287 results about "Upper limb rehabilitation" patented technology

The invention discloses an upper limb exoskeleton rehabilitation robot control system and method, and relates to the technical field of rehabilitation robot upper limb control, and the method comprises the steps: collecting multi-modal data such as multi-channel myoelectricity, joint angles, angular velocity and interactive torque; constructing a sliding window feature vector, predicting a next joint angle increment through TCN and Bi-LSTM deep networks, and outputting intention confidence; and based on the confidence coefficient and the muscle fatigue factor, dynamically adjusting an impedance parameter, and combining an impedance control model to generate a power-assisted torque in real time so as to realize power-assisted torque output. By introducing an impedance adjustment mechanism of multi-modal perception, deep time sequence learning and myoelectricity driving, the bottleneck of a traditional upper limb rehabilitation robot in the aspects of intention prediction, parameter adjustment and training individuation is broken through, and the accuracy, safety and active participation degree in the rehabilitation training process are remarkably improved; wide clinical application prospects and industrial transformation values are realized.

The invention belongs to the field of cerebral apoplexy rehabilitation training, and provides a cerebral apoplexy upper limb dynamic rehabilitation method and system based on vagus nerve electrical stimulation, the excitement degree of a cortical spinal cord pathway of a patient is measured and evaluated by using motor evoked potential to obtain a motor function evaluation result, and an initial rehabilitation training task is set according to the motor function evaluation result; the training motion intention of the patient is determined by monitoring the electroencephalogram signal and the electromyographic signal of the patient, and percutaneous ear vagus nerve electrical stimulation is triggered; after percutaneous ear vagus nerve electrical stimulation, performing rehabilitation training analysis on basic clinical characteristics and multi-modal signals of the patient to determine intermuscular coordination, brain region connectivity and brain muscle coupling of the patient; the training condition of the patient is evaluated according to the rehabilitation training analysis result, and parameters of percutaneous ear vagus nerve electrical stimulation and training tasks are adjusted based on the evaluation result for iterative rehabilitation training; and stopping iteration until the rehabilitation training analysis result of the patient reaches a preset standard, and completing rehabilitation training.

The invention relates to the technical field of medical rehabilitation, and discloses a virtual fusion personalized upper limb rehabilitation training cloud platform and method. The platform is composed of a multi-source biological signal acquisition module, a motion function feature modeling module, a heterogeneous data fusion module, a rehabilitation knowledge graph construction module, a dynamic training planning module and the like. The method comprises the steps of collecting multi-source biological signals, carrying out hierarchical feature modeling, carrying out data fusion, constructing an atlas database, generating a personalized rehabilitation scheme and the like. In this way, individuation and precision of upper limb rehabilitation training are achieved. Patient data can be comprehensively collected, fusion rehabilitation state representation is generated, a double-layer atlas database is constructed to assist training planning, training safety is guaranteed, the rehabilitation effect is predicted, pertinence, scientificity and efficiency of rehabilitation training are effectively improved, and high-quality rehabilitation service is provided for upper limb dysfunction patients.

The invention discloses a multi-link collaborative evaluation and feedback system for upper limb rehabilitation training, and belongs to the technical field of medical rehabilitation, and the system comprises a data collection module which is used for obtaining the related data of the upper limb of a patient in the rehabilitation training process, and the related data comprises the motion posture, the muscle activity condition and the joint activity degree; the data processing module responds to the data acquisition module and is used for preprocessing the acquired related data, including filtering and denoising the related data, acquiring feature information in the preprocessed related data and sending the feature information to the data acquisition module; the feature information comprises movement tracks of joints, contraction intensity and time of muscles and coordination of upper limb movement. Multi-dimensional data such as action postures, muscle movement conditions and joint movement ranges in upper limb rehabilitation training are collected, preprocessing and feature extraction are carried out through the data processing module, the upper limb rehabilitation condition of a patient can be comprehensively and accurately evaluated, and a basis is provided for formulating a personalized rehabilitation scheme.

The invention discloses an upper limb rehabilitation control method and system based on a multimode coordination adaptive brain-computer interface, and belongs to the technical field of neural rehabilitation engineering and brain-computer interfaces. The system comprises a brain signal acquisition module, a self-adaptive residual filtering module, a feature extraction module, a predictive control module, an upper limb rehabilitation actuator and a self-adaptive updating module. The core is that a self-adaptive updating module constructs a composite error cost function by fusing kinematics errors of a physical layer and error correlation potentials of a neurocognitive layer, and on the basis of the composite error cost function, a front-end filtering weight and a network weight of a rear-end control model are synchronously adjusted, so that full-link parameter collaborative optimization from signal preprocessing to motion control is realized. According to the method, the framework limitation of single error feedback and independent parameter optimization of a traditional system is broken through, a closed-loop brain-computer interface system which can sense internal and external states and has system-level self-optimization capability is constructed, and the decoding robustness, the control precision and the practicability under long-term use are effectively improved.

The invention discloses an upper limb rehabilitation training method and system based on a human body motion model, and relates to the technical field of rehabilitation training. Constructing a human body motion model and outputting simulation data; calculating a physiological index coefficient, and further calculating the exercise intensity of each training action; calculating a motion mode complexity index of each training action so as to obtain and calculate the training duration of each training action; and calculating a motion deviation value, and further calculating a comprehensive dynamic deviation index. Presetting a threshold value and judging whether the rehabilitation training plan is suitable for the current state of the patient; whether a rehabilitation training plan needs to be changed; according to the method, the suitability of the rehabilitation training plan can be evaluated in real time, and the training scheme is dynamically adjusted; the training is always fit with the condition of the patient, and the rehabilitation efficiency and success rate are improved.

The invention discloses an upper limb rehabilitation intelligent self-adaptive system based on multi-modal fusion and MRD-FES cooperation. The system comprises a multi-modal signal acquisition module, a dynamic intention analysis module, a variable damping precise execution module, a neural remodeling strengthening module and a quantitative effect evaluation module. The tDCS-MRD-FES time sequence cooperation protocol is provided, the cortical excitability is improved through tDCS preprocessing, MRD drives training based on intention, FES closed loop strengthens muscle contraction, and vibration tactile feedback is assisted to strengthen sensory movement integration. And the quantitative effect evaluation module further combines a neuroplasticity index and clinical scale digitalization to realize dynamic optimization of training parameters.

The utility model provides an electric wheelchair with a rehabilitation function, which is used for upper limb rehabilitation exercise of a wheelchair user and comprises a touch sensor array arranged on the surface of an armrest of the electric wheelchair, and the touch sensor array comprises a plurality of touch sensors capable of being triggered by touch actions; when the touch sensor array is touched, the trigger state and the triggered sequence of each touch sensor are sent to the control module, so that the electric wheelchair moves according to the trigger state and the triggered sequence of each touch sensor in the touch sensor array; a wheelchair left side driving wheel is controlled by the touch action of the touch sensor array at the left armrest, and a wheelchair right side driving wheel is controlled by the touch action of the touch sensor array at the right armrest, so that a user can automatically judge the exercise amount of upper limb rehabilitation exercise according to the rotating direction and the moving distance of the electric wheelchair; according to the rehabilitation exercise device, convenient rehabilitation exercise can be provided for people with mobility difficulties, and a user can conveniently evaluate the rehabilitation exercise amount of the user.

The embodiment of the invention discloses a cerebral apoplexy upper limb rehabilitation training system and method based on dynamic reward feedback. A data acquisition module is used for acquiring physiological signals, motion signals, emotional state data and training performance data; the motion intention decoding module is used for performing motion intention feature extraction and reliability evaluation on the physiological signals according to an improved MREE-Net + + fusion algorithm, performing weighted fusion after feature weights are adjusted according to a reliability result, obtaining a unified motion intention feature vector, performing motion intention decoding, and obtaining a motion intention intensity index and a motion intention vector; the dynamic reward decision module is used for processing the facial micro-expression data according to an improved VGG-Face model to obtain an emotion titer, and obtaining an emotion awakening degree according to the voice signal; a reward action is generated according to an improved deep reinforcement learning algorithm; and the adaptive training regulation and control module is used for generating a personalized virtual training scene according to the generative adversarial network and regulating and controlling the training intensity according to the fatigue index. The rehabilitation training effect can be improved.

The application discloses a rehabilitation robot control method based on multi-source information perception and electronic equipment, and the method comprises the following steps: acquiring upper limb modal signals of a patient without motor function, wherein the upper limb modal signals comprise electroencephalogram signals, and eye movement signals and / or electromyogram signals; for each kind of upper limb modal signal, using an intention recognition model to perform motor intention recognition on the upper limb modal signal to obtain a corresponding motor intention recognition result; acquiring a confidence degree corresponding to each kind of upper limb modal signal; determining the motor intention of the patient according to the motor intention recognition result corresponding to each kind of upper limb modal signal and the corresponding confidence degree; determining a motor control signal of an upper limb rehabilitation exoskeleton according to the motor intention; and controlling the upper limb rehabilitation exoskeleton to move according to the motor control signal. The application can improve the motor intention recognition accuracy of the patient without motor function in the upper limb rehabilitation training process.

The invention discloses an upper limb rehabilitation training device, method and system and a storage medium, and the method comprises the steps: constructing a virtual scene according to the rehabilitation condition of a patient, and combining rehabilitation paradigms from a paradigm library; high-channel electroencephalogram signals are collected, and real-time quality monitoring is conducted; extracting motor imagery features from the electroencephalogram signals and analyzing the motor imagery features into a motor intention; mapping the motion intention to a virtual limb to realize VR / AR body feedback; and behavior data such as concentration degree are calculated and displayed in real time, and personalized rehabilitation evaluation is completed. By the adoption of the technical scheme, the problems that in existing cerebral apoplexy rehabilitation treatment, the normal form has body deficiency, the training scene is single, medical intervention lacks real-time performance, rehabilitation evaluation is high in subjectivity, and individuation is insufficient are solved.

The invention discloses a breast cancer postoperative upper limb function rehabilitation assisting method and system, and the method achieves the precise rehabilitation through multi-dimensional data collection and intelligent scheme generation: collecting the joint movement range, muscle strength index, lymphedema data, VAS pain score and Borg fatigue index of the upper limb of a patient, and carrying out the fusion to generate an upper limb function feature set; dividing the rehabilitation process into four stages, and generating a rehabilitation target corresponding to each stage by means of a preset mapping mechanism based on the feature set; generating a candidate rehabilitation scheme by applying a rehabilitation scheme generation model based on machine learning according to the staged rehabilitation target; through a prediction model based on multi-dimensional evaluation, rehabilitation prediction scores are generated in combination with the upper limb function feature set and the candidate rehabilitation schemes, and the candidate scheme with the highest score is selected as the optimal rehabilitation scheme. Personalized and dynamic management of upper limb rehabilitation after the breast cancer operation is achieved, and adaptability and effectiveness of a rehabilitation scheme are improved.

The invention discloses upper limb rehabilitation training equipment capable of being mutually used by left and right arms, which comprises a small arm elbow joint training mechanism, a big arm shoulder joint training mechanism and a left and right reversing mechanism, and is characterized in that the small arm elbow joint training mechanism is connected with the front end of the big arm shoulder joint training mechanism in a foldable manner through a folding part; the rear end of the big arm shoulder joint training mechanism is connected with the left-right reversing mechanism, and the left-right reversing mechanism is used for driving the big arm shoulder joint training mechanism to rotate relatively. According to the upper limb rehabilitation training equipment capable of being used by the left arm and the right arm, the functions of being small in size, light and easy to use are achieved, the pull rope is used for power transmission, the overall size of the equipment is optimized, daily use is more convenient through the rotating clutch mechanism used by the left arm and the right arm, and the equipment is small in size, convenient to store, simple in structure, practical and easy to operate.

The invention discloses a rehabilitation training fatigue detection system based on EEG-GSR-PPG and upper limb rehabilitation robot motion signals, and belongs to the crossing field of rehabilitation training monitoring, robot motion sensing and signal processing. According to the system, physiological signals are synchronously collected through EEG, GSR and PPG modules, kinematics / dynamics signals are obtained in combination with an upper limb rehabilitation robot, and the fatigue state is marked based on a Borg scale; the method comprises the following steps: carrying out differential preprocessing and segmentation on a multi-modal signal, extracting features, screening core features through a random forest, and realizing fatigue four-stage classification through an SVM, DT or KNN algorithm. According to the method, full-link objective, real-time and grading evaluation of'center (EEG)-periphery (GSR / PPG)-motion execution (robot signal) 'of rehabilitation training fatigue is realized, and a solid data support is provided for dynamic adjustment of a training scheme.

1. The name of the design product: multi-degree-of-freedom upper limb rehabilitation robot. 2. The use of the design product: for patient upper limb rehabilitation. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: perspective view.

The application relates to the technical field of medical rehabilitation robots, in particular to a safe upper limb rehabilitation exoskeleton robot, which comprises a fixing frame and a mechanical arm arranged on the fixing frame and used for assisting the movement of a patient's arm, the mechanical arm comprises, in sequence, a shoulder joint vertical folding and unfolding module, a shoulder joint horizontal folding and unfolding module, a shoulder joint flexion and extension module, an elbow joint flexion and extension module, a wrist joint flexion and extension module and a lower arm rotating module, the mechanical arm can be suitable for a left arm or a right arm by switching left and right states. Each module of the mechanical arm is provided with a mechanical limiting structure used for limiting the activity range of the corresponding module, and the mechanical limiting structure can switch left and right states, and is used for synchronously switching when the mechanical arm switches left and right states to ensure the safety of the patient. The spring positioning pin is used for adjustably limiting, the application can realize the left and right exchange function of the mechanical arm, ensure the mechanical safety limiting of the limit angle of the two arms and improve the safety of the equipment.

The utility model discloses an upper limb flexion and extension straight training device, which comprises a base, an overturning seat, a first supporting plate, a second supporting plate and a driving unit, the rear part of the overturning seat is rotatably connected with a lug boss above the base through a first rotating shaft, the first supporting plate is adjustably arranged on the overturning seat, the front end of the second supporting plate is movably connected with the base, and the driving unit is arranged on the overturning seat. The driving unit is arranged on the inner side of the base, the rear end is rotationally connected with the base, and the front end is rotationally connected with the overturning base. When the upper limb rehabilitation training device is used, a patient only needs to place the forearm on the first supporting plate and place the upper arm on the second supporting plate, then the driving unit drives the overturning base and the first supporting plate to overturn up and down, and therefore the bending and stretching straight movement of the upper limb is achieved, operation is easy and convenient, and the patient can independently complete training without assistance of other people; and therefore, the use convenience of the device is improved.

A desktop upper limb rehabilitation robot includes: a housing having a bottom plate; a clamping member comprising a main body slidably connected to the bottom plate and a jaw connected to the main body, the main body defining a threaded hole, the threaded hole and the jaw located at opposite sides of the bottom plate; a threaded rod structure comprising a threaded rod, the threaded rod comprising an end rotatably connected to and abutting against the bottom plate, the threaded rod threadedly engaged with the threaded hole, and the threaded rod configured to rotate with respect to the bottom plate so as to drive the main body to move with respect to the bottom plate, allowing the jaw to move together with the main body to a desired position where an edge of a desk is sandwiched between the bottom plate and the jaw.

1. Name of the product in this design: Upper limb rehabilitation training device. 2. Purpose of this design: for upper limb rehabilitation training. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

The embodiment of the invention discloses an upper limb rehabilitation training system and method based on virtual reality, and relates to the technical field of medical rehabilitation, and the system comprises a virtual reality display module which is used for displaying a virtual training scene to a target user performing upper limb rehabilitation training; the first data acquisition module is used for acquiring first motion data; the data processing module is connected with the virtual reality display module and the first data acquisition module, and the data processing module is configured to determine second motion data of the virtual hand under the condition that the motion distance corresponding to the first position is equal to a target distance determined by a motion distance upper limit value, and the virtual hand is controlled to move towards the target object based on the second motion data to guide the real hand to approach the target object, so that the compliance of the target user in the rehabilitation training process is improved, and the rehabilitation training process is accelerated.

The utility model belongs to the field of medical instruments, and discloses an upper limb internal and external rotation training device and an upper limb rehabilitation training system.The upper limb internal and external rotation training device comprises a base, a power output assembly, a torque sensor, an arm support assembly and a grip strength detection handle; the power output assembly is arranged on the base; the torque sensor is fixedly connected with the output end of the power output assembly. The arm support assembly is fixedly connected with the output end of the power output assembly, and the power output assembly drives the arm support assembly to rotate; the grip strength detection handle is fixedly arranged relative to the arm support assembly. By arranging the power output assembly, the arm support assembly and the grip strength detection handle, internal and external rotation training can be carried out on the upper limbs, comprehensive, safe and effective rehabilitation training can be carried out on the forearms, finger joints and other fine joints of a patient, and the training effect is improved; in addition, through multi-dimensional feedback of torque, force and the like, the autonomous participation willingness of the patient is effectively improved, the training effectiveness is enhanced, and manpower resources are saved to a certain extent.

The invention belongs to the field of rehabilitation training devices, and particularly relates to a portable training device for upper limb rehabilitation of adults, which comprises a back hanger, a fixing seat for providing a fixed track is mounted on one side of the back hanger, and a rotating handle for stretching is mounted above the fixing seat. The fixing base and the rotating handle can exist in the same direction, so that the occupied space is reduced, the problem that an existing adult upper limb rehabilitation training device is not portable enough is solved, a user can conveniently carry the device when moving outdoors or in a long distance, and the training effect is kept; a user drives a rotating handle to move through two hands, an elastic belt is stretched through a moving handle, the function of exercising the bending function of the upper limbs and elbows of the user is achieved, a patient is helped to recover the elbows, and the elastic belt can be wound around the outer side of a connecting pipe by rotating connecting rods on the two sides of the connecting pipe in different directions; the function of exercising wrist twisting of the user is achieved, and the user is helped to recover the wrist.

The application relates to the technical field of rehabilitation, in particular to an upper limb rehabilitation training device which comprises a sleeve, an air bag fixedly connected to the inner side of the sleeve, an air pump communicated with the air bag, fixed ends and movable ends respectively at the two ends of the sleeve, a box body fixedly connected to the outer side of the fixed end of the sleeve, a receiving cavity and a control cavity separated by a partition plate in the box body, a receiving opening formed in the side wall of the receiving cavity, a motor fixedly connected to the inner side wall of the receiving cavity, a reel coaxially fixedly connected to the output shaft of the motor, a connecting rod fixedly connected to the side wall of the reel, and the movable end of the sleeve fixedly connected to the side wall of the connecting rod; a controller arranged in the control cavity, and a probe assembly embedded in the inner side of the sleeve. The sleeve is automatically wound and unwound to replace the traditional magic tape fixing, the air bag pressure is automatically adjusted in cooperation with the controller, the probe assembly is integrated to realize real-time monitoring of arterial blood flow, the problems of traditional pressurized sleeves, such as complicated wearing, easy hooking and displacement, and low pressure control precision, are solved, and the single-person convenient wearing, stable and accurate blood flow restriction training is realized.

The utility model relates to the technical field of robots, and discloses an upper limb rehabilitation training robot which comprises a base and a training arm, a lead screw lifter is connected to the base, a fixed arm is connected to the lead screw lifter, the training arm is arranged on one side of the fixed arm, and a distance adjusting structure is arranged between the fixed arm and the training arm. Placing soft cushions are arranged on the training arms and the fixed arms, arm fixing belts which are wound and fixed by hook-and-loop fasteners are connected to the fixed arms and the training arms, air pressure clamping structures for clamping arms are arranged on the inner sides of the arm fixing belts, the extending ends of the training arms are connected with extending plates, and air cylinders are connected to the lower portions of the extending plates; the extending end of the air cylinder penetrates through the extending plate to be connected with a B-shaped frame, and a foam sleeve is arranged on a cross rod in the middle of the B-shaped frame. The utility model has the advantages that the training area does not need to be replaced repeatedly, and the constraint to the arm is more comfortable.

The invention relates to the technical field of mechanical arm control methods, and discloses a muscle force evaluation and self-adaptive control method for a household remote control upper limb intelligent rehabilitation mechanical arm, which comprises the following steps: initializing a system, guiding the first elbow flexion by voice, and judging the anti-gravity capability according to an elbow joint flexion angle. Secondary elbow bending is carried out after different reverse resistances are applied, the resistance resistance is judged according to the elbow joint bending angle, a scale is converted into clinical muscle force classification, a main control board calculates self-adaptive traction force and realizes closed-loop control, meanwhile, whole-course data are uploaded to a cloud side, and remote terminal monitoring and parameter adjustment are supported; according to the invention, the evaluation logic conforms to the clinical standard, the detection precision is high, the system integration level is good, quantitative muscle force evaluation, individualized adaptive training and remote professional supervision can be realized, the system is suitable for household upper limb rehabilitation of stroke, nerve injury and postoperative patients, and the technical problems of inaccurate evaluation, fixed control and lack of remote management of existing equipment are effectively solved.

The application discloses a digital twin upper limb rehabilitation training robot and method considering patient emotion, which comprises: a teleoperation master robot for obtaining accurate action information of a trainer; at least one wearable exoskeleton mechanical arm for obtaining force, heart rate, electromyographic signal and facial expression of the patient respectively, restoring the action of the trainer and making the same movement with the patient; a computer system carrying a digital twin, comprising a digital twin model established according to the connecting rod relationship of the mechanical arm, and a man-machine interaction module and a voice broadcast module; according to different training stages, the action of the trainer is learned and output to guide the exoskeleton mechanical arm to replicate the action. In the training process, the trainer can participate and help the patient to restore the action of the trainer through the teleoperation teaching mode, and at the same time, the patient emotion is considered to adjust the training progress and intensity, so that better training effect is achieved and the training time is saved.

The invention discloses a BCI method and system based on EOG autonomous rehabilitation, and the method comprises the steps: constructing a graphical user interface comprising button flickering visual clues and corresponding upper limb motion types, enabling all buttons to flicker circularly according to a set time interval, and enabling a user to select a target motion function through synchronous blinking and then stop flickering; the method comprises the following steps: acquiring an EOG signal when a user blinking through a wearable BCI device, and synchronously marking a motion type corresponding to button flickering to form motion intention information; a decision control unit is optimized based on the threshold parameter obtained in the calibration stage, EOG signal features are extracted by using the optimized decision control unit, and a blinking event corresponding to button blinking is detected; a target button function is recognized according to the blink detection result, and a control instruction corresponding to upper limb rehabilitation exercise is generated and sent to the lower computer; the lower computer receives the instruction, drives the motor to execute rehabilitation actions, and assists the user in completing upper limb joint and muscle function training.

The invention discloses a nursing device facilitating postoperative upper limb rehabilitation of an affected side after a breast cancer operation, and relates to the technical field of postoperative rehabilitation of the breast cancer. The nursing device convenient for the upper limb rehabilitation of the affected side after the breast cancer operation comprises a rack, an adjusting mechanism is arranged on one side of the rack, a rotating mechanism is arranged on one side of the adjusting mechanism, a massage mechanism is arranged on one side of the rotating mechanism, and an exercise mechanism is arranged on one side of the adjusting mechanism; the massage mechanism comprises two mounting plates, the two mounting plates are located on the two sides in the rack respectively, a connecting ring is fixedly connected to one side of each mounting plate, the inner wall of each connecting ring is arranged at the position sleeving the arm of the patient, and a cavity is formed in each connecting ring. Meanwhile, the rotating ball is enabled to perform pressing and rolling type massage operation on the arms of the patient, the side upper limbs of the patient can be exercised, pain of the patient due to muscle contraction can be avoided, and the effect of accelerating the rehabilitation progress of the patient is achieved.

The invention discloses a soft stipulation performance reinforcement learning control method for rehabilitation exoskeleton, and the method is a reinforcement learning control method based on soft preset performance, and comprises the steps: S1, building a soft stipulation performance reinforcement learning control law based on a dynamic soft constraint mechanism and an online learning and compensation mechanism; wherein the dynamic soft constraint mechanism is used for intelligent coordination control of safety and high performance, and the online learning and compensation mechanism is used for intelligent coordination calculation of complexity, model dependence and control precision; and S2, controlling the rehabilitation exoskeleton based on the soft stipulation performance reinforcement learning control law. The invention further discloses a corresponding system, electronic equipment and a computer readable storage medium, a soft constraint dynamic adjustment mechanism is combined with an intelligent learning and decision-making mechanism, and therefore the balance problem of safety, accuracy and self-adaptability when the upper limb rehabilitation robot faces uncertainty is solved.

This utility model discloses an upper limb rehabilitation training device, relating to the field of medical device technology, including a worktable, a traction component, and a support frame. The traction component includes a first link, a second link, a third link, a fourth link, and a slider. The slider is movably mounted on the worktable. One end of the first link is fixedly connected to the slider, and the other end is rotatably connected to the second link. The fourth link is rotatably mounted on the worktable and rotatably connected to the third link, as are the second and third links. The support frame is located at the connection between the second and third links and is used by the patient to place the affected limb. This upper limb rehabilitation training device, through the traction of the first, second, third, and fourth links and the slider to move the support frame, can achieve diversified movement trajectories of the support frame, more accurately simulating human upper limb movements, and the operation is more stable, improving the safety and comfort of rehabilitation training.