables the robot to respond to patient state changes in real time, and significantly improves the safety and effectiveness of rehabilitation training.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning, more particularly, the present application relates to a rehabilitation robot motion state digital twinning monitoring and dynamic compensation system. BACKGROUND

[0002] As an important means to assist patients in recovering motor function, rehabilitation robots have been widely used in the fields of neurological rehabilitation and orthopedic rehabilitation in recent years. With the deep integration of robotics technology and rehabilitation medicine, rehabilitation robots have developed from early passive assistive devices to interactive systems with certain intelligence. Currently, the rehabilitation robots used in clinical applications mainly include upper limb exoskeleton robots, lower limb gait training robots, and hand function rehabilitation robots, which help patients recover motor function by providing precise motion guidance and appropriate mechanical assistance.

[0003] In actual rehabilitation training, the muscles, skin and other soft tissues of the patient's limbs will undergo highly nonlinear and individualized deformation with movement, exhibiting complex mechanical properties such as strain rate dependence, anisotropy and viscoelasticity. These deformations not only affect the contact force distribution exerted by the patient on the robot, but also change the kinematic and dynamic characteristics of the limb. However, existing technologies still mainly rely on rigid body assumptions or simplified elastic models, which cannot accurately capture these soft tissue deformations. When a patient performs elbow joint flexion and extension training, the contraction and relaxation of the forearm muscle group will cause significant changes in local tissue stiffness. Traditional systems often apply inappropriate assistive forces due to their inability to monitor these changes in real time, resulting in discomfort for the patient and even secondary injury. In addition, existing digital twinning modeling methods either use overly simplified mass-spring models leading to insufficient accuracy, or use high-order nonlinear finite element models leading to high computational complexity. Solving a typical fine model of the whole limb requires several minutes or even hours, which is far from meeting the millisecond-level response requirements of real-time control in rehabilitation. Especially in the rehabilitation of stroke patients, muscle tension abnormalities and spasticity can change in an instant, and traditional models cannot provide real-time dynamic boundary condition updates, making it impossible for the robot to adjust the assistance strategy in a timely manner. This technical defect not only reduces the rehabilitation effect, but also may exacerbate the patient's psychological resistance.

[0004] In view of this, the present application proposes a rehabilitation robot motion state digital twinning monitoring and dynamic compensation system to solve the above problems. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, in order to achieve the above-mentioned purposes, the present application provides the following technical scheme: a rehabilitation robot motion state digital twinning monitoring and dynamic compensation system, comprising:

[0006] an acquisition module configured to acquire surface deformation images and joint torque data of a patient's limb at each time during the motion of a rehabilitation robot;

[0007] a deformation field construction module configured to construct a dynamic deformation field of soft tissue of a patient's limb according to deformation gradient distribution and local curvature variation among pixel points in the surface deformation image;

[0008] a stability analysis module configured to obtain deformation stability of each local region in the dynamic deformation field at each time according to deformation direction consistency and deformation amplitude fluctuation of the same local region in the dynamic deformation field at adjacent times in an analysis period; and filter out high-stability deformation regions based on the deformation stability;

[0009] a boundary condition module configured to construct dynamic mechanical boundary conditions of a digital twin model according to deformation characteristics of each high-stability deformation region in the dynamic deformation field at each time and corresponding joint torque data;

[0010] a model updating and compensation module configured to update a motion state of the digital twin model in real time based on the dynamic mechanical boundary conditions and a preset low-order finite element grid, and generate a dynamic compensation instruction of a rehabilitation robot motion trajectory according to the motion state;

[0011] The various modules are connected through wired and / or wireless means to realize data transmission between the modules.

[0012] The technical effects and advantages of the rehabilitation robot motion state digital twin monitoring and dynamic compensation system of the present application are as follows:

[0013] The present application realizes precise adaptation to individual differences of patients, changes the rehabilitation training from a "one-size-fits-all" mode to a truly personalized precise intervention, not only improves the training effect, but also greatly shortens the rehabilitation period. When performing functional training, muscle tension abnormalities and spasticity can be sensed in real time and trigger corresponding adjustments, effectively avoiding the secondary injury risk that may be caused by traditional systems, and further improving patient training compliance. The real-time response capability of the system makes the rehabilitation robot exhibit a "compliance" similar to that of a human therapist, which can intelligently adjust the assistance force and training difficulty when the patient is tired or uncomfortable, creating a safe and comfortable rehabilitation environment. Especially for patients with complex pathological conditions, such as patients with muscle tension disorders or involuntary movement, the system can adapt to their highly nonlinear and unpredictable motion characteristics, reducing the mechanical injury risk commonly seen in traditional rehabilitation. In addition, the accurate digital twin model generated by the system provides a quantitative evaluation and prognosis prediction tool for doctors, making up for the subjectivity of traditional evaluation methods. BRIEF DESCRIPTION OF DRAWINGS

[0014] Figure 1 The figure is a schematic diagram of the rehabilitation robot motion state digital twin monitoring and dynamic compensation system of the present application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0016] Please refer to Figure 1 The present application provides a rehabilitation robot motion state digital twin monitoring and dynamic compensation system, comprising:

[0017] The acquisition module is configured to acquire surface deformation images and joint torque data of a patient's limb at each time during the motion of the rehabilitation robot.

[0018] The deformation field construction module is configured to construct a dynamic deformation field of the soft tissue of the patient's limb according to the deformation gradient distribution and local curvature change between pixel points in the surface deformation images.

[0019] The stability analysis module is configured to obtain the deformation stability of each local region in the dynamic deformation field at each time according to the deformation direction consistency and deformation amplitude fluctuation of the same local region in the dynamic deformation field at adjacent times within an analysis period at each time, and to screen out high-stability deformation regions based on the deformation stability.

[0020] The boundary condition module is configured to construct dynamic mechanical boundary conditions of the digital twin model according to the deformation characteristics of each high-stability deformation region in the dynamic deformation field at each time and the corresponding joint torque data.

[0021] The model updating and compensation module is configured to update the motion state of the digital twin model in real time based on the dynamic mechanical boundary conditions and a pre-set low-order finite element mesh, and to generate a dynamic compensation instruction for the motion trajectory of the rehabilitation robot according to the motion state.

[0022] The various modules are connected through wired and / or wireless means to realize data transmission between the modules.

[0023] The present application captures the surface deformation images and joint torque data of the patient's limb in real time, constructs a dynamic deformation field to analyze the deformation characteristics of the soft tissue of the limb, screens out high-stability deformation regions as reliable observation points, constructs dynamic mechanical boundary conditions to drive the digital twin model to update, and generates a dynamic compensation instruction for the rehabilitation robot based on the motion state of the digital twin model, thereby realizing accurate adjustment of the motion trajectory of the robot during rehabilitation, effectively adapting to individual differences of patients and dynamic changes during rehabilitation, and improving the safety and effectiveness of rehabilitation training.

[0024] In an embodiment of the present invention, obtaining the deformation stability of each local area in the dynamic deformation field at each moment includes:

[0025] Track the deformation vectors of the pixels in the surface deformation image at all times, and obtain the deformation vector of each pixel in the surface deformation image at each moment;

[0026] Count the number of times the direction angle of the deformation vectors of the same local area in the dynamic deformation field at adjacent moments within the analysis period at each moment is less than the preset direction threshold, and record it as the deformation direction consistency of each local area in the dynamic deformation field at each moment;

[0027] Calculate the standard deviation of the amplitude of the deformation vector of the same local area in the dynamic deformation field at all moments within the analysis period at each moment as the deformation amplitude fluctuation of each local area in the dynamic deformation field at each moment;

[0028] The deformation direction consistency and the inverse of the deformation amplitude fluctuation are weightedly fused to obtain the deformation stability of each local area in the dynamic deformation field at each moment.

[0029] In the embodiment of the present invention, the "same local area" refers to a rectangular or circular area of ​​a preset size centered on a pixel point in the surface deformation image, and the specific size is determined according to the actual application requirements. For example, in this embodiment, the local area can be defined as a rectangular area with a side length of 10×10 pixels centered on a certain pixel point, or a circular area with a radius of 5 pixels. The same local area maintains a consistent spatial position in the dynamic deformation field at consecutive moments, that is, it corresponds through the spatial coordinates of the pixel points. The division of the local area covers the entire surface deformation image, ensuring that each pixel point belongs to at least one local area.

[0030] In this embodiment, the surface deformation images of the continuous time series are first analyzed by pixel tracking technology, the temporal motion trajectory of each pixel is calculated, and the deformation vector field at each moment is generated; the analysis period is usually set to 0.5-2 seconds, and the directional change characteristics of the deformation vectors of the same local area are counted within this time window; the directional angle between the deformation vectors of the same local area at adjacent moments is calculated, and a preset directional threshold (usually 15°-30°) is set; the number of times the directional angle is less than the preset threshold is counted, and the higher the value, the more stable the deformation direction of the area, which is recorded as Deformation direction consistency; at the same time, the standard deviation of the deformation vector amplitude of the local area during the analysis period is calculated. The smaller the value, the smaller the deformation amplitude fluctuation, which is recorded as deformation amplitude fluctuation. The deformation direction consistency and the inverse of the deformation amplitude fluctuation are combined through weighted fusion. The typical weighting coefficients are α=0.6 and β=0.4. The calculation formula is: deformation stability = α×deformation direction consistency + β×(1 / deformation amplitude fluctuation). The higher the deformation stability value, the more stable the deformation characteristics of the local area in continuous time, and the more suitable it is as a reliable observation point for subsequent analysis.

[0031] To further clarify the "deformation vector of the same local area" and its relationship to the deformation vector of the pixel point, in this embodiment, the deformation vector of the same local area refers to the set of deformation vectors of all pixels in the local area. Specifically, for a local area, after obtaining the deformation vector of each pixel point in the area, the direction angle and amplitude standard deviation of these deformation vectors are calculated. The direction angle is calculated as follows: for adjacent time points t and t+1, the deformation vectors of the i-th pixel point in the local area are v_i(t) and v_i(t+1) respectively;

[0032] Calculate the angle between two vectors , where · represents the vector dot product and |·| represents the vector modulus. s is the adjustment coefficient, a very small real number that ensures the denominator is non-zero. The number of times the included angle of all pixels in the local region is less than the preset directional threshold is counted as the deformation direction consistency. The amplitude standard deviation is calculated as follows: for all moments in the analysis period, the deformation vector amplitude of the i-th pixel in the local region is |v_i(t)|. The standard deviation of the deformation vector amplitudes of all pixels in the local region at all moments is calculated as the deformation amplitude fluctuation.

[0033] This implementation achieves precise identification of stable regions within a dynamic deformation field by comprehensively considering both the directional and amplitude stability of deformation. Compared to traditional methods that focus solely on deformation amplitude or analyze a single moment in time, this method captures the dynamic characteristics of deformation through time series analysis, improving the accuracy and robustness of deformation stability assessment and providing a reliable foundation for subsequent screening of highly stable deformation regions.

[0034] In an embodiment of the present invention, a method for screening a high-stability deformation region includes:

[0035] The deformation stability of each local area in the dynamic deformation field at each moment is sorted, and the local area with deformation stability greater than a preset stability threshold is selected as the candidate area;

[0036] The mean boundary curvature of each candidate region in the surface deformation image is calculated, and candidate regions with a mean boundary curvature greater than a preset curvature threshold are eliminated to obtain highly stable deformation regions.

[0037] In this embodiment, first, all local regions in the dynamic deformation field at each moment are sorted from high to low according to the deformation stability value; a preset stability threshold is set (typical value is 0.75-0.85, and the full score is 1), and local regions with deformation stability higher than the threshold are selected as preliminary candidate regions; boundary feature analysis is performed on each candidate region to extract its boundary contour in the surface deformation image; the local curvature distribution of the boundary contour is calculated, including calculating the local curvature of each point on the boundary and obtaining the mean curvature of the entire boundary; a preset curvature threshold is set (usually 0.08-0.15mm -1 ), and eliminate candidate areas with a mean boundary curvature greater than the threshold, because high curvature boundaries usually indicate complex or irregular regional shapes, which may lead to unstable calculations of mechanical properties; after double screening, the retained areas have both high deformation stability and good boundary shape characteristics, and are identified as high-stability deformation areas; these high-stability deformation areas will serve as key observation points for constructing the dynamic mechanical boundary conditions of the digital twin model.

[0038] In this embodiment, the deformation characteristics of the high stability deformation area include the deformation gradient tensor and the deformation velocity. Specifically, the deformation gradient tensor F1 is obtained by calculating the deformation displacement vectors of all pixels in the area. For the set of pixels in the high stability deformation area, the deformation displacement vector u(x) represents the displacement of the pixel in space, and the deformation gradient tensor F1 is defined as ,in is the Jacobian matrix of the displacement gradient, u(x,t) is the deformation displacement vector of pixel point x at time t, and for each pixel point x, the spatial derivative of the deformation displacement vector u(x,t) at time t is calculated to obtain I is the identity matrix. The deformation velocity v is calculated by the time difference of the deformation displacement vector at consecutive moments, that is, v = Δu / Δt, where Δu is the displacement difference between adjacent moments and Δt is the time interval.

[0039] The embodiment ensures that the selected region has stable deformation characteristics and suitable geometric characteristics for mechanical analysis through the double screening mechanism of deformation stability and boundary curvature. Compared with the traditional method which only relies on a single index, the method significantly improves the reliability and applicability of the screening results, avoids the numerical calculation instability problem caused by irregular boundary regions, and provides high-quality observation regions for the construction of subsequent dynamic mechanical boundary conditions.

[0040] In the embodiment of the application, the method for constructing dynamic mechanical boundary conditions of a digital twin model comprises:

[0041] Extract deformation characteristics of each high-stability deformation region in the dynamic deformation field at each time, and the deformation characteristics include a deformation gradient tensor and a deformation velocity;

[0042] According to the deformation gradient tensor and the deformation velocity, an equivalent stiffness coefficient of each high-stability deformation region is calculated;

[0043] According to the joint torque data, a torque distribution vector corresponding to each high-stability deformation region is obtained;

[0044] The equivalent stiffness coefficient and the torque distribution vector are mapped by a matrix to obtain dynamic mechanical boundary conditions of the corresponding high-stability deformation region.

[0045] In the embodiment, first, key deformation characteristics of each high-stability deformation region in the dynamic deformation field are extracted; the deformation characteristics mainly include a deformation gradient tensor (describing the direction and amplitude of local deformation) and a deformation velocity (describing the time rate of deformation); the deformation gradient tensor F1 is obtained by calculating the spatial derivative of the displacement field; the deformation velocity v is calculated by the time difference of the displacement field at consecutive time points; based on the continuum mechanics theory, an stress-strain relationship is established by using the hyperelastic model such as Neo-Hookean or Mooney-Rivlin, in combination with the deformation gradient tensor and the deformation velocity; by least square fitting or neural network regression, an equivalent stiffness coefficient K of each high-stability deformation region is calculated, and the coefficient reflects the mechanical properties of the local tissue; at the same time, according to the joint torque data M measured by the sensor, in combination with the robot kinematics model and the human biomechanics model, a decomposition vector of the torque in each spatial direction is calculated; a mapping relationship between the high-stability deformation region and the joint torque is established to obtain a torque distribution vector T_m corresponding to each region; finally, the equivalent stiffness coefficient K and the torque distribution vector T_m are mapped by matrix operation to generate dynamic mechanical boundary conditions in the form of B=K·T_m; these boundary conditions include displacement constraints, force constraints or mixed constraints, and completely describe the relationship between tissue deformation and external force.

[0046] In this embodiment, based on the Neo-Hookean hyperelastic model, the relationship between the stress tensor σ and the deformation gradient tensor F1 is σ=λtr(E)I+2μE, where E is the Green-Lagrange strain tensor, , λ and μ are Lamé constants, tr represents the matrix trace, and T is the transpose of the matrix or vector. The damping effect is introduced by the deformation velocity v, and the damping stress σ_d = η·v, where η is the damping coefficient. The stress tensor σ and the damping stress σ_d are superimposed to obtain the total stress σ_total = σ + σ_d. The equivalent stiffness coefficient K is obtained by fitting the linear relationship between the total stress and the deformation gradient tensor using the least squares method.

[0047] It needs to be explained that in actual applications, the deformation of the patient's limb soft tissue during rehabilitation training is usually small (i.e., F1 is close to the unit matrix I, and E is small).

[0048] Therefore, the complex nonlinear stress-strain relationship is approximated as a linear relationship:

[0049] σtotal≈K·some deformation; the “some deformation” here needs to be associated with the deformation gradient tensor F1 and the deformation velocity v.

[0050] Specifically, an equivalent deformation D1 is defined such that σtotal ≈ K·D1 (equivalent to a certain deformation mentioned above); D1 here comprehensively considers the deformation gradient tensor F1 and the deformation velocity v;

[0051] Specifically, based on F1, the equivalent strain ε_eq= , represents the magnitude of deformation; extract the equivalent velocity from v , which represents the amplitude of the velocity; the equivalent deformation D1=α1·ε_eq+β1·v_eq is obtained comprehensively, where α1 and β1 are weighting coefficients used to balance the contributions of elastic effect and damping effect. The typical values ​​are α1=0.7 and β1=0.3.

[0052] By using the least squares method to solve K, the error between σtotal and K·D1 is minimized; thus, the equivalent stiffness coefficient K is obtained.

[0053] The obtained K is a scalar that represents the equivalent stiffness characteristics of the high-stability deformation region. It integrates the elastic stiffness (determined by F and the Neo-Hookean model) and the damping stiffness (determined by v and the damping coefficient η), reflecting the comprehensive mechanical behavior of this region in dynamic deformation.

[0054] To further clarify the physical meaning of B = K·T_m and the specific content of the dynamic mechanical boundary condition, in this embodiment, B represents the dynamic mechanical boundary condition vector, and the physical meaning thereof is the mechanical response of the high-stability deformation region under the action of an external force, including displacement constraint, force constraint or mixed constraint. K is an equivalent stiffness coefficient, T_m is a moment distribution vector, and B = K·T_m represents that the moment distribution is mapped to the mechanical constraint at the boundary through the stiffness characteristics. Specifically, the displacement constraint is represented by the displacement value of the boundary node, the force constraint is represented by the external force value of the boundary node, and the mixed constraint is represented by the combination of displacement and external force. The decomposition of the moment distribution vector T_m in each spatial direction is realized through the robot kinematics model, that is, T_m = [T_mx, T_my, T_mz] T where T_mx, T_my, and T_mz are the components of the moment in the x, y, and z directions, respectively. The dynamic mechanical boundary condition B in different spatial directions is represented by B = [B_x, B_y, B_z] T where each component corresponds to the mechanical constraint in the corresponding direction.

[0055] In this embodiment, the mechanical characteristics of the high-stability deformation region are extracted, and the actual joint moment data are combined to establish accurate dynamic mechanical boundary conditions. Compared with the limitations of the traditional method using simplified boundary assumptions or empirical parameters, the boundary conditions constructed based on actual observation data in this method are more close to the real mechanical behavior of human tissues, and can accurately reflect individual differences and dynamic change characteristics, providing reliable driving conditions for high-precision updating of the digital twin model.

[0056] In the embodiment of the application, based on the dynamic mechanical boundary condition and the preset low-order finite element grid, the motion state of the digital twin model is updated in real time, including:

[0057] A preset low-order finite element grid is constructed, and the low-order finite element grid includes adaptive grid elements divided based on the high-stability deformation region;

[0058] The dynamic mechanical boundary condition is mapped to the boundary nodes of the low-order finite element grid to generate boundary constraint equations;

[0059] The stress distribution and displacement distribution of the low-order finite element grid are obtained by iteratively solving the boundary constraint equations, and the motion state of the digital twin model is updated.

[0060] In this embodiment, first, a preset low-order finite element grid is constructed, and low-order element types such as tetrahedral elements (for volumetric deformation analysis) or shell elements (for surface analysis) are used; the grid density is higher near the high-stability deformation area, and relatively sparse away from these areas, forming an adaptive grid structure; the use of low-order elements (such as linear tetrahedron, linear hexahedron, etc.) reduces the computational complexity while maintaining sufficient simulation accuracy, and is particularly suitable for real-time calculation requirements; the dynamic mechanical boundary conditions are mapped to the corresponding boundary nodes of the finite element grid, including converting displacement constraints, force constraints or mixed constraints into boundary conditions on the nodes; for displacement boundary conditions, the displacement value of the node is directly specified; for force boundary conditions, the force is converted into a node force; for mixed boundary conditions, the punishment method or Lagrange multiplier method is used for processing; the boundary constraint equation is established, which is in the form of K1·U=F2, where K1 is the stiffness matrix, U is the node displacement vector, and F2 is the node force vector; considering the nonlinear characteristics of human soft tissue, Newton-Raphson and other iterative methods are used to solve the boundary constraint equation; in each iteration, the tangent stiffness matrix is updated and the residual is calculated until convergence; the complete displacement field and stress field on the finite element grid are obtained by solving; the displacement field describes the geometric characteristics of tissue deformation, and the stress field reflects the mechanical state inside the tissue; the motion state of the digital twin model is updated according to the calculation results, including complete information such as the posture of the limb, the angle of the joint, and the deformation of the soft tissue; the entire calculation process is optimized for real-time performance, and a complete update can usually be completed within 50-100ms.

[0061] In this embodiment, the node displacement vector U represents the displacement of each node in the finite element grid, and its initial value is directly specified by the displacement constraint in the dynamic mechanical boundary condition B, or is updated step by step by iterative solving. The node force vector F2 represents the external force acting on each node, and its value is directly specified by the force constraint in the dynamic mechanical boundary condition B, or is calculated by interpolation of the moment distribution vector T_m on the grid nodes. Specifically, the moment distribution vector T_m is decomposed into force components in the spatial direction through the robot kinematics model, and is distributed to the boundary nodes through the interpolation method to form the node force vector F2. The stiffness matrix K1 is expanded from the equivalent stiffness coefficient K, specifically by assembling the stiffness characteristics of each grid element through the finite element method to obtain the global stiffness matrix K1.

[0062] In this embodiment, Newton-Raphson iterative method is used to solve the boundary constraint equation K1 U = F2. The specific steps are: (1) initialize the node displacement vector U_0, usually set to zero vector or based on the displacement value at the last time; (2) calculate the residual vector R = F2 - K1 U_0, the residual vector R represents the error between the current solution and the actual constraint; (3) calculate the tangent stiffness matrix K_t, the tangent stiffness matrix K_t is the linearization approximation of the stiffness matrix K1 at the current displacement U_0, which is usually calculated by numerical method; (4) solve the linear equation K_t Delta U = R, get the displacement increment Delta U;

[0063] (5) update the displacement vector U_1 = U_0 + Delta U; (6) repeat steps (2)-(5) until the modulus of the residual vector R is less than the preset convergence threshold (typical value is 10 -6 ), that is, the iteration is considered to be converged.

[0064] In this embodiment, the displacement distribution is directly used to update the posture of the limb and the deformation of the soft tissue in the digital twin model, that is, the coordinates of each node in the model are adjusted through the displacement vector U to reflect the geometric change of the limb; the stress distribution is used to update the angle of the joint, that is, the moment change at the joint is calculated through the stress distribution, and the adjustment amount of the joint angle is back calculated combined with the kinematic model of the robot, so as to update the joint state of the digital twin model.

[0065] It should be noted that the equivalent stiffness coefficient K is a scalar, representing the local stiffness characteristics of the high stability deformation region; the stiffness matrix K1 is a matrix, representing the global stiffness characteristics of the finite element mesh, which is assembled by the local stiffness coefficients of each mesh element.

[0066] This embodiment realizes real-time updating of the digital twin model through low-order finite element mesh and efficient solving algorithm. Compared with the limitation of complex calculation and slow updating of the traditional high-order finite element method, this method significantly improves the calculation efficiency under the premise of ensuring the accuracy, and meets the strict requirements of real-time of the rehabilitation robot control. The adaptive mesh strategy and the boundary condition mapping mechanism further improve the fine description ability of the model to the key area, and ensure that the digital twin model can accurately reflect the real motion state of the patient's limb.

[0067] In the embodiment of the application, the dynamic compensation instruction for generating the motion trajectory of the rehabilitation robot according to the motion state comprises:

[0068] According to the motion state of the digital twin model, the deviation vector between the expected pose and the actual pose of the end effector of the rehabilitation robot is calculated;

[0069] According to the deviation vector and the preset impedance control parameter, the dynamic compensation instruction for generating the motion trajectory of the rehabilitation robot is generated;

[0070] The driving joint angle of the rehabilitation robot is adjusted by a dynamic compensation instruction to realize real-time compensation of the motion trajectory.

[0071] In this embodiment, first, the real motion state of the patient's limb is obtained through the digital twin model, including joint position, soft tissue deformation, etc.; based on the human biomechanical model and the rehabilitation task requirements, the ideal expected pose of the end effector (such as a manipulator or a bandage) of the rehabilitation robot is calculated; at the same time, the actual pose of the end effector is obtained through the forward kinematics of the robot and sensor feedback; the deviation vector Δx between the expected pose and the actual pose is calculated, including position deviation and attitude deviation; the preset impedance control parameters are set, including the impedance stiffness matrix K2 (usually a diagonal matrix, corresponding to the stiffness coefficients in different directions), the damping matrix D and the inertia matrix M; based on the impedance control model F = K2 × Δx + D × Δx1 + M × Δx2, the compensation force F to be applied is calculated, where Δx1 and Δx2 are the first and second derivatives of the deviation, respectively; the compensation force F is mapped back to the joint space through the Jacobian matrix J of the robot, and the required joint torque τ = J T ·F is calculated; according to the joint torque and the robot dynamics model, the adjustment amount Δθ of the joint angle is calculated; a formatted dynamic compensation instruction is generated, containing control parameters such as the target angle, angular velocity and acceleration of each driving joint; the dynamic compensation instruction is executed by the robot's bottom controller to adjust the robot's motion trajectory in real time; the compensation process is usually completed within 10-30 ms, ensuring real-time following and adaptation to the patient's motion.

[0072] In this embodiment, the adjustment amount Δθ of the joint angle is calculated through the robot dynamics model, specifically:

[0073] τ = M(θ)·Δθ2 + C(θ,θ1)·Δθ1 + G(θ), where τ is the joint torque vector, representing the torque acting on each joint of the robot, whose value is the joint torque calculated by the impedance control model, Δθ2 is the joint angle acceleration vector, representing the acceleration of each joint angle, whose value is the unknown to be solved, obtained by solving the equation; M(θ) is the inertia matrix, representing the inertia characteristics of the robot joints, calculated by the robot dynamics model, dependent on the current joint angle θ; Δθ1 is the joint angle velocity vector, representing the velocity of each joint angle; C(θ,θ1) is the Coriolis force and centrifugal force matrix, representing the forces generated due to velocity coupling in the robot motion, dependent on the current joint angle θ and joint angular velocity θ1; G(θ) is the gravity term, representing the torque of the robot joints affected by gravity.

[0074] By solving the equation (such as Newton-Euler method or Lagrange method), the joint angle adjustment amount Δθ is obtained;

[0075] In actual solving, the joint torque τ is a known quantity calculated by the impedance control model; M(θ), C(θ, θ1), G(θ) are known matrices or vectors calculated by the robot dynamics model, which depend on the current joint angle θ and the joint angle velocity vector Δθ1.

[0076] Δθ1 is the current joint velocity, usually provided by the system state (or sensor measurement). The initial Δθ1 is known, and the subsequent Δθ1 is updated by numerical integration.

[0077] Therefore, the only unknown quantity in the equation is Δθ2 (joint angle acceleration vector), which can be directly solved by linear algebra method:

[0078] ;

[0079] The relationship from Δθ2 to Δθ can be established by numerical integration:

[0080] Joint velocity update: Δθ1(t+Δt)=Δθ1(t)+Δθ2(t)·Δt;

[0081] Joint angle update: Δθ(t+Δt)=Δθ(t)+Δθ1(t)·Δt;

[0082] Where Δt is the time step, Δθ(t) is the joint angle adjustment at time t, Δθ1(t) is the joint angle velocity vector at time t, Δθ2(t) is the joint angle acceleration vector at time t, Δθ(t+Δt) is the joint angle adjustment at time t+Δt, Δθ1(t+Δt) is the joint angle velocity vector at time t+Δt.

[0083] The target angle of each driven joint θ_target=θ+Δθ, where θ is the current joint angle; the target velocity θ1_target and the target acceleration θ2_target are calculated by the first and second time derivatives of Δθ, respectively.

[0084] It should be noted that the impedance stiffness matrix K2 is a matrix in the impedance control parameters, representing the stiffness characteristics of the robot end effector, used to control the size of the compensation force.

[0085] The embodiment realizes dynamic compensation of the rehabilitation robot motion trajectory based on the digital twin model impedance control strategy. Compared with the rigidity of traditional fixed trajectory control and the limitation of pre-defined trajectory library, this method can dynamically adjust the robot behavior according to the real-time state of the patient, and provide personalized rehabilitation assistance. The impedance control mechanism makes the robot show appropriate "flexibility", which can guide the patient to complete the standard action, and also adapt to the movement ability and comfort needs of the patient, significantly improving the safety and effectiveness of rehabilitation training.

[0086] In the embodiment of the present application, the method for constructing the dynamic deformation field comprises:

[0087] performing feature point matching on the pixel points in the surface deformation image to obtain a deformation displacement vector of each pixel point;

[0088] calculating a deformation gradient tensor between any two pixel points in the surface deformation image according to the deformation displacement vector;

[0089] constructing a dynamic deformation field at the corresponding moment according to the deformation gradient tensor and the local curvature variation of the pixel points in the surface deformation image.

[0090] In the embodiment, first, the surface deformation images at continuous moments are processed by computer vision algorithms to identify and track the feature points in the images; stable feature points in the surface deformation images are extracted by using SIFT, SURF or ORB feature descriptor methods; a pixel-level correspondence is established between the continuous frames by applying feature matching algorithms such as KLT (Kanade-Lucas-Tomasi) optical flow method or description-based matching method; the displacement difference between each matching point pair is calculated to generate a dense deformation displacement vector field; for the sparse areas in the deformation displacement vector field, methods such as bilinear interpolation or radial basis function (RBF) interpolation are used for filling to ensure the continuity of the deformation field; the deformation gradient tensor F1 between any two adjacent pixel points in the surface deformation image is calculated according to the obtained deformation displacement vector; at the same time, the local curvature variation of each pixel point in the surface deformation image is calculated, including principal curvature, mean curvature and Gaussian curvature and other features; the local curvature variation reflects the local variation characteristics of the surface shape, providing additional geometric constraints for the deformation field; the deformation gradient tensor and the local curvature variation information are fused to construct a complete dynamic deformation field; the dynamic deformation field is represented by a tensor field, and each spatial point contains complete deformation information including displacement, strain, velocity and other dimensions; the update frequency of the deformation field is synchronized with the image acquisition frequency, which is usually 25-30 Hz, ensuring that the transient changes in the limb movement are captured.

[0091] The embodiment constructs a complete dynamic deformation field describing the deformation of the soft tissue of the patient's limb by high-precision feature point matching and deformation gradient calculation combined with local curvature analysis. Compared with the limitations of traditional methods that only focus on the surface contour or joint position, the present method captures the detailed features of soft tissue deformation, providing a rich information foundation for subsequent deformation stability analysis and high-stability region screening. The dynamic deformation field serves as a bridge connecting image data and mechanical models, enabling the system to infer the mechanical state inside the tissue from visual observation, providing key support for the construction of a digital twin model.

[0092] The adaptive mesh element division method of the low-order finite element grid in the embodiment of the application comprises the following steps:

[0093] An initial mesh element is generated according to the boundary shape of the high-stability deformation region;

[0094] A deformation gradient mean value of each initial mesh element is calculated, and the deformation gradient mean value is recorded as the deformation complexity of the mesh element.

[0095] The initial mesh element with the deformation complexity greater than a preset complexity threshold is subjected to secondary subdivision to obtain an adaptive mesh element.

[0096] In the embodiment, first, an initial mesh element is generated according to the boundary shape of the identified high-stability deformation region by using a Delaunay triangle partitioning or tetrahedron partitioning algorithm; the initial mesh maintains a relatively uniform element size and shape quality, and generally adopts a tetrahedron or hexahedron element; for each initial mesh element, deformation gradient data of the coverage region of the element is extracted from a dynamic deformation field; a mean value of the deformation gradient tensor in the element is calculated, and the mean value reflects the complexity of the deformation of the region; the calculation of the deformation gradient mean value considers all components of the tensor, and generally uses a Frobenius norm or an eigenvalue analysis method; the calculated deformation gradient mean value is defined as the deformation complexity of the mesh element, and the higher the deformation complexity, the more complex the deformation of the region; a preset complexity threshold (a typical value is 0.15-0.25) is set, and the threshold is dynamically adjusted according to application requirements and computing resources; the adaptive subdivision strategy is applied to the initial mesh element with the deformation complexity greater than the preset threshold; the subdivision method includes uniform subdivision (uniformly dividing one element into multiple sub-elements) and non-uniform subdivision (directional subdivision according to the gradient direction); generally, secondary subdivision is adopted, that is, the original element is divided into 8 (tetrahedron) or 27 (hexahedron) sub-elements; for a particularly complex region, multi-level subdivision can be performed, but generally not more than three levels, to balance the accuracy and computing efficiency; the mesh elements after the subdivision are dense in the high-deformation-complexity region and sparse in the low-deformation-complexity region, forming an adaptive mesh structure; the number of adaptive mesh elements generated finally is generally controlled to be 5,000-20,000, ensuring real-time computing performance.

[0097] In the embodiment, the boundary shape of the high-stability deformation region is determined by the following steps: (1) extracting boundary pixel points of the high-stability deformation region in a surface deformation image, the boundary pixel points being the demarcation points between the pixel points in the region and the pixel points outside the region; (2) performing curve fitting on the boundary pixel points to generate a continuous boundary contour curve, and generally adopting a B-spline curve or a polynomial curve; and (3) the boundary shape is a geometric description of the boundary contour curve, including curvature, length and direction and the like.

[0098] In this embodiment, the mean deformation gradient of the initial mesh element is calculated by the following steps:

[0099] (1) Determine the set of pixel points covered by the mesh element; Specifically, the initial mesh element is divided based on the geometric shape of the surface deformation image at time t, and is generated by the Delaunay triangulation or tetrahedral partitioning algorithm. The set of pixel points covered by each mesh element refers to all pixel points in the projection area of the element in the surface deformation image.

[0100] (2) For each pixel point in the set, obtain its deformation displacement vector u(x); It should be noted that the deformation displacement vector u(x) is not directly calculated when the mesh element is divided, but is calculated in advance in the dynamic deformation field construction process. Specifically, the dynamic deformation field is calculated by the surface deformation image at consecutive time points, using feature point matching and pixel point tracking algorithm to obtain the deformation displacement vector field u1(x). In the dynamic deformation field, the deformation displacement vector u(x, t) of each pixel point x at time t represents the displacement difference of the pixel point from the reference state (usually the initial time t_0) to the current time t, that is, u(x, t) = x(t) - x(t_0), where x(t) and x(t_0) are the spatial coordinates of the pixel point at time t and t_0, respectively. By feature matching algorithm (such as KLT optical flow method or pixel point matching algorithm based on deep learning), the pixel-level correspondence between consecutive frames is established, and the displacement difference between each matching point pair is calculated, thereby generating a dense deformation displacement vector field u1(x). Therefore, when calculating the mean deformation gradient of the initial mesh element, the deformation displacement vector u(x, t) at time t is directly extracted from the dynamic deformation field.

[0101] (3) Calculate the deformation gradient tensor , where is the Jacobian matrix of the displacement gradient; Specifically, for each pixel point x in the set of pixel points covered by the mesh element, the spatial derivative of its deformation displacement vector u(x, t) at time t is calculated, thereby obtaining .

[0102] (4) Take the average of the deformation gradient tensors F1 of all pixel points in the mesh element to obtain the mean deformation gradient, which is usually represented using the Frobenius norm.

[0103] This embodiment achieves efficient allocation of computing resources through an adaptive mesh subdivision strategy based on deformation complexity. Compared to the redundant calculations of uniform meshes or the subjectivity of empirical subdivision, this method automatically adjusts the mesh density based on the deformation characteristics, providing high-precision expression in key areas while maintaining computational simplicity in less important areas. This adaptive mesh strategy significantly improves the balance between accuracy and efficiency of numerical simulations, ensuring maximum simulation results with limited computing resources and meeting the requirements of real-time updates of digital twin models.

[0104] In an embodiment of the present invention, a deformation vector tracking method includes:

[0105] A pixel matching algorithm based on deep learning is used to extract features from pixels in the surface deformation image and obtain the feature descriptor of each pixel.

[0106] According to the feature descriptor, the matching probability of the same pixel in the surface deformation image at adjacent moments is calculated;

[0107] According to the matching probability, a deformation vector is generated for each pixel.

[0108] In this embodiment, a deep learning method is first used to extract features and match pixels of the surface deformation image; a pre-trained convolutional neural network (CNN) such as ResNet, VGG or a specially designed U-Net is used as a feature extractor; a feature descriptor is extracted for each pixel in the image, and the descriptor dimension is usually 128-256, which includes the texture, gradient and semantic features of the area around the point; the feature descriptor has rotation invariance, scale invariance and partial illumination invariance, ensuring that stable features can be maintained during the deformation process; for two frames of surface deformation images at consecutive moments, the similarity between the feature descriptors of each pixel is calculated, and commonly used similarity metrics include cosine similarity or L2 distance ; Establish a feature descriptor matching matrix between the two frames of images, where each element in the matrix represents the matching probability of the corresponding pixel pair; use the matching probability as the weight, combined with the local spatial consistency constraint and the temporal continuity constraint, to optimize the pixel correspondence relationship; optimization methods include graph cut algorithm, Markov random field (MRF) or variational inference; for pixel pairs with a matching probability higher than a threshold (usually 0.7-0.8), calculate the position difference between them to form a pixel-level deformation vector; for low matching probability or many-to-one matching, use the information of the surrounding high-confidence matching points for interpolation or inference; finally generate a complete deformation vector field that covers all pixels in the image, and each vector contains displacement direction and amplitude information.

[0109] In this embodiment, the matching probability P is obtained by normalizing the feature descriptor similarity S. Specifically, for the feature descriptors f_i and f_j of pixel points i and j, the similarity S(i, j) = cos(f_i, f_j), where cos represents cosine similarity; ... , the denominator represents the sum of all possible matching pixel points j, and the probability distribution is obtained after normalization.

[0110] This embodiment achieves high-precision pixel matching and deformation vector tracking through deep learning technology. Compared to the limitations of traditional feature point methods or optical flow methods, deep learning-based methods can extract richer semantic features and contextual information, improving tracking accuracy under conditions of complex textures, large deformations, and varying illumination. High-quality deformation vectors are the foundation of deformation stability analysis, directly affecting the reliability of subsequent analysis results and providing a stable data input source for the system.

[0111] In an embodiment of the present invention, a method for acquiring a surface deformation image includes:

[0112] The multi-view depth camera installed on the rehabilitation robot collects 3D point cloud data of the patient's limbs during movement.

[0113] Surface reconstruction is performed on the three-dimensional point cloud data to generate a surface deformation image of the patient's limb.

[0114] In this embodiment, first install multiple depth cameras at appropriate positions of the rehabilitation robot to form a multi-view observation system; usually configure 3-5 depth cameras to cover each key angle of the patient's limbs during rehabilitation training; use depth cameras with infrared structured light (such as Kinect), time-of-flight (ToF), or binocular stereo vision technology, with a resolution of not less than 640x480 and a depth accuracy of millimeter level; set the camera acquisition frequency to 30-60 Hz to ensure capturing transient changes in rapid motion; strictly calibrate and synchronize the multiple depth cameras in space and time to establish a unified world coordinate system; collect the original depth images and RGB images of the patient's limbs during rehabilitation movement; extract three-dimensional point cloud data from the depth images, each point containing (x, y, z) spatial coordinates and corresponding color information; register and fuse point cloud data from different angles using algorithms such as Iterative Closest Point (ICP) or feature matching; remove noise points, outliers, and overlapping redundant points in the point cloud to improve data quality; based on the simplified point cloud data, use Poisson surface reconstruction, Moving Least Squares (MLS), or implicit function methods for surface reconstruction; the reconstructed surface model is usually represented by triangular mesh or NURBS surface; project the surface model to a 2D plane to generate a surface deformation image containing depth information; the surface deformation image contains rich information such as spatial coordinates, normal vectors, and curvature of each pixel point; for subsequent analysis, organize the surface deformation image into a time series data structure, retaining complete timestamp and camera parameter information.

[0115] This embodiment realizes comprehensive capture of patient limb surface deformation through multi-view depth cameras and high-precision surface reconstruction technology. Compared with the blind area problem of single-view observation and the information loss of two-dimensional images, the multi-view three-dimensional reconstruction method provides complete spatial deformation information, overcoming the limitations of traditional methods in limb self-occlusion and complex posture. High-quality surface deformation images provide a reliable data foundation for subsequent dynamic deformation field construction and deformation analysis, and are an important input source for the entire system.

[0116] In the embodiment of the application, the detailed implementation steps of the deformation vector tracking of the pixel points in the surface deformation image at all times include:

[0117] Local feature enhancement preprocessing is applied to each frame of surface deformation image to improve texture contrast and edge definition; continuous multiple frames of images are organized into a time sequence buffer to ensure time continuity analysis; multi-scale feature descriptors are extracted for each pixel point, including local gradient direction histogram (HOG), local binary pattern (LBP) and deep features; recursive optical flow algorithm is applied to track the displacement of each pixel point between consecutive frames, while forward-backward consistency check is used to verify the tracking reliability; time smoothing filter is applied to the tracking results to eliminate high-frequency noise and transient jumps, and generate continuous and smooth deformation vector field; for the pixel points with failed tracking, interpolation estimation is used based on spatial coherence constraint to ensure the integrity of the deformation vector field.

[0118] The above merely describes preferred embodiments of the present application and is not intended to limit the present application. Although the above embodiments of the present application have been described in detail, those skilled in the art can modify the technical solutions described in the above embodiments, or replace some of the technical features with equivalent ones, without departing from the spirit and principles of the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application shall fall within the scope of the present application.

[0119] It should be noted that the formulas in the specification are dimensionless numerical calculations, the formulas are obtained by software simulation of a large number of collected data to obtain a formula of the most recent real situation, and the preset parameters and threshold values in the formulas are set by those skilled in the art according to the actual situation.

[0120] Although the embodiments of the present application have been shown and described, those skilled in the art can understand that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirit of the present application, and the scope of the present application is defined by the claims and their equivalents.

Claims

1. The digital twin monitoring and dynamic compensation system for the motion state of rehabilitation robots is characterized by: include: An acquisition module is used to obtain the surface deformation image and joint torque data of the patient's limb at each moment during the movement of the rehabilitation robot; a deformation field construction module, configured to construct a dynamic deformation field of the patient's limb soft tissue based on the deformation gradient distribution and local curvature change between pixels in the surface deformation image; a stability analysis module, configured to obtain the deformation stability of each local area in the dynamic deformation field at each moment based on the consistency of deformation directions and deformation amplitude fluctuations of the same local area in the dynamic deformation field at adjacent moments within an analysis period at each moment; Screening out high-stability deformation regions based on the deformation stability; The boundary condition module is used to construct the dynamic mechanical boundary conditions of the digital twin model based on the deformation characteristics of each high-stability deformation area in the dynamic deformation field at each moment and the corresponding joint torque data; including: Extracting deformation features of each high-stability deformation region in the dynamic deformation field at each moment, wherein the deformation features include a deformation gradient tensor and a deformation velocity; Calculating an equivalent stiffness coefficient of each high-stability deformation region according to the deformation gradient tensor and the deformation velocity; Obtaining a torque distribution vector corresponding to each high-stability deformation region according to the joint torque data; Performing matrix mapping on the equivalent stiffness coefficient and the moment distribution vector to obtain dynamic mechanical boundary conditions corresponding to a high-stability deformation region; The model update and compensation module is used to update the motion state of the digital twin model in real time based on the dynamic mechanical boundary conditions and the preset low-order finite element mesh, including: Constructing a preset low-order finite element grid, wherein the low-order finite element grid includes adaptive grid units based on high-stability deformation region division; Mapping the dynamic mechanical boundary conditions to the boundary nodes of the low-order finite element mesh to generate boundary constraint equations; By iteratively solving the boundary constraint equation, the stress distribution and displacement distribution of the low-order finite element grid are obtained, and the motion state of the digital twin model is updated; and generating a dynamic compensation instruction for the motion trajectory of the rehabilitation robot according to the motion state; The modules are connected via wired and / or wireless means to achieve data transmission between modules.

2. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 1 is characterized in that: The obtaining of the deformation stability of each local area in the dynamic deformation field at each moment includes: Tracking deformation vectors of pixels in the surface deformation image at all moments to obtain the deformation vector of each pixel in the surface deformation image at each moment; Counting the number of times that the direction angle of the deformation vectors of the same local area in the dynamic deformation field at adjacent moments within the analysis period at each moment is less than a preset direction threshold, and recording this as the deformation direction consistency of each local area in the dynamic deformation field at each moment; Calculating the standard deviation of the amplitude of the deformation vector of the same local area in the dynamic deformation field at all moments within the analysis period at each moment as the deformation amplitude fluctuation of each local area in the dynamic deformation field at each moment; The deformation direction consistency and the inverse of the deformation amplitude fluctuation are weightedly fused to obtain the deformation stability of each local area in the dynamic deformation field at each moment.

3. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 1 is characterized in that: The method for screening the high-stability deformation region comprises: sorting the deformation stability of each local area in the dynamic deformation field at each moment, and selecting a local area whose deformation stability is greater than a preset stability threshold as a candidate area; The mean value of the boundary curvature of each candidate region in the surface deformation image is calculated, and candidate regions whose mean value of the boundary curvature is greater than a preset curvature threshold are eliminated to obtain highly stable deformation regions.

4. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 1, characterized in that: The step of generating a dynamic compensation instruction for the motion trajectory of the rehabilitation robot according to the motion state includes: Calculating a deviation vector between a desired pose and an actual pose of an end effector of the rehabilitation robot according to a motion state of the digital twin model; Generating a dynamic compensation instruction for the motion trajectory of the rehabilitation robot according to the deviation vector and a preset impedance control parameter; The driving joint angles of the rehabilitation robot are adjusted by the dynamic compensation instructions to achieve real-time compensation of the motion trajectory.

5. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 2, characterized in that: The method for constructing the dynamic deformation field comprises: Performing feature point matching on pixel points in the surface deformation image to obtain a deformation displacement vector for each pixel point; Calculating a deformation gradient tensor between any two pixel points in the surface deformation image according to the deformation displacement vector; A dynamic deformation field at a corresponding moment is constructed according to the deformation gradient tensor and the local curvature change of the pixel points in the surface deformation image.

6. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 1, characterized in that: The method for dividing the adaptive grid units of the low-order finite element grid includes: generating an initial grid cell according to the boundary shape of the high-stability deformation region; Calculate the mean deformation gradient of each initial grid cell and record it as the deformation complexity of the grid cell; The initial grid cells whose deformation complexity is greater than the preset complexity threshold are subdivided twice to obtain adaptive grid cells.

7. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 2, characterized in that: The deformation vector tracking method includes: Using a deep learning-based pixel matching algorithm, feature extraction is performed on the pixels in the surface deformation image to obtain a feature descriptor for each pixel; Calculating, based on the feature descriptor, the matching probability of the same pixel point in the surface deformation image at adjacent moments; A deformation vector for each pixel is generated according to the matching probability.

8. The rehabilitation robot motion state digital twin monitoring and dynamic compensation system according to claim 1, characterized in that: The method for acquiring the surface deformation image comprises: The multi-view depth camera installed on the rehabilitation robot collects 3D point cloud data of the patient's limbs during movement. Surface reconstruction is performed on the three-dimensional point cloud data to generate a surface deformation image of the patient's limb.

Images