311 results about "Prosthetic limb" patented technology

The invention discloses an intelligent artificial limb movement intention recognition method based on multi-modal information and a D-S evidence theory, and belongs to the technical field of artificial intelligence, mode recognition and intelligent artificial limb control. According to the method, firstly, electromyographic signals and kinematics signals of user limbs and three-dimensional point cloud information of the terrain where the user limbs are located are synchronously collected; filtering, segmenting and time domain / frequency domain feature extraction are carried out on the physiological signals, rotation correction and dimension reduction are carried out on the environment point cloud, and a binary image is generated; using a deep learning model to identify a preliminary motion mode from the physiological features and identify a terrain category from the environment image; and finally, inputting the two recognition results as evidence bodies into an improved D-S evidence theory model for decision-level fusion, and outputting a final comprehensive motion intention recognition result. According to the method, the human physiological signal and the external environment information are fused, so that the ambiguity and uncertainty of single information source identification are effectively solved, and the intention identification accuracy and adaptability of the intelligent artificial limb in different complex scenes are remarkably improved.

Disclosed are prosthetic systems comprising a powered knee prosthesis and a volitional controller configured to provide control of the prosthesis to the user. The prosthetic system may be configured to enable a user to walk on smooth and / or uneven terrain and to ascend and / or descend stairs. The volitional controller may be configured in a contact state when the prosthesis is in contact with a ground surface and a no contact state when the prosthesis is lifted from the ground surface. When in the contact state, the controller may output a knee torque signal for controlling the powered knee of the prosthesis. The knee torque signal may be based on a target knee torque determined by the knee orientation and the torque measured at the ankle of a prosthetic foot. When in the no contact state, the controller may output a knee torque signal based on a desired knee position.

The invention belongs to the field of intelligent prostheses, and particularly relates to an intelligent prosthetic control algorithm based on EMG electromyographic signals, which comprises the following steps: S1, electromyographic signal acquisition: acquiring the electromyographic signals of the forearm of a user through a multi-channel surface electromyographic sensor, the electromyographic signals being sEMG signals; s2, signal preprocessing; according to the time-frequency feature enhancement and mixed learning architecture, the system can realize more accurate and stable small sample gesture recognition, the processing capability and classification performance of the non-stationary electromyographic signals are remarkably improved, and in addition, due to the fact that deep features and discriminative manual features are fused and a lightweight network and a multi-modal decision mechanism are combined, the recognition efficiency of the non-stationary electromyographic signals is improved. A user can realize reliable and smooth gesture interaction in a low-delay and low-data-dependence embedded environment, and does not need to depend on a large amount of labeled data or complex computing resources, so that the whole method has higher adaptability and practicability.

The present disclosure describes self-adjusting sockets for lower limb prostheses in which each step transmits motion to a resilient resistive element coupled to an actuator configured to cycle between a rest position and an actuated position. The resistive element can transmit the motion to the actuator to cycle the actuator. Each cycle of the actuator acts through a mechanical linkage to tighten the socket around the residuum, until a desired threshold tightness on the residuum is reached. After the threshold tightness is reached, the resistive element yields and absorbs the motion rather than transmitting the motion, so that the actuator ceases to cycle on each step, preventing further tightening beyond the threshold.

The invention discloses a gesture recognition system and method based on multi-channel mixing of EMG, FMG and IMU. The system comprises a multi-channel signal acquisition module, a signal conditioning and synchronous acquisition circuit, a data preprocessing module, a deep neural network fusion recognition module and an output interface module. By integrating a surface electromyogram, a muscle force diagram and an inertial measurement unit, synchronous acquisition of multi-modal physiological signals of the forearm of a human body is realized; a double-flow convolution-time sequence attention fusion network (DCTANet) is adopted for feature extraction and classification decision making, and neuromuscular activity, muscle mechanical response and limb movement information are effectively fused. The accuracy, robustness and real-time performance of gesture recognition are improved, and the method is suitable for the fields of intelligent prostheses, wearable interaction, rehabilitation training and the like. The system is compact in structure, supports embedded deployment, and has a good practical prospect.

The invention provides a bionic lower limb robot artificial limb test system and method. The system comprises a humanoid robot test main body, a load module, a support module and a data acquisition module, the humanoid robot testing main body at least comprises human lower limb joints and is used for simulating human lower limb walking; the human body lower limb joint comprises at least one of a knee joint, an ankle joint and a foot modularization, and at least part of the human body lower limb joint can be replaced by an artificial limb to-be-tested unit, so that the humanoid robot test main body can drive the artificial limb to-be-tested unit to carry out a walking test; the load module is arranged on the humanoid robot test main body and is used for providing a target load for the artificial limb to-be-tested unit; the supporting module is used for providing a walking road on which the humanoid robot testing main body can carry out a walking test; the data acquisition module is used for monitoring test parameters when the artificial limb to-be-tested unit is subjected to a walking test. According to the invention, a real use scene can be simulated, and accurate detection of the multi-dimensional performance of the artificial limb can be realized.

Methods, systems, and / or apparatuses are provided for providing multi-joint assistance for and / or resistance against leg movement of a user. The assistance may be provided to a paretic leg or a prosthetic leg of the user. Kinematic data associated with the paretic or prosthetic leg of the user may be received. The data may include one or more of velocity data, position data, orientation data, or acceleration data for differing portions of the paretic or prosthetic leg. A current phase of a gait motion for the paretic or prosthetic leg may be determined based on the kinematic data. One or more of electrical stimuli or motorized assistance or resistance may be provided to the paretic leg, prosthetic leg, or the remaining portion of the amputated leg based on the current phase of the gait motion of the paretic or prosthetic leg.

Disclosed are prosthetic systems comprising a powered knee upper leg prosthesis and a volitional controller configured to provide control of the prosthesis to the user. The prosthetic system may be configured to enable a user to climb a set of stairs. The prosthetic system may be activated by the activation of an EMG signal source, such as the biceps femoris muscle of the upper leg. The volitional controller of the prosthetic system may be further configured to receive a ground state signal and / or an IMU signal to determine a target knee torque for operating the powered knee of the prosthesis.

The invention provides a brain-computer interface system and an action control method of a bionic artificial limb, and relates to the technical field of signal processing, the system comprises an optimization scheduling module used for constructing a target model, and determining an acquisition channel subset, a feature path selection table and a network parameter sparse template according to the target model; the signal acquisition and processing module is used for acquiring a multi-modal neural signal according to the acquisition channel subset and processing the multi-modal neural signal; the intention prediction module is used for generating a candidate intention set according to the feature path selection table and the processed multi-modal neural signal; the intention decision module is used for scoring each candidate intention in the candidate intention set according to the network parameter sparse template to obtain a confidence score of each candidate intention and determine a target intention; the intention prediction module, the intention decision module and the optimization scheduling module are integrated on a collaborative chip platform, and the defects caused by the existing recognition accuracy and the use of a split-type hardware architecture are overcome.

The invention discloses an intelligent man-machine interaction artificial limb system for high-position upper limb amputation disabled people and a control method of the intelligent man-machine interaction artificial limb system. The system comprises a multi-degree-of-freedom artificial limb mechanism; the multi-mode sensing unit is used for collecting an interaction intention signal of a user and environment visual information; the intelligent decision-making unit is used for identifying a user task intention based on the interaction intention signal and the environment visual information and generating a high-level task plan; the task execution unit is used for driving the multi-degree-of-freedom artificial limb mechanism to execute operation according to the high-level task plan; wherein the task execution unit comprises a double-arm cooperative control module, and the double-arm cooperative control module is configured to adopt a cooperative control strategy based on the Stackelberg game to enable the prosthetic mechanism to actively generate a motion instruction coordinated with a sound arm of a user. According to the intelligent man-machine interaction artificial limb system and the control method thereof, natural, efficient and high-generalization auxiliary operation tasks can be achieved, and the system and the method are particularly suitable for daily use requirements of severe disabled people.

The invention discloses an artificial limb receiving cavity motion data acquisition device, and belongs to the field of data acquisition. The device comprises an inertial sensor used for collecting acceleration information and angular velocity information of an artificial limb receiving cavity; the data storage module is used for storing data information acquired by the inertial sensor; the data processing module is used for preprocessing the information stored in the data storage module; and the power supply module is used for supplying power to the inertial sensor, the data storage module and the data processing module.

The application discloses a single-shaft active and passive mixed driving intelligent artificial knee joint structure with energy recovery function, which comprises a joint rotating module, a gear transmission module, a hydraulic damping module, a rack and a motor. The gear transmission module comprises a primary bevel gear transmission system, a secondary gear transmission system, a synchronous belt wheel transmission assembly and a transmission rack. The motor is fixed on the transmission rack. In the active stage, the motor provides an active driving torque for the knee joint through the gear transmission module and the joint rotating module. In the passive stage, the joint rotating module transmits a passive torque of the knee joint to the motor through the gear transmission module, drives the motor to rotate, so that the motor generates electricity to recover energy, and the hydraulic damping module provides a damping torque to ensure the stability of the knee joint. In various use occasions, the required damping or driving torque can be obtained, the power consumption of the motor can be reduced by recovering the passive torque of the knee joint in the passive stage, and the working endurance of the intelligent artificial limb is improved.

A prosthetic or orthotic device (100) is described for implementation of a locomotion activity. The prosthetic or orthotic device (100) may cause an actuator (228) to perform a provide a first torque. Based on the first torque and one or more values of one or more parameters, the prosthetic or orthotic device (100) may perform a first portion of a flexion action. Subsequent to or during performance of the first portion of the flexion action, the prosthetic or orthotic device (100) may determine an angle associated with the prosthetic or orthotic device (100). Based on the angle, the prosthetic or orthotic device (100) may perform an adjustment of the one or more parameters. Based on the adjustment, the prosthetic or orthotic device (100) may perform a second portion of the flexion action. For example, the prosthetic or orthotic device (100) may perform the second portion while gradually increasing the one or more values.

Method for visualizing multiple sensor signals derived via electrodes from a limb or amputation stump to detect muscle activity, comprising the following steps: • Each signal is assigned a display direction and a display amount • The display direction represents exactly one signal • The displayed value represents the intensity of motor activity of either the respective muscle or its nerve. • The direction and magnitude of all signals are simultaneously displayed in real time on a display device as a single graphical object. • On the display device, reference objects that were saved during previous analysis sessions are displayed simultaneously with the object. • Reference contractions are used as reference objects. • Simultaneously with the visualization, a prosthetic or orthotic device is controlled with the signals, whereby the reference objects are used to parameterize the prosthetic or orthotic control.

The application relates to a compact active artificial knee joint with a torque adjusting device, which comprises a knee joint module, a receiving cavity connecting block, a lower leg connecting piece and a torque adjusting device, wherein the torque adjusting device comprises a spiral spring, a bent spring groove and the like, the knee joint module comprises a knee joint shell, a knee joint shaft center, a knee joint stator sleeve end cover and the like, one end of the spring is fixed at the upper receiving cavity connecting lug through an opening on the motor stator sleeve end cover, and the other end is fixed in the bent spring groove at the position of the motor stator sleeve end cover and the knee joint shaft center. The torque adjusting device can realize torque assistance and adjustment according to the angle size and direction of the limb rotation; meanwhile, the driving peak torque of the motor can be reduced, the size and the maximum torque of the driving motor are smaller due to the fact that the artificial limb needs to be easily worn, energy consumption and space are saved.

This utility model relates to a hand with a gripping thumb, aiming to solve the problems of existing prosthetic hands, such as limited functionality, complex structure, difficult maintenance, non-removable components, and excessive weight. The hand with a gripping thumb includes a palm shell, a thumb mechanism, a return spring, and a control cable. The palm shell is a hollow structure with an internal hinge seat and a long slot. The thumb mechanism consists of a thumb head, a hinge shaft, and a drive arm, and is installed inside the palm shell. The return spring connects the drive arm and the fixed seat, and the control cable connects to the drive arm and extends from the wrist, achieving the swinging gripping of the thumb head through its reaction with the return spring. This utility model has a simple structure, few parts, low cost, and is easy to maintain. The palm cover of the palm shell is removable, facilitating repair and replacement, and reducing maintenance costs. The overall design is lightweight, reducing the burden on patients and providing a practical, economical, and reliable solution for amputees, meeting their diverse daily needs.

A prosthetic leg 10 comprises: a thigh connection part; a lower leg section that is connected to the thigh connection part and that is provided rotatably around a knee shaft; a load acquisition unit 130 that acquires a load applied to the prosthetic leg via a thigh section; a knee angle acquisition unit 110 that acquires a knee angle formed between a shaft of the lower leg section and a shaft of the thigh section; and a rotation resistance control unit 100 that controls the rotation resistance of the knee shaft. When the knee angle exceeds a prescribed bouncing angle, the rotation resistance control part 100 executes bouncing control for strengthening the rotation resistance so as to limit a further increase of the knee angle, determines, on the basis of the load acquired by the load acquisition part 130 during execution of the bouncing control, whether the position of the load is in an end position state within a prescribed end range, and ends the bouncing control when a continuation time of the end position state exceeds a prescribed time.

AI-Enabled Smart Prosthetic Limb with Bio-Mimetic Structural Design

The utility model relates to the technical field of prostheses, and discloses an artificial limb auxiliary tool autonomous rapid replacement device, which comprises a device main body and an artificial limb main body, the device main body is provided with a plurality of placing grooves along the axial direction, the placing grooves are internally provided with arm connecting ends, and the arm connecting ends are connected with the device main body through structures such as a connecting rod, a control pedal and a special-shaped sliding rod. Therefore, when an auxiliary tool needs to be replaced, the butt joint block on the artificial limb body can be in butt joint with the interior of the butt joint groove in the connecting end of the arm to be replaced, the control pedal is treaded down, the connecting rod is driven by the control pedal to vertically descend, locking between the connecting end of the arm and the containing groove is relieved, meanwhile, the special-shaped sliding rod loses butt joint of the connecting rod, and the auxiliary tool is replaced. The special-shaped sliding rod can be pushed to abut against the inner wall of the inner cavity through the compression spring, the self-locking block on the special-shaped sliding rod is inserted into the self-locking groove in the butt joint block, locking and fixing between the arm connecting end and the artificial limb body are achieved, and on the contrary, separation between the artificial limb body and the arm connecting end can be achieved.

The application discloses a novel human-simulating flexible parallel wrist joint with redundant driving, and has the characteristics that the joint comprises a moving platform (1), an intermediate branch chain (2), a first driving branch chain (3-1), a second driving branch chain (3-2), a third driving branch chain (3-2) and a base (4). The application is based on bionics and bionically designs the bony structure and muscle system of a human wrist joint, adopts a rope driving mode, has a high stiffness bearing ratio, is driven redundantly and has good human-machine interaction performance. The joint can be pulled by three motors through external ropes, converts the rotation of the motors into the movement of the ropes through a movable pulley, realizes 2-DOF (degree of freedom) movement, and is suitable for occasions such as the end wrist joint of an industrial robot, a human-simulating arm wrist joint and an intelligent prosthesis.

The utility model discloses an artificial limb socket with a neck bush, and relates to the technical field of artificial limb sockets. Comprising an artificial limb receiving cavity, and a threaded hole is formed in the bottom of the artificial limb receiving cavity; the neck bush is used for being arranged on the stump in a sleeving mode, a metal support is arranged at the bottom of the outer side of the neck bush, and a lock pin is detachably connected to the center of the bottom of the metal support; the anti-damage bottom support structure is arranged at the lower end part of the neck bush and is connected with the metal support; and the outer side of one end of the special-shaped lock, which is provided with a lock hole for inserting the lock pin, is provided with an external thread and extends into the threaded hole to be connected with the artificial limb receiving cavity through threaded connection. The neck bush is detachably connected into an artificial limb receiving cavity through the special-shaped lock, wearing of an artificial limb is facilitated, meanwhile, the stump is better supported through the anti-damage bottom support structure at the rigid connecting position of the bottom of the neck bush, the stump is prevented from being hurt due to the fact that reverse acting force is generated on the stump, and the leg is prevented from being hurt.

This method for providing a user interface for manufacturing a prosthesis comprises: providing a guide image visualizing the inner surface of a prosthesis to be put on a prepared tooth; providing a parameter adjusting unit for adjusting a plurality of parameters for generating the prosthesis; displaying, on the guide image, a selected parameter image for explaining a parameter selected by a user from among the plurality of parameters; and generating a 3-dimensional image of the prosthesis on the basis of data set by the parameter adjusting unit.

The present invention relates to a torque connector device for an osseointegration prosthetic limb (OPL) system. The device features a body with a base portion that anchors and restrains movement, and includes a first spindle bushing positioned between the base and spindle release body to facilitate axial rotation. A second spindle bushing prevents unwanted pivoting of the first bushing. The spindle release body is centrally aligned to lock rotational alignment and connect the abutment assembly. A threaded connection between the base portion, calibration cap, and washers creates a locked state under normal conditions, maintaining stability across all axes. When torque exceeds a predetermined threshold, the first and second washers deform, disengaging the release pad and spindle release body, and allowing rotational movement to an unlocked state.

The application relates to an intelligent artificial limb system for identity authentication and myoelectric text conversion and belongs to the technical field of robots; the intelligent artificial limb system solves the problem that the intelligent artificial limb system in the prior art cannot realize the functions of myoelectric activation, text conversion and identity authentication; the intelligent artificial limb system comprises, which are electrically connected in sequence, a myoelectric signal detection sensor, a myoelectric signal recognition control module, a motor driving device and a bionic hand device; wherein the myoelectric signal detection sensor is used for detecting myoelectric signals and sending the myoelectric signals to the myoelectric signal recognition control module; the myoelectric signal recognition control module is used for recognizing and processing the received myoelectric signals, and mode conversion is carried out according to the myoelectric signal recognition result, so as to realize identity authentication, daily action control and conversion of myoelectric signals into texts; the motor driving device is used for controlling the bionic hand device to make actions corresponding to the myoelectric signals based on the recognition result of the myoelectric signal recognition control module, so as to realize daily action control.

A method of cooling a prosthetic socket includes placing a thermally conductive heat spreader including a curved shape portion in contact with a residual limb of a user, placing a heat extraction subsystem through a wall of the prosthetic socket and coupling the heat extraction subsystem to the thermally conductive heat spreader, and operating the heat extraction subsystem to drive heat from inside the prosthetic socket to an external environment using the thermally conductive heat spreader and the heat extraction subsystem such that a desired temperature is maintained in the prosthetic socket.

A low extensibility material for use in prosthetics and orthotics. The low extensibility material is adhered to the fabric portion of a prosthetic liner or orthotic liner either internally or externally and limits the longitudinal movement while allowing for transversal movement. The customizable nature of the invention allows for shaping and personalization depending on the needs of the user.