Abstract: The present disclosure discloses a flexible rehabilitation glove based on hybrid actuators. The flexible rehabilitation glove includes five hybrid actuators and an actuator control box, each hybrid actuator includes an actuator end mounting seat, a flexible actuator, a TPFE water pipe, a flexible actuator front section mounting seat, a flexible actuator air pipe, an air pipe connecting seat II, an SMA spring actuator, an air pipe connecting seat I and a cooling water pipe, the control box includes an air pump, a filter, a water pump and a water tank, a proportional valve and a control circuit board inside, and includes an actuator control box body, a control box cover, a main switch, a button and a voltage display outside, and the filter is connected to the air pump and the electrical proportional valve respectively.

Abstract: A variable stiffness hand exoskeleton device based on antagonistic driving, includes a power mechanism, a support base, a spring-link composite transmission mechanism, and a distal finger sleeve connected to a power output end of the spring-link composite transmission mechanism for fingers. The power mechanism drives the fingers to perform rotational movements through the spring-link composite transmission mechanism. The distal finger sleeve is fixed to a distal joint periphery of a finger joint using a first elastic adjustment band, and provides force feedback to an end of the finger joint under driving force of a link structure. An inner surface of the support base is contoured to match a palm, and a back of the support base is provided with a rotary support seat and a motor fixing seat. A motor group of the power mechanism is mounted on the motor fixing seat.

Abstract: Provided are a multi-degree-of-freedom myoelectric artificial hand control system and a method for using same. The system comprises a robotic hand, a robotic wrist (2), a stump receiving cavity (1) and a data processor (3), wherein the robotic hand and the stump receiving cavity (1) are respectively mounted on two ends of the robotic wrist (2); a multi-channel myoelectric array electrode oversleeve, a control unit circuit board, and a battery are connected in the stump receiving cavity (1); and the other end of the control unit circuit board is connected to the robotic hand and the robotic wrist (2).

Abstract: Disclosed is a lightweight hand exoskeleton force feedback apparatus, including a driver, a first rotating link, a second rotating link, a first linkage link, a second linkage link, a finger sleeve, and a pressure sensor fixing member; the driver is worn on a back of metacarpal bone of a human hand, the finger sleeve is fixed on an index finger, and the pressure sensor fixing member is fixed below the index finger; when the human hand bends to simulate a state of grasping an object, the driver drives the first rotating link to couple with the first linkage link and the second linkage link through the second rotating link to drive the finger sleeve to bend and stretch, force feedback is applied to the fingertip, and a pressure is accordingly imposed on a pressure sensor of the pressure sensor fixing member, so that closed-loop force feedback control is implemented.

Abstract: Disclosed is an optimization modeling and robust control method for a soft robot based on a fusion prediction equation, including the following steps: deriving measurement coordinates based on the fusion prediction equation; designing an observation function based on the measurement coordinates; identifying a Koopman model based on the observation function; and designing a robust model predictive controller based on the Koopman model. Further disclosed are a fusion prediction equation and a derivation method thereof, which can derive correct, abundant but non-redundant measurement coordinates, overcoming the problem of single measurement coordinates in a soft robot system, thereby being conducive to simplifying a design process of the observation function and further improving the accuracy of the Koopman model for the soft robot.

Abstract: Disclosed is a safety shared control system based on performance of teleoperator, including a master teleoperation system, a slave robotic manipulator system and a communication module; where the master teleoperation system includes EEG signal measurement of a teleoperator, hand controller operation input, and upper computer software, and the upper computer software includes a graphical user interface (GUI), safety simulation for protecting the safety of a robot, and a PoT model; and the slave robotic manipulator system includes a robotic manipulator, a vision camera and lower computer software, and the lower computer software includes a target recognition algorithm, an autonomous controller, and a shared controller for dynamically allocating human-robot control weights.

Abstract: Disclosed is an online estimation method for wrist torque based on neural features and LSTM, including following steps: (1) an experimenter keeps his/her arms stationary and applies torque to a torque sensor through his/her wrist; (2) acquiring data from the torque sensor and high-density surface EMG ((HD-sEMG) synchronously; (3) decomposing the HD-sEMG using a blind source separation algorithm to obtain a motor unit spike train (MUST); (4) constructing input and output vectors on the basis of the original HD-sEMG and the decomposed MUST, performing training of the LSTM, and performing polynomial regression of a discharge rate and torque of a neural feature; and (5) calculating a real-time discharge rate (DR) of the CST using a sliding window approach for real-time estimation of the torque.

Abstract: Disclosed is an EEG recognition method for a natural hand movement based on a time-domain and frequency-domain multi-layer brain network, including: (1) acquiring a multi-channel EEG signal of the natural hand movement; (2) preprocessing the multi-channel EEG signal, and extracting a ? wave, a ? wave, a ? wave, a ? wave, and a ? wave at each time point; (3) constructing a time-domain multi-layer brain network using a wSAR model; (4) calculating the frequency-domain multi-layer brain network using the phase-amplitude coupling; (5) combining the time-domain multi-layer brain network and the frequency-domain multi-layer brain network, and performing standardization; and (6) calculating metrics of the time-domain and frequency-domain multi-layer brain network and a super-adjacency matrix of a decomposed time-domain and frequency-domain multi-layer brain network, inputting the same to a two-layer graph convolutional network (GCN), and fusing manual, shallow, and deep features for analysis.

Abstract: Disclosed is a lightweight hand exoskeleton force feedback apparatus, including a driver, a first rotating link, a second rotating link, a first linkage link, a second linkage link, a finger sleeve, and a pressure sensor fixing member; the driver is worn on a back of metacarpal bone of a human hand, the finger sleeve is fixed on an index finger, and the pressure sensor fixing member is fixed below the index finger; when the human hand bends to simulate a state of grasping an object, the driver drives the first rotating link to couple with the first linkage link and the second linkage link through the second rotating link to drive the finger sleeve to bend and stretch, force feedback is applied to the fingertip, and a pressure is accordingly imposed on a pressure sensor of the pressure sensor fixing member, so that closed-loop force feedback control is implemented.

Abstract: Disclosed are an embracing crawling robot for detecting an underwater pier of a highway bridge and a detection method therefor. The robot includes a main body, underwater lighting systems, tool compartments, depth metering modules, servo driving wheels, inclination measurement modules, underwater manipulator arms, vision array modules, synchronized stretching and fixing systems, and driven wheels. The robot is capable of crawling around an underwater pier of a highway bridge and operating stably in an underwater environment. After cleaning surface attachments on the underwater pier, the robot performs visual detection of a disease; and after determining type and location information of the disease, the robot will transmit disease information back. The robot is capable of crawling around the underwater pier of the highway bridge stably at any depths, perceiving depth and visual information under high-speed and turbid water conditions, thereby realizing detection of the disease on the underwater pier.

Abstract: Disclosed are an affective haptic regulation system and method based on multimodal fusion, including a haptic optimal parameter adjustment module, a haptic generation module, a visual-auditory generation module, a multi-physiological signal acquisition module, a multi-sensory signal acquisition module, and a multimodal fusion emotion recognition module.

Abstract: The present invention discloses a dual-airway bionic snail soft robot, which includes ventral muscular feet, an air pressure controlling device and mucus, wherein the ventral muscular foot includes an upper deformation layer, a lower deformation layer and a strain sensor. Snail ventral muscular feet are simulated by the upper deformation layer and the lower deformation layer to produce wave motion. The strain sensor senses a wave motion state of the soft robot to provide a basis for the air pressure controlling device to output air pressure. In another aspect, snail mucus is replaced with glycerin to produce a suction force and improve crawling efficiency. The designed bionic snail soft robot can move forward, move backward and turn in situ, thereby realizing free movement in a microgravity environment.

Abstract: Disclosed is a digital image calculation method and system for RGB-D camera multi-view matching based on a variable template, the method includes six steps: acquiring data, preprocessing point cloud data, performing feature point matching, re-registering a variable template, calculating point cloud data transformation relationships among large-view images, and performing point cloud fusion. A size of a non-adjacent image matching template is adjusted based on registration results of adjacent angles of view, and correct registration of feature points of images from non-adjacent angles of view is accordingly achieved, which improves matching accuracy, eliminates cumulative errors in image sets, and provides more accurate initial values for subsequent iterations of point cloud fusion, such that the number of iterations is reduced, and three-dimensional reconstruction of images is implemented.

Abstract: Disclosed is a wearable haptic feedback device for human-robot formation control, including an interactive interface module and a main control module, wherein the interactive interface module includes an input module and a wearable haptics feedback module; the wearable haptics feedback module includes an extrusion force feedback module, a shear force feedback module, and a vibration feedback module, and the main control module controls each module and receives operation instructions. The device can be wirelessly deployed on an arm of a user, and provide feedback on the formation change, motion guidance, and obstacle detection of the human-robot formation by generating three haptic feedback signals: extrusion, shearing, and vibration.

Abstract: The present disclosure discloses an autonomous mobile grabbing method for a mechanical arm based on visual-haptic fusion under a complex illumination condition, which mainly includes approaching control over a target position and feedback control over environment information. According to the method, under the complex illumination condition, weighted fusion is conducted on visible light and depth images of a preselected region, identification and positioning of a target object are completed based on a deep neural network, and a mobile mechanical arm is driven to continuously approach the target object; in addition, the pose of the mechanical arm is adjusted according to contact force information of a sensor module, the external environment and the target object; and meanwhile, visual information and haptic information of the target object are fused, and the optimal grabbing pose and the appropriate grabbing force of the target object are selected.

Abstract: Disclosed in the present disclosure is a method for identifying skills of a human-machine cooperation robot based on a generative adversarial imitation learning, which includes: firstly, defining classifications of human-machine cooperation skills that needed to be conducted; conducing demonstrations on different classifications of the skills by human experts, and collecting image information and data in the demonstrations to make calibrations; identifying the image information by means of image processing, extracting effective feature vectors capable of clearly distinguishing the different classifications of the skills and taking the effective feature vectors as demonstration teaching data; training a plurality of discriminators respectively by utilizing the acquired demonstration teaching data through a method of the generative adversarial imitation learning; extracting user's data after the training and putting the data into different discriminators, and taking a discriminator corresponding to a maximum va

Abstract: The present disclosure discloses a pipeline inspection robot with crisscross structure-changeable crawler belts and a control method thereof. The pipeline inspection robot includes a robot main body, crawler belt tilt angle adjustment mechanisms symmetrically provided on left and right sides of the robot main body, and crisscross structure-changeable crawler belt assemblies provided on the crawler belt tilt angle adjustment mechanisms. The robot main body is connected to the crisscross structure-changeable crawler belt assemblies at the left and right sides thereof by means of the crawler belt tilt angle adjustment mechanisms. The crawler belt tilt angle adjustment mechanisms are adjusted by means of supporting sliding blocks at the bottom of the robot main body. The crisscross structure-changeable crawler belt assembly includes a primary traveling crawler belt, an auxiliary traveling crawler belt, and a crisscross structure-changeable sliding block.

Abstract: A rope-driven soft hand function rehabilitation device includes four finger exoskeleton mechanisms, a thumb exoskeleton mechanism, and a soft rubber glove. An index-finger exoskeleton mechanism includes an index-finger distal phalanx loop, an index-finger middle phalanx loop, and an index-finger proximal phalanx loop which are mutually connected via a hinge structure. The thumb exoskeleton mechanism includes a thumb proximal phalanx loop and a thumb distal phalanx loop which are connected via a hinge structure. The rope is fastened to the hand function rehabilitation device via an aluminum sleeve which prevents the rope from slipping off during finger flexion/extension and abduction/adduction when the fingers are pulled by the rope at the palm and the hand back.

Abstract: A combined six-dimensional force sensor based on thin-film sputtering technology includes a force transmission table, a cross beam, a base, a top cover, a bottom cover and strain gauges. Strain gauges are sputtered on the elastomer structure to form six sets of Wheatstone bridges. The measurement method of the six-dimensional force sensor is that: an input force/moment of a certain dimension acts on the elastomer structure including the force transmission table and the cross beam through the top cover, the cross beam is deformed and resistance values of strain gauges at corresponding positions change, and output voltages of corresponding bridges change.

Abstract: A combined structure for thin film sputtering high-precision six-dimensional force sensor includes a cross beam, a double U-shaped beam, a base, a top cover, a bottom cover and thin film strain gauges. Strain gauges are sputtered on the main beam to form six sets of Wheatstone bridges, with three sets on the cross beam and three sets on the double U-shaped beam. The measurement method of the six-dimensional force sensor is that: an input force/moment of a certain dimension acts on the center of the cross beam and the center of the double U-shaped beam, so that the sensor is deformed and resistance values of strain gauges at corresponding positions change, thereby changing output voltages of corresponding bridges.