61 results about "Wearable robot" patented technology

Exemplary task-agnostic exoskeleton control system and method are disclosed that are task-agnostic utilizing instantaneous estimates of biological joint moments from deep neural networks to assist the user movements. The exemplary control system employs multiple body sections and joints in-the-loop estimation to provide multi-joint assistance operation, e.g., within an autonomous, clothing-integrated exoskeleton. The exemplary control system may deploy a deep domain adaptation (DDA) method configured to translate human movement data between a simulated sensor domain and a real sensor domain.

The invention provides a gait trigger control method and an exoskeleton power assisting device, and relates to the technical field of wearable robotics.The method comprises the steps that original data representing user movement and postures are collected through a multi-modal sensing unit, the multi-modal sensing unit comprises an inertial measurement unit, a plantar pressure sensor, a hip joint encoder and a knee joint angle sensor; original data collected by the multi-mode sensing unit is sorted and then transmitted to the signal processing unit, and the signal processing unit carries out noise reduction and extracts characteristic signals; the extracted feature signals are transmitted to a control unit, and the control unit recognizes the gaits of the user according to the feature signals and generates control instructions corresponding to the gaits; according to the gait trigger control method, the control instruction is transmitted to the assistance execution unit, the assistance execution unit outputs the assistance torque or the foot support supporting force corresponding to the control instruction to complete gait trigger control, and the use convenience of the exoskeleton assistance device can be improved through the gait trigger control method.

1. Name of the design product: hip walking exoskeleton. 2. Use of the design product: for exoskeleton device (wearable robot). 3. Design points of the design product: in shape. 4. Picture or photograph best indicating the design points: perspective view.

This application belongs to the field of wearable robot technology, specifically providing a mechanical load-bearing exoskeleton system based on ground reaction force self-triggering. The exoskeleton system includes an upper body mechanism, a thigh mechanism, a knee joint mechanism, a lower leg mechanism, and a foot mechanism. The knee joint mechanism includes a knee joint support, a locking component, and a transmission assembly. When the foot mechanism touches the ground and the sole of the foot is compressed and deformed by the ground reaction force, the thigh mechanism slides downward relative to the knee joint support. The transmission assembly drives the locking component to slide towards the thigh mechanism and connect with it, thereby locking the knee joint mechanism. The compression deformation of the sole of the foot caused by the ground reaction force is used as a trigger signal to automatically trigger the locking of the knee joint mechanism. The knee joint mechanism can lock at any reasonable angle, so that when the wearer is going up or down slopes, climbing stairs, or bending their knees for cover, the exoskeleton system can still effectively assist the human body in bearing the load by locking the knee joint mechanism.

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 is applicable to the field of wearable robots, and discloses a self-adaptive control method for a waist exoskeleton robot, which comprises the following steps: firstly, acquiring attitude and angular velocity information of double inertial measurement units and displacement and velocity information of each encoder; combining encoder information and an exoskeleton geometric model to calculate a posture calculation value of the waist relative to the pelvis, and calculating a first posture estimation value according to double inertial navigation information; converting the two postures into a relative attitude error, mapping the relative attitude error into a three-dimensional attitude error vector, constructing a dynamic weight matrix, and calculating a consistency residual error of the two postures; fusing the consistency residual error with at least one of the actuator tracking deviation, the stroke approximation degree and the prediction confidence coefficient to construct a risk index; and finally, according to a comparison result of the risk index and two preset threshold values, an exoskeleton control mode is adaptively switched to a normal mode, a compliant degradation mode or an output stopping mode, and the method can realize accurate posture estimation of the waist exoskeleton and full-process risk dynamic management and control.

The invention discloses a wearable robot assistance parameter adjusting method and system based on a biomechanical model, relates to the field of wearable robots, and solves the problem that a current wearable robot cannot intelligently adjust an assistance torque and a damping coefficient. The method comprises the following steps: constructing a test single-step period standard deviation and a standard plantar pressure interval of legs of a wearer; according to the difference value, selecting an initial assistance torque and an initial damping coefficient when the current wearer uses the wearable robot; analyzing plantar pressure at different time nodes after the wearer uses the wearable robot to assist; whether the wearable robot needs to be adjusted or not is analyzed according to the actual plantar pressure and the actual single-step cycle standard deviation; according to the plantar pressure deviation rate and the single-step period deviation rate, the initial power assisting torque and the initial damping coefficient of the wearable robot are adjusted. According to the method, adaptive adjustment of the power assisting parameters of the wearable robot is achieved according to the plantar pressure deviation data and the single-step period deviation data.

The invention relates to a posture sensing method and device based on a flexible wearable robot, and belongs to the technical field of rehabilitation robot application, and the method comprises the steps: synchronously collecting standard motion data and real-time motion data of a user; performing coarse attitude calculation through a complementary filtering algorithm to obtain initial six-degree-of-freedom attitude data; calibrating the initial six-degree-of-freedom attitude data based on the deformation resistance change data, the real-time environment temperature data and a pre-constructed attitude deformation calibration model, completing attitude drift correction and motion artifact elimination, and obtaining calibrated six-degree-of-freedom attitude data; based on the calibrated six-degree-of-freedom attitude data, extracting user exclusive action characteristics and temperature correlation characteristics, and dynamically correcting core parameters of the attitude deformation calibration model according to the user exclusive action characteristics and the temperature correlation characteristics; and inputting the real-time action data into the corrected attitude deformation calibration model, and outputting real-time attitude data. The method has the effect of improving the attitude sensing precision and real-time performance.

The invention belongs to the technical field of robots, and provides a quick release structure for conversion of an outer limb and an exoskeleton of a lower limb and a wearable robot, the quick release structure comprises a push rod, a push cover and a plug cover; an accommodating space for arranging a magnet is formed in the push cover, the push rod is provided with a horizontal shaft part arranged in the accommodating space, the end surface of the horizontal shaft part is provided with a spiral wedge surface, an accommodating space for arranging a magnet is formed in the plug cover, and the central end surface of the plug cover is provided with a spiral wedge surface; the robot comprises a hip joint structure, two legs, two ankle structures and two feet. The push cover is connected with the foot, the plug cover is connected with the leg, and during mode switching, rapid switching between the exoskeleton and the outer limb can be achieved by disassembling the rapid disassembling structure. The device can be flexibly switched between an outer limb mode and an exoskeleton mode according to different use requirements, assistance can be provided for the lower limbs during walking and standing, the human body load can be shared, effective support can be provided in a complex environment, and the use occasion of the device is widened.

The present invention relates to a wearable robot module that assists the movement of a wearer's arm, the wearable robot module including: a clutch unit capable of implementing, on the basis of an operation, a plurality of modes including a fixed mode and an elastic mode; a wire having one end connected to the clutch unit; and an operation unit connected to the other end of the wire, wherein the clutch unit includes: a housing; a gear located within the housing; a plurality of levers connected to one end of the housing by a connection member and capable of independently controlling the rotatable direction of the gear; a wire pulley capable of being coupled to the gear; and an elastic member capable of being connected to the wire pulley.

The present disclosure relates to a wearable robot including upper and lower body portions configured to be closely attached to upper and lower bodies, respectively, of a person. Specifically, the upper body portion includes: a waist strap member; an intermediate connection link having one side connected to the lower body portion; a strap connection member connected to the waist strap member and the intermediate connection link; and an upper connection link including a side connected to the middle connection link and a section extending toward the chest of the person. Specifically, the strap connection member and the intermediate connection link are rotatably connected, and the intermediate connection link and the upper connection link are rotatably connected.

A data collection system that performs data collection of human-driven robot actions for robot learning. The data collection system includes: i) a wearable computation subsystem that is worn by a human data collector and that controls the data collection process and ii) a human-machine operation interface subsystem that allows the human data collector to use the human-machine operation interface to operate an attached robotic gripper to perform one or more actions. A user interface subsystem receives instructions from the wearable computation subsystem that direct the human data collector to perform the one or more actions using the human-machine operation interface subsystem. A visual sensing subsystem includes one or more cameras that collect raw visual data related to the pose and movement of the robotic gripper while performing the one or more actions. A data collection subsystem receives collected data related to the one or more actions.

The invention relates to the related technical field of the fields of man-machine cooperation, rehabilitation assistive devices and wearable robots, in particular to a five-connecting-rod knee joint exoskeleton device which comprises a thigh assembly (1), a transmission assembly (2) and a shank assembly (3), and the thigh assembly (1) comprises an output motor (101), a power output rod (102), a thigh binding piece (103), a thigh sliding block (104) and a thigh guide rod (105). The transmission assembly (2) comprises a first connecting rod (201), a second connecting rod (202), a third connecting rod (203), a fourth connecting rod (204), a fifth connecting rod (205) and an auxiliary connecting rod (206), and the shank assembly (3) comprises a shank binding piece (301), a shank sliding block (302), a shank guide rod (303) and a sensing unit (304). The five-connecting-rod knee joint exoskeleton device is based on the mechanical structure design of a five-connecting-rod mechanism, advanced control strategies such as multi-sensor fusion and impedance control are combined, and the nonlinear track of a sliding rotation center in the bending and stretching process of the knee joint of the human body is highly fitted in kinematics; meanwhile, the exoskeleton can adaptively provide assistance or damping according to the gait characteristics and the motion intention of the user by adjusting the output torque and flexibility in real time on the aspect of dynamic control, so that the naturalness, comfort and safety of man-machine interaction are effectively improved; therefore, diversified application requirements of rehabilitation training, walking assistance, man-machine cooperation and the like can be better met.

The present disclosure provides a support assembly comprising: a support frame; a seat member attached to the support frame; and a plurality of friction pads attached to the seat member. The plurality of friction pads extend in a first direction of the seat member and are spaced apart from each other in a direction around an imaginary line extending in the first direction.

Provided are a portable pneumatic generator and a wearable robot including the same. The portable pneumatic generator includes: a first tank for storing a first reactant; a second tank for storing a second reactant; a reactor for generating a gas by reacting the first reactant with the second reactant; and a reservoir for storing the gas generated by reacting the first reactant with the second reactant and outputting the gas to the outside and storing a residue, wherein the first reactant includes a material used for an exothermic reaction, and the second reactant includes a material used for an endothermic reaction.

A wearable robot includes upper and lower body parts configured to be respectively tightly attached to upper and lower bodies of a person. In particular, the upper body part includes: a waist harness member, a middle connection link having one side connected to the lower body part; a harness connection member connected to the waist harness member and the middle connection link; and an upper connection link that includes one side connected to the middle connection link, and a section extending toward a chest of the person. In particular, the harness connection member and the middle connection link are rotatably connected, and the middle connection link and the upper connection link are rotatably connected.

This invention discloses a method and system for adjusting assist parameters of wearable robots based on a biomechanical model, relating to the field of wearable robots. It addresses the current problem that wearable robots cannot intelligently adjust assist torque and damping coefficient. The method involves: constructing the standard deviation of the single-step cycle and the standard plantar pressure range for the wearer's legs; selecting the initial assist torque and initial damping coefficient when the wearer uses the wearable robot based on the difference values; analyzing the plantar pressure at different time points after the wearer uses the robot; analyzing whether the wearable robot needs adjustment based on the actual plantar pressure and the actual single-step cycle standard deviation; and adjusting the initial assist torque and initial damping coefficient of the wearable robot based on the plantar pressure deviation rate and the single-step cycle deviation rate. This invention achieves adaptive adjustment of the wearable robot's assist parameters based on plantar pressure deviation data and single-step cycle deviation data.

The present invention relates to a wearable robot. The wearable robot according to the present invention includes a first fixing part mounted on a body part on one side of a joint part, a second fixing part mounted on a body part on the other side of the joint part, a driving part connected to the first fixing part, and a connecting member connecting the driving part and the second fixing part and transmitting the driving force provided from the driving part to the second fixing part for the movement of the joint part. The connecting member is characterized in that its length is adjusted corresponding to the distance between the driving part and the second fixing part which changes according to the magnitude of the movement of the joint part, or includes a plurality of members arranged in a row and an interlocking part connecting the plurality of members so that the plurality of members interlock with each other. The driving part includes a driver that generates power for auxiliary force. 【Representative Drawing】 Figure 2

The application discloses a motion following control method and system of a wearable robot and a storable medium, and relates to the technical field of robot control, wherein the method comprises the following steps: realizing the following control of the wearable robot by constructing a tracking differentiator, improving an inverse dynamics control model and a joint torque representation model, and enabling the wearable robot to follow the motion of a wearer in real time; and the application can generate a control instruction which is more suitable for the actual working condition of a lower-limb wearable robot.

The invention relates to a bionic flexible multi-mode sensor, in particular to a bionic flexible multi-mode sensor for touch perception of a wearable robot and a preparation method of the bionic flexible multi-mode sensor. The bionic flexible multimode sensor comprises polyimide bionic cilia and a rigid base, and the polyimide bionic cilia is connected with the rigid base; the preparation method comprises the steps of preparation of the polyimide bionic cilia and the flexible sensitive element, manufacturing and installation of the rigid base of the sensor, packaging of the sensor and the like. According to the invention, the bionic flexible cilia is used as a core sensing unit, touch pressure, a near body flow field and environment temperature information are obtained by calculating a multi-mode electric signal of the laser-induced graphene sensitive element on the surface of the bionic flexible cilia, and the limitation that a traditional wearable sensor is single in function and multiple sensors are separately integrated is overcome. The process flow is simple, the cost is low, and the method is suitable for rapid prototype development and large-scale flexible manufacturing.

This application discloses a wearable robot skin, including a silicone sleeve and a magnetic fixing structure. The silicone sleeve covers a metal frame and is divided into multiple modular components. Adjacent modular components are detachably assembled via a tongue-and-groove interlocking structure. The magnetic fixing structure consists of a ferrite sheet pre-embedded in the silicone sleeve and a neodymium iron boron magnet embedded in the metal frame, achieving component adsorption and fixation through a magnetic field. First silicone microbeads are distributed at the contact interface between the silicone sleeve and the metal frame, and second silicone microbeads are distributed around the ferrite sheet, serving to buffer impact stress and enhance interface adhesion. This robot skin employs a dual fixing mechanism of "magnetic attraction + tongue-and-groove interlocking," with both working synergistically to achieve dynamic and static complementarity. The magnetic attraction structure provides flexible fit and dynamic compliance, while the tongue-and-groove interlocking structure ensures rigid support and resistance to shear and torsion, jointly improving impact resistance and connection stability, thereby increasing the service life of the silicone sleeve.

The invention provides a pneumatic soft joint movement rehabilitation robot, and belongs to the technical field of wearable robots. Comprising an elbow soft body actuator, a knee soft body actuator, a pneumatic driving assembly, a main controller and a power source, the elbow soft body actuator comprises an arm sleeve, the two ends of the arm sleeve are each fixedly connected with a wedge-shaped block A, a folding type air bag A is fixedly connected between the two wedge-shaped blocks A, and a curvature sensor A and an electromyographic signal collecting module A are arranged on the inner side of the arm sleeve; the knee soft body actuator comprises a leg sleeve, the two ends of the leg sleeve are each fixedly connected with a wedge-shaped block B, a folding type air bag B is fixedly connected between the two wedge-shaped blocks B, and a curvature sensor B and an electromyographic signal collecting module B are arranged on the inner side of the leg sleeve. According to the invention, bending of arms and legs can be effectively supported at the same time, human body action intentions can be judged by collecting electromyographic signals, human body movement and rehabilitation training can be assisted, and muscle fatigue generated by movement can be effectively relieved.

The invention relates to a control method for a flexible lower limb exoskeleton, which belongs to the technical field of wearable robots and comprises the following steps: acquiring a physical signal group and a physiological signal group; constructing a feature vector including a rigidity estimator and gait phase information; respectively inputting the feature vectors into two prediction models to obtain candidate control outputs, and generating a control quantity through a fusion module; judging whether the transmission material is in a material state change stage or not; in the change stage, the contribution of human physiological signals to control output is inhibited; according to the method, the mechanical state of the material and the motion state of the human body are coupled and coded, and a unified information basis is provided for subsequent double-flow prediction; and the architecture of a double-prediction-model parallel inference and fusion module is adopted, so that a physical signal channel and a physiological signal channel are mutually independent and do not interfere with each other, a conflict suppression mechanism in a material state change stage is introduced, a physiological signal is prevented from misleading a control decision in a high non-stationary section, and the robustness of the system is improved.

Disclosed are a robot-assisted walking training system and a control method therefor, the training system having: a main system having a walking motion generation section having an end effector type robot pedal stepped by a patient for walking training and a pedal-operation unit for driving the robot pedal, and a main control section for controlling the end effector type robot pedal and the pedal-operation unit; a main control unit that performs walking training of the patient stepping on the robot pedal by controlling the pedal-operation unit; and a cooperative system in the form of a wearable robot having a cooperative system with one or more joint-operating engines mounted to the patient's body and configured to assist or force joint movement of the patient's lower body in synchronization with movement of the pedal-operating unit, and a lower control portion configured to control the lower body of the patient's lower body. The lower control portion is configured to control the one or more joint-operating engines and associate or link motion of the one or more active joint portions to motion of the pedal-operating unit in response to a control signal from the main control portion.

The wearable robot mainly comprises a movable bottom frame and a waist protection support, the bottom of the waist protection support is rotationally connected with two symmetrically-arranged leg exoskeletons through bearings, and the top of the waist protection support is fixedly connected with a mounting frame through a flexible belt. The robot has the advantages that when a patient wears the robot, the body is fixed through the hook-and-loop fastener bandages of the waist protection support and the chest protection support, and the upper limbs are placed in the upper limb locking frame; during training, a patient drives the upper limb locking frame to rotate, the rotating shaft synchronously drives the cam to rotate, the cam extrudes the pressure sensor in the extension frame, the pressure sensor transmits a signal to the controller, and the controller controls the leg exoskeleton to move cooperatively according to the pressure signal. The whole control process does not need to depend on brain signals, pressure sensing is triggered through active movement of the upper limbs of the patient, control signal disorder caused by emotion, fatigue and other factors is avoided, the robot is more accurate in response and more coordinated in action, and the safety and reliability of rehabilitation training are improved.

A support assembly includes a supporting frame, a seating member attached to the supporting frame, and a plurality of friction pads attached to the seating member. The plurality of friction pads extend in a first direction of the seating member and are spaced apart from one another in a direction surrounding an imaginary line extending in the first direction.

1. Name of the designed product: main body of a charging stand for a wearable robot. 2. Use of the designed product: the designed product as a whole and the part claimed for protection are used as a charging stand for a wearable robot to place the wearable robot and charge it. 3. Design points of the designed product: the shape of the solid line part. 4. Picture or photo best indicating the design points: perspective view 1. 5. Other circumstances or explanations: the part depicted by solid lines in the view is the part claimed for protection.

Exemplary task-agnostic exoskeleton control system and method are disclosed that are task-agnostic utilizing instantaneous estimates of biological joint moments from deep neural networks to assist the user movements. The exemplary control system employs multiple body sections and joints in-the-loop estimation to provide multi-joint assistance operation, e.g., within an autonomous, clothing-integrated exoskeleton. The exemplary control system may deploy a deep domain adaptation (DDA) method configured to translate human movement data between a simulated sensor domain and a real sensor domain.

To provide a motion assistance method and system that can immediately respond to sudden changes in the user's movements. [Solution] The present invention relates to a wearable robot, and the wearable robot according to the present invention includes a first fixing part attached to a body part on one side of a joint, a second fixing part attached to a body part on the other side of the joint, a drive unit connected to the first fixing part, and a connecting member that connects the drive unit and the second fixing part and transmits the driving force provided from the drive unit to the second fixing part for the movement of the joint, wherein the connecting member is characterized in that its length is adjusted in accordance with the distance between the drive unit and the second fixing part which changes according to the magnitude of the movement of the joint, and includes a plurality of members arranged in a line and an interlocking part that connects the plurality of members so that the plurality of members interlock with each other, and the drive unit includes a drive that generates power for auxiliary force.

The invention discloses an intelligent walking assisting exoskeleton in a visual impaired environment, and belongs to the field of wearable robots. According to the scheme, the exoskeleton comprises a lightweight exoskeleton main body; the environment sensing system is composed of a laser radar, a camera and an ultrasonic sensor; a navigation obstacle avoidance system based on an SLAM algorithm; the man-machine interaction system comprises a bone conduction earphone and a controller; a power system; the invention further discloses an intention recognition system fusing myoelectricity and electroencephalogram. In addition, functions of fall detection and remote monitoring are integrated. According to the invention, environment perception, intelligent navigation and physical assistance are integrated, the path can be planned in real time, the walking intention can be identified, accurate assistance can be provided, and the autonomy and safety of walking in a visual impaired environment can be effectively improved.