194 results about "Hand movements" patented technology

The disclosure presents a humanoid robot with an upper region (head, torso, arms with forearm assemblies, end effectors), lower region (legs), and connecting central region. Each end effector features index, middle, ring, little finger, and thumb assemblies attached to a housing of said end effector. The housing includes interior wall extents creating spaces for tendon routing, where the first distance between first and second wall extents is less than 45% of the second distance between third and fourth wall extents. Tendons controlling finger movements pass between these wall extents. The robot incorporates a wrist assembly connecting the housing of the end effector to the forearm, actuators housed in the forearm that control the tendons, and a carpal tunnel-like structure that guides tendons from forearm to base of the housing, enabling precise hand movements without requiring actuators in the hand itself.

The invention provides a rigid-flexible coupling humanoid manipulator which comprises a humanoid rigid-flexible coupling manipulator mechanical body, a wrist tube connected with a hand body and a driving control system and a hand body driving control system, a thumb and palm connecting piece drives a thumb to do palm-facing movement, and a steering engine module is in transmission connection with fingers and the thumb through a plurality of driving ropes. The fingers and the thumb can do flexion or abduction movement, and the fingers can do lateral deviation abduction movement; and elastic ligaments are connected to joints of the fingers and the thumb. Through the autonomous variable-stiffness metacarpophalangeal joints, the bionic interphalangeal joint system and the hand-simulated hand movement system of the elastic envelope structure, dexterous movement and contact compliance of the manipulator in a complex operation task are achieved, and the dynamic balance requirement of the manipulator between dexterous operation and rigid maintenance is met; the invention has the advantages of excellent movement performance, strong environmental adaptability, low manufacturing cost and the like.

The invention provides a method and a device for redirecting human hand actions to a heterogeneous manipulator in a multi-task scene, and relates to the technical field of robots and intelligent control. The method comprises the following steps: acquiring visual data and tactile data; performing task type classification by adopting a pre-trained Perciver IO model to obtain a task type code; according to a physical constraint dynamic correction mechanism, correcting the joint weight of the machine finger to obtain a normalized finger weight; key point extraction is conducted on the human hand, and vectors between all joints of the human hand are calculated through a geometric vector method; performing driven joint constraint processing according to the established joint mapping matrix, calculating an adapted Jacobian matrix, and obtaining an adapted standardized robot arm kinematics model; and carrying out nonlinear optimization on the vectors between the human fingers and between the robot fingers to obtain each joint angle of the robot arm, so that the robot arm completes action redirection. By adopting the method, the generalization ability of cross-task and heterogeneous models can be improved.

The invention discloses an auxiliary stroke rehabilitation method and device based on a multi-source physiological signal wearable device. The method comprises the steps that the pulse waveform variation rate and sublingual vein feature parameters of a subject are monitored through a self-powered five-hidden monitoring wrist strap; dynamically evaluating the internal organ imbalance index of the subject according to the pulse waveform variation rate and the sublingual vein characteristic parameters; generating personalized rehabilitation adjustment parameters according to the internal organ imbalance index of the subject; synchronously acquiring an electroencephalogram signal of a subject and a surface electromyogram signal of a target muscle, and generating an acupoint activation time sequence map of preset hand actions; the acupoint activation time sequence map is optimized according to the personalized rehabilitation adjustment parameters so as to adjust acupoint selection, stimulation intensity and stimulation time sequence; and presenting a built-in foot yangming stomach meridian virtual acupuncture scene to the subject through the VR guide instrument. According to the apoplexy rehabilitation method, electroencephalogram and myoelectricity cooperative decoding, personalized parameter adjustment, VR and a viscera imbalance traditional Chinese medicine diagnosis method are integrated into a rehabilitation scheme, and the apoplexy rehabilitation effect is improved.

The invention relates to the technical field of medical hygiene, and particularly discloses a hygiene visual intelligent monitoring and guiding system suitable for surgical hand disinfection, hand motion data is collected by fusing a multi-modal motion capture module with a depth camera and an inertial sensor, and a high-risk area identification module analyzes the risk of microbial residues in finger seams and fingernail edges. The three-dimensional motion modeling module constructs a biomechanical model to calculate a trajectory, the dynamic compliance guiding module marks deviation in real time through optical projection, the multi-source data fusion module integrates a risk value and a spectral data evaluation effect, and the intelligent decision engine module outputs an operation matching degree and a correction instruction based on a neural network. Omnibearing monitoring, accurate risk assessment, real-time action guidance and quantitative effect evaluation of the hand disinfection process of an operator are realized, the standardization and effectiveness of surgical hand disinfection operation are finally improved, and the infection risk of a surgical site is reduced.

The invention provides a system for controlling a manipulator in real time through hand electromyographic signals, which comprises a data acquisition unit, a terminal equipment unit and a tail end execution unit which are in communication connection through serial ports. The data acquisition unit comprises a data acquisition device and a signal acquisition module, and is configured to acquire a multi-channel electromyographic signal of a hand of a user in real time and perform signal conditioning and digitization so as to obtain a digital signal sequence representing a muscle activity intention of the user; the terminal equipment unit comprises a data preprocessing module, a model training module, a gesture recognition module and an instruction generation module; the tail end execution unit comprises a manipulator control unit which is in communication connection with the control output module and is configured to be used for receiving the manipulator control instruction and driving a manipulator to execute corresponding actions; in combination with a control method, the problems of insufficient real-time performance, poor hand action recognition precision and robustness, unstable control instruction, poor user adaptability and the like in the prior art are solved, and the man-machine interaction performance is improved.

The present disclosure provides a machine vision-based method for determining a range of motion of a joint of a hand of a subject and a system for implementing the same. The provided method comprises: facilitating the subject to perform a hand movement at a preset position; capturing at least two prior-movement images of the hand when the hand is in a neutral posture before performing the hand movement; capturing at least two post-movement images of the hand when the hand is in an assessment posture after performing the hand movement; processing the captured prior-movement images to obtain a plurality of prior-movement key point positions; processing the captured post-movement images to obtain a plurality of post-movement key point positions; and calculating the range of motion of the joint based on the plurality of prior-movement key point positions and the plurality of post-movement key point positions.

The invention provides intelligent wrist and hand function training equipment for old people at home, and relates to the technical field of training equipment for old people. The intelligent wrist and hand function training equipment for the old at home comprises a fixing plate and a silica gel plate, a connecting box is fixedly connected to the upper end of the fixing plate, a movement assembly is arranged in the connecting box, a detection assembly is arranged at the joint of the fixing plate and the silica gel plate, and the movement assembly comprises a connecting frame; an auxiliary assembly is arranged at the front end of the moving assembly, a soft sleeve is arranged outside the auxiliary assembly, and first rotating shafts are rotationally connected to the middles of the front ends of the inner walls of the two sides of the connecting frame. According to the intelligent wrist and hand function training equipment for the old people at home, when the old people do hand movement, a silica gel plate drives a fixed disc to synchronously move, a reset spring is compressed through a second fixed block, so that a first fixed block transmits a dynamic pressure signal to a pressure sensor, and the signal is processed by a control display panel.

The invention provides an ultrasound-guided nerve block anesthesia puncture method based on artificial intelligence, and the method comprises the steps: S11, collecting a target nerve block image through an ultrasonic probe, and positioning a to-be-punctured point in the target nerve block image; s12, identifying tissues except the point to be punctured in the target nerve block image, marking the tissues as dangerous areas, and planning a path from the skin to the point to be punctured by taking avoidance of the dangerous areas as a principle; s13, electromyographic signals of the arms of the operator are collected in real time, and an intention prediction model between the electromyographic signals and hand actions is established; and S14, determining a space coordinate system position of a puncture needle point based on the to-be-punctured point, associating the puncture needle point with the intention prediction model, monitoring whether the puncture needle point punctures along the planned path, and if not, sending out an early warning signal. The precision, the safety, the efficiency and the reliability of puncture are improved, the operation difficulty and the complication risk are reduced, and meanwhile, the development of personalized medical treatment is promoted.

The invention relates to the technical field of man-machine interaction, in particular to a dexterous hand pose data acquisition method based on infrared optical motion capture, which comprises the following steps: initializing an infrared optical motion capture system and a bending value of each finger flexion and extension of each dexterous hand; constructing a hand model; modifying the message format of the VRPN communication protocol, obtaining the pose data of each mark point of the hand, calculating the rotation angle of each finger near-end fingertip joint of each hand under each task, taking the rotation angle as the rotation angle of each finger near-end fingertip joint of the dexterous hand corresponding to each hand under each task, and outputting the rotation angle of each finger near-end fingertip joint of the dexterous hand. And sequentially calculating the rotation angle of each finger palm knuckle, the bending value of each finger flexion and extension and the bending value of the thumb adduction and abduction under each task. According to the method, the grabbing success rate of the dexterous hand is increased, the reliability of the dexterous hand is improved, the capacity of capturing complex hand actions is enhanced, and the performance of the dexterous hand in a complex task scene is enhanced.

The invention relates to the technical field of fingertip recognition, and discloses a fingertip recognition method and device for hand contour area judgment. The method comprises the following steps: acquiring a hand image and extracting a hand contour point sequence; calculating a local shape dimension value based on the hand contour point sequence, and recognizing fingertip candidate region data in combination with a local curvature value and a convexity metric value; creating a fingertip form descriptor according to the fingertip candidate region data, and determining a fingertip candidate point set by calculating a fingertip-recess association degree value and a hand contour sector area ratio; performing multi-feature fusion judgment on the fingertip candidate point set to obtain a real fingertip point set; and establishing a nonlinear mapping relation between a physical coordinate system and an image coordinate system in the real fingertip point set, and outputting a steady-state locked accurate fingertip position. According to the invention, accurate positioning and smooth tracking of the fingertip position are realized, shaking and jumping phenomena during rapid movement of the hand are effectively eliminated, and stable and continuous fingertip trajectory output is provided.

The present invention relates to a virtual reality (VR) system and method for enhancing medical training. Integrating advanced hand tracking technology with a VR headset, this system offers an immersive training environment for a variety of medical procedures, including CPR, emergency medical interventions, and physical examinations. The hand tracking sensors provide precise monitoring of hand movements, allowing for gesture-based interaction without physical controllers. The system includes several modules for different medical scenarios, each designed to accurately replicate medical techniques and provide real-time feedback. Key innovations include haptic feedback, adjustable difficulty levels, interactive tutorials, and an AI-driven virtual instructor for a personalized training experience. The system is particularly beneficial for training healthcare professionals in critical skills necessary for effective patient care in emergency situations, representing a significant improvement over traditional training methods.

The invention belongs to the technical field related to medical robots, and discloses a rigid-flexible coupling pneumatic humanoid dexterous finger and a dexterous hand. The dexterous finger comprises a sectional corrugated pipe actuator, a rigid cover plate, a rigid bottom plate, a flexible finger pulp patch and a one-way stretchable fabric; a cooperative structure of rigid supporting, flexible driving and contact adaptation is formed through a preset assembly relation; by designing the wave number of the corrugated pipe at each joint of the pneumatic dexterous finger, the bending proportion of each joint is ensured to accord with the human hand movement rule; the one-way stretchable fabric can restrain ineffective upheaval at the joints, and the energy conversion efficiency is improved. The dexterous hand can integrate five anthropomorphic-size dexterous fingers, and the palm notch angle, the thumb turning direction angle and the flexible palm patch are all engraved with the physiological characteristics and structure of the hand of the human body. According to the pneumatic dexterous hand, personification of the pneumatic dexterous hand in appearance and movement modes is achieved, flexibility and bearing stability are both considered, and the pneumatic dexterous hand can meet the requirements of multiple scenes such as medical care and industrial assembly.

A method including acquiring a hand movement video obtained by capturing images during a process in which a target user rotates a wrist joint from a first angle to a second angle while maintaining a hand posture with five fingers naturally extended, so that the hand movement video comprises a plurality of image content frames captured during a rotation process of the hand from a front / side view to a side / front view; acquiring curvature information of the fingers and / or nails from the plurality of image content frames acquired during the rotation process; and creating a 3D hand model of the target user based on the hand movement video, and optimizing key point parameters of the fingers and / or nails in the 3D hand model based on the curvature information of the fingers and / or nails. The present disclosure enables digital reconstruction of the hand and improve the reconstruction accuracy of the hand.

The invention provides a three-dimensional hand reconstruction method and device based on multi-view feature interaction, and the method comprises the following steps: obtaining hand images corresponding to the same hand under at least three views, inputting each preprocessed hand image into a pre-trained hand feature reconstruction network, and obtaining a vertex offset matrix, and performing reconstruction based on the vertex offset matrix and a preset standard hand grid to obtain a three-dimensional hand reconstruction result. According to the scheme, in the feature fusion stage, geometric features and key information are extracted at the same time through the dynamic feature fusion module and the multi-view feature fusion module, and in the decoding stage, the interaction relation between joints and vertexes and the physical characteristics of hand movement are deeply excavated, so that accurate three-dimensional reconstruction is completed.

The invention relates to the technical field of rehabilitation medical treatment, in particular to a hand rehabilitation training system based on virtual reality and gesture interaction, and the system comprises a gesture sensing module which collects a hand movement track, a muscle electric signal, grip pressure and a joint movement angle; the VR rehabilitation scene construction module constructs a rehabilitation training virtual scene, simulates a hand interaction behavior and a force feedback effect through an adaptive physical engine and a neural action mapping algorithm, and outputs simulation data; the intelligent evaluation center evaluates the action standard degree and the muscle activation efficiency based on an improved CNN-GRU model, identifies an action compensation mode and abnormal force generation, and outputs an evaluation report; the interactive training unit renders a motion state and a training process in real time, and generates personalized training guidance in combination with voice, visual and tactile prompts; and the personalized regulation and control unit predicts a rehabilitation trend and a stage target through a reinforcement learning algorithm, and dynamically adjusts training parameters and scene difficulty. Therefore, the problems of low interaction precision, incapability of sharing and the like in the prior art are solved.

A head-wearable apparatus improves user interactions with virtual interface elements in augmented reality (AR) environments. The apparatus tracks hand movements in 3D space, calculating velocity vectors and positions of fingers. For each virtual interface element, it determines a UI-to-finger vector and calculates alignment with the finger's velocity vector. Interaction zones are dynamically adjusted based on this alignment and velocity magnitude. The system evaluates consistency between finger movement and element locations to predict intended targets. Interactions are triggered when fingers enter adjusted zones of predicted targets. This approach reduces erroneous selections and improves interaction accuracy, even for closely-spaced elements. The invention applies to various AR scenarios, enhancing user experiences in applications like gaming and education.

The invention discloses a non-active finger exoskeleton and a non-active hand exoskeleton. The finger exoskeleton comprises a fixed seat, an upper pull rod, a lower pull rod and knuckles. And the far end of the upper pull rod is connected with the middle ends of the knuckles and the near end of the central pull rod. The near end of the lower pull rod is connected with the fixed seat, and the far end is connected with the knuckle near end. A unique ergonomic design is adopted, a user is allowed to control the exoskeleton through simple hand actions without depending on external power, complex holding and operation tasks are completed, and the life self-care ability of a person with finger amputation or insufficiency is remarkably improved.

The utility model discloses a hand rehabilitation training exoskeleton, and relates to the technical field of exoskeletons. According to the hand rehabilitation training exoskeleton, the ends of the palm shells are connected with the joints in a supporting mode through supporting sleeves, and the supporting sleeves are connected with an air conveying device in a communicating mode. The carpal joint is connected with the palm shell through a supporting sleeve, the other end of the carpal joint is connected with the metacarpal joint or the finger joint through the supporting sleeve, and the other end of the metacarpal joint is connected with the finger joint through the supporting sleeve. The problems that in the prior art, the size is large, flexibility is poor, operation is complex and the like are solved, and the requirements for precise assistance and natural training are difficult to meet. According to the hand rehabilitation training exoskeleton, the exoskeleton and the pneumatic technology design are combined, the lightweight design and the intelligent control technology are combined, the hand rehabilitation training exoskeleton aims at assisting a hand dysfunction patient in scientific rehabilitation training, and the hand rehabilitation training exoskeleton is suitable for stroke, brain injury, joint diseases or postoperative hand function recovery. Natural assistance and scientific rehabilitation of hand movement are achieved, and an efficient and safe hand function recovery means is provided for a patient.

This invention discloses a finger joint angle detection mechanism and a method for constructing a 3D model of an object; belonging to the field of exoskeletons for human finger joints, it consists of a fabric substrate, a data storage module, a displacement sensor, and a transmission mechanism, including five sets of three-segment skeletons. The thumb skeleton includes a fingertip joint rod, a root joint rod, a back-of-hand rod, and a wrist rod; the other finger skeletons include a fingertip joint rod, a middle joint rod, a root joint rod, and a back-of-hand rod. Each pair of skeleton segments is connected by a transmission mechanism and a cylindrical pin. The glove does not affect the natural movement of the human hand, and when collecting finger joint data through grasping or other methods, it ensures flexible hand movement, and the range of joint bending angles is unrestricted. When the human hand wears the glove to grasp an object, the bending angles of each finger joint are collected and converted into bending angle images. A convolutional neural network is used to fuse the bending angle images with multi-angle captured object images to achieve accurate 3D reconstruction of the object.

This invention relates to the field of medical and nursing device technology, and in particular to a restraint-type distance-sensing anti-extubation alarm glove and its method of use. The glove includes a restraint glove with a fixing strap on one side of its surface. A magnet is fixedly connected to the top of the fixing strap, and a magnet is disposed within the inner cavity of the magnet. This invention combines physical restraint with intelligent early warning, catheter positioning, and catheter angle adjustment. Through a specially designed enclosed space on the right side of the restraint glove's inner cavity, the range of motion of the patient's ring and little fingers is physically restricted, effectively preventing the patient from pulling the tube by clenching their fist. Simultaneously, a distance monitoring system is constructed using positioning chips one, two, and three. When hand movements pose a risk, multiple alerts are provided through different colored lights, alarm sounds, and vibrations, offering comprehensive warnings to the patient and medical staff from auditory, visual, and tactile dimensions, allowing for timely measures to prevent extubation.

A head-wearable apparatus improves user interactions with virtual interface elements in augmented reality (AR) environments. The apparatus tracks hand movements in 3D space, calculating velocity vectors and positions of fingers. For each virtual interface element, it determines a UI-to-finger vector and calculates alignment with the finger's velocity vector. Interaction zones are dynamically adjusted based on this alignment and velocity magnitude. The system evaluates consistency between finger movement and element locations to predict intended targets. Interactions are triggered when fingers enter adjusted zones of predicted targets. This approach reduces erroneous selections and improves interaction accuracy, even for closely-spaced elements. The invention applies to various AR scenarios, enhancing user experiences in applications like gaming and education.

Flexible nanocomposite-based piezoelectric glove system for recognizing hand gestures and wirelessly controlling the movement of a trolley, comprising a flexible glove adapted to be worn on a user's hand; a plurality of piezoelectric nanocomposite sensors attached to the glove at the wrist or finger joints, the sensors configured to generate voltage signals in response to mechanical deformation caused by wrist or hand movements; a microcontroller unit integrated into the glove, configured to receive and process the voltage signals from the sensors to classify specific hand gestures based on signal patterns; a wireless communication module operatively coupled to the microcontroller unit and configured to transmit gesture-based control signals to a remote receiver; a receiver module integrated into a remote movable device, the receiver configured to receive the transmitted control signals and generate corresponding motion control commands for the movable device; wherein the system (100) is configured to enable wireless real-time control of the movable device by user hand gestures without requiring external power for gesture sensing.

The utility model relates to the technical field of electric power detection, and discloses a portable electric power back splint, which comprises a back splint body, a fixing mechanism is arranged on the rear side of the back splint body, a handheld mechanism is arranged on the rear side of the fixing mechanism, the handheld mechanism comprises a limiting block, the limiting block is arranged in the fixing mechanism, and the limiting block is arranged in the fixing mechanism. The back splint comprises a back splint body, a limiting block is arranged on the back splint body, a connecting frame is fixedly connected to the rear side of the limiting block, a fixing sleeve is fixedly connected to the rear side of the connecting frame, and a sponge body is fixedly connected to the bottom in the fixing sleeve. By means of the technical scheme, the back splint can be carried more conveniently, meanwhile, accidents possibly caused by holding the back splint body by hand can be reduced, the stability of the back splint is guaranteed, meanwhile, the back splint body is arranged on an arm in a sleeving mode so that immediate measurement and reading can be achieved, extra hand actions are not needed, and therefore work continuity and efficiency can be improved.

A method and system for continuous aerial handwriting stroke recognition in extended reality includes: sampling over time to acquire the three-dimensional position sequence of key finger points during user writing and the 6-DOF pose information of an XR computing device at the sampling time; constructing and training a lightweight neural network model, the model flow of which is as follows: preprocessing the input data and constructing kinematic features, then passing the kinematic features through a deep separable temporal convolutional network to output the writing probability and boundary probability at each sampling time, with the boundary probability used for auxiliary supervision during training; passing the sampled data through the trained lightweight neural network model to infer and output the writing probability at the sampling time, and extracting connected segments according to a threshold to recover the stroke segment set, thereby achieving visual interaction with the user. This invention relates to the field of information technology and can automatically identify the position of writing strokes and their boundaries from continuous hand movements without relying on virtual plane constraints or excessive reliance on explicit switching actions.

The invention provides a controllable variable-stiffness hybrid-driven self-adaptive dexterous hand and a driving method thereof, the controllable variable-stiffness hybrid-driven self-adaptive dexterous hand comprises a bionic connecting assembly, a variable-stiffness finger assembly and a thumb assembly, and the variable-stiffness finger assembly comprises an assembly frame, a variable-stiffness assembly, a first driving mechanism, a near knuckle assembly, a middle knuckle assembly and a first fingertip assembly; the thumb assembly comprises a mounting base, a rotary driving mechanism, a second driving mechanism, a thumb knuckle assembly and a second fingertip assembly. The contradiction between fine operation and flexibility of a traditional dexterous hand is broken through, and the grabbing adaptability and operation reliability of the dexterous hand are remarkably improved. According to the variable-rigidity finger assembly, the rigidity of each finger of the variable-rigidity finger assembly is adjusted in real time according to the characteristics of a grabbed object through the magneto-rheological regulation and control technology, and the problem that the dexterous hand lacks rigidity controllability is solved. The thumb assembly can be independently bent, regulated and rotationally adjusted, the hand movement freedom degree and operation flexibility are further expanded, and the requirements of multiple fields for multiple functions and high adaptability of the dexterous hand are met.

The invention relates to a variable resistance force feedback hand exoskeleton system and a control method thereof. The system comprises a thumb base which comprises a thumb fixing support used for fixing the thumb, a plurality of shaft rod fixing bases rigidly connected with the thumb fixing support and a posture sensor used for obtaining the overall relative posture of the hand. The system further comprises a plurality of finger tip moving resistance mechanisms, and each finger tip moving resistance mechanism comprises a shaft rod, a finger tip moving resistance mechanism, a finger tip moving resistance mechanism, a finger tip moving resistance mechanism and a finger tip moving resistance mechanism, wherein the lower end of the shaft rod is rotationally hinged to a corresponding shaft rod fixing base on the thumb base; the finger tip main body is arranged on the shaft rod in a sliding manner; the finger fixing ring is fixed on the finger tip main body and is used for fixing fingertips of an index finger, a middle finger, a ring finger or a little finger; the variable resistance assembly is arranged on the finger tip main body and is used for extruding the shaft rod to generate variable resistance; the position sensor is fixed to the finger tip body and used for detecting the position of the finger tip body relative to the shaft rod in real time. According to the technical scheme, the hand motion freedom degree and the resistance feedback authenticity in virtual reality interaction can be improved.

The application discloses a hand exoskeleton for capturing finger movement and a finger configuration reconstruction method, and can realize full-space precise movement capturing of human fingers and reconstruction of finger configurations. The hand exoskeleton is composed of a plurality of serial kinematic chains and a common base, each serial kinematic chain comprises one active joint and five passive joints, and a magnetic rotation angle sensor is arranged on the joint to realize movement capturing of the end of the serial kinematic chain. The serial kinematic chain forms a parallel structure with a human finger to realize six-degree-of-freedom precise movement capturing of the end of the human finger. Captured human finger tip movement is reconstructed through a circular arc fitting algorithm, and the finger movement configuration can be displayed in real time in a three-dimensional visual simulation environment. According to different requirements, the number of serial kinematic chains on the base can be increased or reduced, and hand movement can be reproduced in real time in a three-dimensional simulation environment, and experience is improved.

The invention discloses an intelligent control auxiliary finger device for fine finger exercise training, and relates to the technical field of hand exercise training, the intelligent control auxiliary finger device comprises a base and a wrist frame fixedly arranged on the base, and an auxiliary assembly for multi-mode cooperative composite training is arranged in the wrist frame; a supporting frame used for supporting the wrist of a user is arranged at the movable end of the auxiliary assembly, a frame plate is arranged on the supporting frame, a training assembly is arranged in the frame plate, the movable end of the training assembly is provided with four first fingerstalls and a second fingerstall which are used for being arranged on the four fingers and the thumb in a sleeving mode, and a sponge ball used for hot compress of the palm of the patient is arranged on the frame plate. At least one pressing plate which is pushed by a user to trigger the training assembly is arranged in the auxiliary assembly, three training modes are integrated, three-dimensional space composite training of wrist rotation, palm pitching and finger grabbing is combined, the training is directly benchmarked with complex actions in daily life, and the functional value of rehabilitation is improved.

The invention relates to the use of a marking instrument (10; 10a), such as a ruler, set square, or protractor, to refine hand movements and increase the confidence and comfort of individuals who have difficulty automating hand gestures in time and space. The instrument comprises a main body (12) with one or more lateral marking elements (22), with one or more sliding systems (14, 15) and one or more gripping systems (16), and is constructed in several blocks. The main body (12) associated with the gripping system(s) (16) and the lateral marking elements (22) associated with the sliding system(s) (14, 15) are separate blocks, and the main body is actuated by pressure to perform a gripping action. Figure for the abstract: Fig. 14