148 results about "Joints movement" patented technology

The invention discloses a knee bone joint state recognition method and system based on artificial intelligence, and relates to the technical field of image analysis, and the method comprises the steps: obtaining multi-source medical image data of a knee joint region of a patient, carrying out the spatial registration and standardization preprocessing, and constructing a three-dimensional structure model of a knee joint after unifying a coordinate system; establishing a mapping relation between joint movement and an anatomical structure by combining knee vibration and behavior characteristic data collected by a patient in a specific movement state, extracting joint key geometric and mechanical parameters from the three-dimensional structure model, and fusing the joint key geometric and mechanical parameters with synchronously collected vibration behavior characteristics; and performing state recognition on the fused multi-source features based on an intelligent recognition model, and outputting a health state label of the knee joint. According to the invention, more accurate and more comprehensive knee joint health state identification can be realized, the accuracy and reliability of an identification result are effectively improved, and the timeliness of disease discovery and the scientificity of intervention are enhanced.

The invention discloses an integrated management system and method for postoperative care of orthopedic patients, and relates to the technical field of medical treatment. Comprising a bone mineral density dynamic monitoring value, six-dimensional mechanical parameters of a joint movement track, emotion spectrum characteristics in voice interaction, microenvironment temperature and humidity changes collected by wearable equipment and skin surface pressure distribution; inputting the recovery data into a multi-modal decision-making model based on orthopedic biomechanics improvement, and generating a nursing scheme including a skeleton stress safety interval, a virtual rehabilitation scene dynamic parameter and an interdisciplinary intervention priority; the scheme parameters are dynamically optimized through a layered reinforcement learning framework special for the orthopedics department, and the deformation logic of the 3D printing brace and the correction strategy of the nursing robot are synchronously controlled; based on the postoperative complication space-time prediction map, a multidisciplinary collaborative response instruction strictly matched with the rehabilitation stage of the patient is triggered.

The application relates to a multi-arm mobile robot control system, which comprises a robot, each joint position of the mechanical arm of which is configured with a joint controller for driving joint movement; a robot controller for realizing the operation of joint motors according to control quantities; a joint position hard analysis unit for calculating the coordinate positions of each joint or mechanical arm in a space coordinate system to output results; and a joint space point position trajectory constraint model for forming a correction quantity of a joint and superimposing the correction quantity on an original control quantity of the joint to become a final control quantity for controlling the joint, the final control quantity being used for output to the joint controller to realize joint movement. The application provides a multi-arm mobile robot control system, which effectively realizes the cooperative control among multi-arm robots, avoids the mutual collision among mechanical arms, improves the avoidance and dynamic response speed of the mechanical arms, and improves the agility of robot actions.

The invention discloses a mechanical arm state limited preset time point control method and system, and relates to the technical field of robot control, and the method comprises the steps: obtaining a joint position tracking error and a joint speed tracking error based on a joint motion state and an expected trajectory of a mechanical arm; based on constrained system states corresponding to the joint position tracking error and the joint speed tracking error, nonlinear transformation is carried out on the joint position tracking error and the joint speed tracking error through an unconstrained state function, and an equivalent unconstrained virtual error variable is constructed in combination with coordinate transformation; based on the unconstrained virtual error variable, designing a sectional sliding mode variable; and designing a second-order reaching law based on the sectional sliding mode variable to form a closed-loop dynamic state, and solving based on the closed-loop dynamic state to obtain a control torque so as to control the mechanical arm joint. According to the method, the trajectory tracking error of the mechanical arm can be converged at the moment specified by a user, the system state is ensured to meet strict physical constraints in the whole process, and the method can be applied to accurate trajectory control in a complex task scene.

The invention relates to the technical field of electric digital data processing, in particular to an intelligent early warning method and system for joint rehabilitation medical equipment, and the method comprises the steps: obtaining the heart rate and joint motion resistance of a user at a plurality of historical moments and in the rehabilitation training process at the current moment; fitting based on the joint movement resistance of the user at multiple historical moments to obtain a resistance safety baseline, and determining a resistance threshold value according to a mean value and a standard deviation of the resistance safety baseline within a set time; if the heart rate of the user at the current moment exceeds a set first threshold value or the joint movement resistance of the user at the current moment exceeds a resistance threshold value for a preset duration, triggering an alarm and stopping rehabilitation training. According to the invention, the problem that self-adaptive switching and intensity optimization adjustment of training modes cannot be realized is solved.

The present invention discloses a key joint motion estimation based method for estimating continuous human postures. A motion estimation block matching algorithm is applied to human key joint tracking, so as to obtain continuous human posture results. Meanwhile, the results are continuously corrected by using a deep neural network based human posture estimator. The present invention may estimate the continuous human postures in a video stream, where the human postures are specifically embodied as coordinate positions of human joints in a video frame. Compared with a posture estimation method completely relying on a deep neural network, the posture estimation method provided by the present invention has the advantages of high frame rate, low hardware requirements, and sequential continuity of recognition results; and compared with a posture estimation method completely relying on a motion estimation algorithm, the present invention may correct a cumulative error, to improve the estimation accuracy.

The invention provides a multi-scene body position conversion-based standing-up assisting control method and system for the elderly suffering from stroke. According to the method, firstly, the standing-assisting device is controlled to obtain a fusion sensing result composed of body pressure distribution data and joint movement data, multi-feature coupling analysis is carried out to generate a combined recognition conclusion containing a body position state and a scene type, and then dynamic mode mapping is carried out according to the combined recognition conclusion. Outputting a target control mode matched with the current scene type and the body position, and finally performing power instruction synthesis by utilizing the target control mode to generate a cooperative control signal for driving the standing assisting equipment to execute body position conversion; according to the technical scheme provided by the invention, accurate conversion from standardized control to personalized control is realized, the suitability and the user experience of the standing assisting process are improved, the uncertainty and the individual difference in actual operation are overcome, and the stability, the safety and the adaptability of the body position conversion process are improved.

The invention relates to the technical field of data processing, in particular to a rehabilitation training control method and system based on a flexible hand joint rehabilitation glove, and the method comprises the steps: obtaining an individualized physiological parameter baseline of a patient; real-time data of a patient in the rehabilitation training process are collected through a multi-modal sensor array on the flexible glove, the active participation degree, the joint movement smoothness and the muscle fatigue degree of the patient are calculated based on the real-time data, the active movement intention of the patient is recognized, and a real-time rehabilitation state evaluation result of the patient is obtained; generating a control instruction through an adaptive control engine according to a preset personalized rehabilitation scheme and the real-time rehabilitation state evaluation result; the generated control instruction is sent to a driving control circuit so as to control a driving unit to execute corresponding bending or stretching actions and assist the patient in completing target training actions; according to the invention, personalized, self-adaptive and quantitative evaluation of rehabilitation training can be realized, and the efficiency and effect of hand rehabilitation training are improved.

The invention provides a virtual reality-based joint movement injury rehabilitation mode generation method and a virtual reality-based joint movement injury rehabilitation mode generation system, and relates to the technical field of virtual reality, and the method comprises the following steps: analyzing a rehabilitation path according to movement joint injury data of a user; performing rehabilitation limb posture decomposition based on the rehabilitation analysis path to generate a rehabilitation analysis view; a multi-modal sensor unit is used for collecting rehabilitation feedback actions of a user, and matching recognition of physiological parameters and rehabilitation constraints is carried out in a rehabilitation analysis view; and according to the posture deviation feedback, performing amplitude and muscle power guidance feedback of the rehabilitation limb posture, and synchronously performing virtual reality visual display. The technical problem that in the prior art, most VR rehabilitation systems mainly pay attention to visual feedback, so that only the motion appearance can be evaluated, and the compensatory motion mode cannot be recognized is solved, real-time monitoring and guidance on the force exerting correctness are achieved through combination of posture decomposition and physiological parameter projection, and the effect that the correctness of force exerting is improved is achieved. Therefore, the compensatory motion mode is effectively blocked.

The invention relates to the technical field of path optimization, in particular to a multi-axis robot path planning optimization method and system, and the method comprises the following steps: collecting the current position and the start-stop interval of a multi-motion-axis joint, calculating the motion distance of each joint, converting the motion distance into an interval occupation ratio, and generating an initial path point through the interpolation of the current position; the method comprises the following steps of: selecting a plurality of path point joint combinations, performing occupation proportion comparison on the plurality of path point joint combinations to determine a dominant constraint direction, performing mapping cutting on other joint motion ranges according to a residual interval proportion, screening path points meeting constraint conditions, and verifying path sequence consistency and joint displacement continuity to form an optimized motion path of the robot. Through multi-motion-axis joint interval proportional description, an interval occupation state is introduced to participate in path screening, a dominant constraint direction is determined, and other joint intervals are mapped and cut, so that multi-axis motion proportions are coordinated, invalid displacement is reduced, and collaboration and motion smoothness are improved.

The disclosure related to methods and systems for image data analysis for objectively analyzing joint motion data. In one embodiment, the methods and system disclosed herein use automated methods to capture image data, extract motion data, and determine an objective score for one or more joints in one or more motions. The system and methods disclosed herein comprise a motion capture system with one or more image capture devices to obtain motion data for a subject and using one or more regression models and analysis techniques, various objective scores can be generated related to the subject's joint motion.

The present application provides a joint motion data adjustment method, device and electronic device, which perform dynamic correction on the joint motion data based on spring-damper system modeling, thereby achieving smooth denoising of the joint motion data while well simulating real human body movement, so that the adjusted joint motion data has a higher degree of naturalness when driving the virtual model to move.

The invention relates to the technical field of robots, and discloses a human body tumble protection method and device, an exoskeleton robot and a medium, and the method comprises the steps: obtaining multi-modal motion data, collected by a sensor in real time, of a user; inputting the multi-modal motion data into a tumble identification model for identification and classification to obtain a tumble type probability of the user; if the tumble probability is greater than a preset safety threshold, determining that the user is in a tumble trend, and generating a variable impedance control instruction matched with the target tumble type according to a preset strategy library; and determining a rigidity parameter and a damping parameter of a target joint motor according to the variable impedance control instruction, and determining a target output torque based on the joint motion data, so that the target joint motor performs fall protection on the user based on the target output torque. The fall type can be accurately recognized, flexible buffering can be achieved, and then the injury risk of a user is remarkably reduced.

This invention relates to a humanoid robot, specifically a parallel rotating mechanical joint based on a ring-shaped guide rail, mimicking the rotation of a human neck. The aim is to provide a parallel rotating mechanical joint based on a ring-shaped guide rail to achieve three degrees of freedom in the movement of a biomimetic human neck joint while ensuring high rigidity and motion accuracy. Furthermore, the joint features a simplified structure, good support performance, and sufficient movement space for the neck joint. The technical solution is a parallel rotating mechanical joint based on a ring-shaped guide rail, characterized by: a head motion platform, a neck ring-shaped guide rail base, and three PSS (Personal Stability Support) link branches connected in parallel between the head motion platform and the neck ring-shaped guide rail base; the center of the head motion platform and the center of the neck ring-shaped guide rail base are connected by a composite rotating shaft.

The embodiment of the utility model discloses a hip joint motion simulation device, which comprises a crotch back cushion, a first supporting plate, a first mounting plate and a first driving mechanism, and is characterized in that the crotch back cushion, the first supporting plate and the first mounting plate are sequentially and oppositely arranged along a first horizontal direction, and the crotch back cushion is mounted on the first supporting plate; the middle of the supporting plate is hinged to the first mounting plate through a first rotating shaft arranged in the vertical direction, the first driving mechanism is arranged on the first mounting plate, the driving end of the first driving mechanism is movably connected with the first supporting plate through a connecting rod, and one end of the connecting rod is hinged to the driving end of the first driving mechanism; the other end of the connecting rod is hinged to one end of the first supporting plate, and the first driving mechanism is used for linearly driving the first supporting plate to rotate around the first rotating shaft in the first horizontal direction so as to drive the crotch back cushion to swing front and back. According to the embodiment of the invention, the hip joint of the patient can be driven to simulate the motion state when the lower limbs walk.

Systems and methods for providing assistance with human motion, including hip and ankle motion, are disclosed. Sensor feedback is used to determine an appropriate profile for actuating a wearable robotic system to deliver desired joint motion assistance. Variations in user kinetics and kinematics, as well as construction, materials, and fit of the wearable robotic system, are considered in order to provide assistance tailored to the user and current activity.

The invention discloses a rehabilitation treatment evaluation method and system based on wearable equipment, and relates to the technical field of medical rehabilitation. The system comprises a wearable sensing module, a wireless communication module, a cloud data processing module, a man-machine interaction module and an auxiliary stimulation module. The wearable sensing module collects joint movement, muscle movement and stress parameters in a non-invasive mode. According to the method, through closed-loop processes of equipment preprocessing and personalized configuration, adaptive model training, real-time data acquisition, cloud quantitative evaluation and multi-dimensional feedback adjustment, full-chain coverage of'perception-analysis-evaluation-feedback 'of rehabilitation treatment is realized. According to the method, the defect that a cognitive movement therapy lacks quantitative indexes is overcome, the problems that traditional rehabilitation evaluation is subjective and a sensor can only detect and cannot assist in treatment are solved, rehabilitation treatment standardization, individuation and high efficiency are achieved, the labor cost is reduced, the rehabilitation quality is improved, and the method is suitable for rehabilitation scenes such as cerebral apoplexy and movement injury.

The utility model discloses a simulation dynamic performance monkey robot device which comprises a neck assembly which is arranged on a base trunk assembly and can twist and pitch, a head assembly which is arranged on the neck assembly and can shake heads and nodding heads, and the head assembly is provided with an opening and closing mouth component and a blinking eye component. The left arm assembly and the right arm assembly are connected to the two sides of the base trunk assembly and can swing front and back, twist big arms and bend elbows, and all the assemblies are wrapped with monkey skin models. The device is simple and ingenious in overall structure and reliable in performance, multi-degree-of-freedom and multi-joint movement can be achieved, and the problems that in the performance process of simulation primates, joints are stiff, actions are stiff, and the expressive force is insufficient are solved.

The invention provides a reconfigurable parallel mechanism capable of switching joint rehabilitation modes and a design method thereof.The reconfigurable parallel mechanism comprises a first motion branch chain, a second motion branch chain, a third motion branch chain, a movable platform and a fixed platform, and the movable platform is connected with the fixed platform through the first motion branch chain, the second motion branch chain and the third motion branch chain; the first motion branch chain and the second motion branch chain are both of a CRC structure, the third motion branch chain is of a CCC structure, and motion pairs, fixedly connected with the movable platform and the fixed platform, of all the motion branch chains are vertically symmetrical along the middle plane. By means of rapid switching of a two-rotation and one-movement ankle joint rehabilitation mode and a two-movement and one-rotation knee joint rehabilitation mode, configuration reconfiguration of the parallel mechanism is achieved, operation is simple, the motion trail of the reconfigurable parallel mechanism coincides with the joint motion axis, and the parallel mechanism has the advantages of being high in rigidity and precision.

Provided is an electronic prosthetic hand that detects and operates hand movements. The electronic prosthetic hand may include a prosthetic hand including a finger unit capable of joint movement and a control unit that controls the finger unit, a first sensor module positioned on a user's finger, a second sensor module positioned on the back of the user's hand, and a gyro sensor provided in each of the first and second sensor modules to measure displacement according to a change in the positions of the first and second sensor modules. The electronic prosthetic hand can be used more precisely because the first and second sensor modules detect the movements of the user's finger and back of the hand, respectively, and implement joint movements of the finger unit based on the displacement difference values according to the movements of the finger and back of the hand.

The invention discloses an upper limb exoskeleton adaptive control method based on multi-modal data fusion, and relates to the technical field of upper limb exoskeleton control. According to the upper limb exoskeleton self-adaptive control method based on multi-modal data fusion, multi-modal data such as user electromyographic signals, joint movement signals and motor output torque time sequence data are obtained; a human-computer interaction torque observation set is generated through an upper limb exoskeleton reverse power model in combination with joint movement signals and motor output torque time sequence data; based on the observation set, carrying out adaptive fusion on the electromyographic signals and the joint movement signals to obtain a fusion weight set, and predicting a user expectation instruction; performing multi-target collaborative optimization by combining the observation set and the expected instruction to generate a control parameter set; according to the upper limb exoskeleton driving control method and system, the upper limb exoskeleton is subjected to driving control processing through the control instruction, so that the exoskeleton control precision is improved, and the upper limb fine assistance requirement is met.

This disclosure relates to a time-sharing adaptive precision assistance method, device, electronic device, and storage medium that adapts to changing target assistance needs. The method includes: calibrating and initializing sensors in the exoskeleton wearer coupling system; identifying the wearer's gait characteristics; predicting the wearer's current target assistance needs based on gait characteristics, joint interaction force characteristics, and center of mass motion characteristics, and matching joint controller parameters accordingly; establishing an exoskeleton swing phase and support phase enhancement torque controller that adaptively adjusts with joint motion amplitude and frequency; and switching the exoskeleton swing phase and support phase enhancement torque controller based on the target assistance needs, thereby achieving time-sharing adaptive assistance of the exoskeleton to adapt to changing target assistance needs. This disclosure achieves dynamic matching of the target motion position by adjusting joint controller parameters, which helps improve the exoskeleton robot's autonomous perception and efficient assistance to the wearer's target assistance needs.

A robot control method and apparatus, and a device and a medium. The robot control method comprises: on the basis of an initial point and a target point of an end effector of a robot, determining a trajectory point set; acquiring joint control information corresponding to each joint of the robot when the end effector is located at each trajectory point in the trajectory point set, wherein the joint control information comprises at least one of a joint position, a joint speed and a joint acceleration; and for a first trajectory point and a second trajectory point that are adjacent to each other in the trajectory point set, and on the basis of first joint control information corresponding to each joint at the first trajectory point and second joint control information corresponding to each joint at the second trajectory point, controlling each joint to move, such that the end effector moves from the first trajectory point to the second trajectory point.

A joint movement therapy and assistive device system. The system includes a torque profile device having a plurality of connecting components, a longitudinal axis, and a center. Each connecting component of the plurality of connecting components is disposed at a selected distance relative to the center and a selected angle relative to the longitudinal axis. The system also includes at least one segment end and a plurality of tensioning components removable secured to the plurality of connecting components of the torque profile device and the at least one segment end. The plurality of tensioning components forms an additive torque profile when coupled between the torque profile device and the at least one segment end.

The invention provides a motion analysis method and system based on image and sole contact modeling, and the method comprises the steps: reconstructing a three-dimensional posture of the motion of a subject according to recognized 2D key points, and generating a personalized skeleton model matched with the subject according to the height data of the subject; the method comprises the following steps: acquiring a pelma image of a subject, automatically generating a plurality of contact balls in a pelma region according to an extracted pelma contour shape to approximately represent each region where the pelma is in contact with the ground, and optimally setting the positions and radiuses of the contact balls according to the foot type of the subject to form a personalized pelma contact model; according to the personalized skeleton model, the joint movement data and the personalized plantar contact model, solving a ground reaction force GRF which enables dynamics to be consistent under a given kinematics condition; determining a moving path of a resultant force acting point of stress along with time according to the stress condition of each contact ball of the two feet, and calculating a track of a plantar pressure center COP. Motion analysis can be carried out based on image and plantar contact modeling.

The invention provides a multi-joint cooperative motion control method and system of a humanoid robot, and relates to the technical field of robot control, the gait phase data of the humanoid robot in different motion states are obtained, and the motion states comprise the walking state, the running state and the sudden stop state; according to the gait phase data, generating a gait phase migration matrix so as to determine a motion mode switching point, further determining a hysteresis compensation opportunity of the pneumatic artificial muscle, and performing hysteresis compensation processing on the pneumatic artificial muscle of each lower limb joint of the humanoid robot so as to obtain a joint motion state; analyzing an angle change rate and a motion acceleration parameter in the joint motion state, and generating a biological heuristic electric signal; according to the joint cooperation angle threshold value and the motion triggering moment of the biological heuristic electric signal, all the lower limb joints of the humanoid robot are driven to conduct cooperative motion, so that seamless switching of multi-mode motion is achieved, and the motion flexibility and stability are improved.

The application belongs to the technical field of robots, and discloses a motion decoupling double-path rope-driven bionic thumb device, which comprises a distal phalanx, a proximal phalanx, a metacarpal bone, a thumb base, IP joints, MCP joints and CMC joints for connecting the phalanges; the distal phalanx, the proximal phalanx, the metacarpal bone and the thumb base are connected through tendon rope transmission. The rope path for driving the IP joint does not pass through the MCP joint, and the part of the rope path across the MCP joint is wrapped by a Bowden tube assembly, so that the length of the rope path remains constant when the MCP joint moves, and the motion decoupling of the MCP joint and the IP joint is realized; the rope path for driving the MCP joint is also wrapped by a Bowden tube assembly outside, so that the length of the rope path remains constant when the CMC joint moves, and the motion decoupling of the MCP joint and the CMC joint is realized. The application has the advantages of compact structure, joint motion decoupling, precise force control, strong bearing capacity and the like.

A multi-joint control method, a controller, and a computer-readable storage medium. The multi-joint control method comprises: constructing a joint control function; on the basis of acquired desired positions of multiple joints and the joint control function, obtaining motion data of each joint; and on the basis of the motion data, controlling all the joints to move to the desired positions. By constructing a joint control function, obtaining motion data of all the joints on the basis of desired positions of all the joints and the joint control function, and controlling, on the basis of the motion data, all the joints to move simultaneously, the purpose of improving the control efficiency and coordination is achieved.

The invention belongs to the technical field of robot control, and discloses a central nervous system-based exoskeleton control method and system, and the method comprises the steps: collecting a central nervous signal in a human body, and carrying out the preprocessing of the central nervous signal, and obtaining a multi-dimensional nerve feature set; performing decoding analysis on the multi-dimensional neural feature set by utilizing a preset dynamic neural intention decoding model to obtain a human body motion intention, and generating joint motion parameters and a driving force control instruction of the exoskeleton robot by utilizing a collaborative model; and the exoskeleton robot is controlled to conduct joint movement, closed-loop feedback is constructed, and the driving force control instruction is adjusted in real time. According to the method, information loss or distortion caused by damage of a central nervous conduction pathway is effectively avoided, the adaptability to a central nervous injury patient is improved, the decoding accuracy is improved, the motion synchronization error is reduced, the control fluency and the man-machine coordination of the exoskeleton robot are improved, and the control safety of the exoskeleton robot is ensured.

The present application relates to a control method, device, robot main hand, medium and product for a robot main hand. The robot main hand includes at least four joints, and the at least four joints are connected in sequence; the at least four joints include at least one redundant joint; the method includes: obtaining the initial angles of the at least four joints, determining the angle change of the redundant joint according to the initial angles of the at least four joints and the objective function; updating the initial angles of the redundant joints according to the angle change to obtain the target angles of the redundant joints; controlling each non-redundant joint and the redundant joint according to the target angles of the redundant joints and the end position of the robot main hand. By using this method for redundant control, each joint is adjusted while ensuring that the end position remains unchanged, which can avoid connecting rod collisions and human interference, and can also prevent the main hand from approaching the singular position of the joint and the extreme position of the joint movement, thereby improving the operational flexibility of the main hand and thus improving the control flexibility of the robot.