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: A computer peripheral device is provided. The computer peripheral device is adapted to be installed in an electronic device supporting signal transmission of a first signal frequency. The computer peripheral device includes a human interface device (HID) and a bridging device. The HID includes a control unit to support signal transmission of a second signal frequency. The bridging device includes a first universal serial bus (USB) interface unit and a second USB interface unit. The first USB interface unit is adapted to be electrically connected to the electronic device, and supports signal transmission of the first signal frequency. The second USB interface unit is adapted to be electrically connected to the HID. The second USB interface unit regards the HID as a communication device class (CDC) device, instructs the control unit to generate an input signal at a timing corresponding to the first signal frequency, and transmits the input signal to the electronic device.

Abstract: A multi-source domain adaptive electroencephalogram (EEG) emotional state classification method based on knowledge distillation are provided. First, data is obtained for band-pass filtering, and artifacts are removed by an independent component analysis technology. Second, EEG features are extracted by using a differential entropy method, and a three-dimensional EEG time series is converted into a two-dimensional sample matrix. Then, a training set and a test set are defined in two task scenarios, respectively. A pseudo-label triple loss based on marginal sampling is combined with a maximum mean discrepancy. Knowledge is learned from different source domains, so that a plurality of single-source models are utilized to the greatest extent, and a more powerful model is implemented with less time consumption. Finally, the classification accuracy is used to evaluate the performance of the model in the two task scenarios.

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: A exoskeleton finger rehabilitation training device includes an exoskeleton finger rehabilitation training mechanism including a supporting base, a finger sleeve actuating mechanism, and a finger joint sleeve connected to a power output end of the finger sleeve actuating mechanism, wherein the finger joint sleeve can be sheathed at the periphery of a finger joint to be rehabilitated, and the finger joint sleeve can be driven by the power actuation of the finger sleeve actuating mechanism to drive the finger joint to be rehabilitated in order to passively bend or stretch; the supporting base includes a profiled shell, with an inner surface of the profiled shell being configured based on the profile of the complete back of a palm or part of the back of the palm, and with the back of the profiled shell being provided with a power fixed base.

Abstract: The present disclosure discloses an automated calibration system and calibration method for a flexible robot actuator. The calibration system includes a support frame. A visual positioning system, a pressure measuring system and a pneumatic pressure control system are respectively installed on the support frame. The visual positioning system is configured to measure a relative displacement and an angle between two ends of the flexible actuator. The pneumatic pressure control system is configured to charge air into an actuating end of the flexible actuator and measure an input pneumatic pressure of the flexible actuator. The pressure measuring system includes a pressure gauge installed on the support frame through a vertical axis motor system, and the flexible actuator to be calibrated installed on the support frame through a horizontal axis motor system and a rotating motor system.

Abstract: A robot-assisted hand-eye coordination training system based on a smooth pursuit eye movement and a guidance force field includes a virtual interactive scene module, a smooth pursuit eye movement detection module, a robot-assisted interception module and an impact force rendering module. The virtual interactive scene module can generate a virtual interactive scene having a virtual moving object and a virtual handle agent. The smooth pursuit eye movement detection module collects an eye movement signal of a user when the user performs pursuit eye movements on the virtual moving object to detect a smooth pursuit eye movement event. The robot-assisted interception module estimates a movement direction of the virtual moving object, generates an interception and guidance force field, and therefore generates assisting force to assist the user in interception. The impact force rendering module generates impact force according to an impact force computation model after collision is detected.

Abstract: An adaptive control method and system for an upper limb rehabilitation robot based on a game theory and surface Electromyography (sEMG) is disclosed. A movement trajectory that a robot is controlled to run within a training time is designed during subject operation. An sEMG-based Back Propagation Neural Network (BPNN) muscle force estimation model establishes a nonlinear dynamic relationship between an sEMG signal and end force by constructing a three-layer neural network. A human-computer interaction system is analyzed by the game theory principle, and a role of the robot is deduced. The control rate between the robot and a subject is updated by Nash equilibrium, and adaptive weight factors of the robot and the subject are determined. The robot adaptively adjusts the training mode thereof according to a movement intention of the subject during operation and a weight coefficient obtained by the game theory principle.

Abstract: A robot-assisted hand-eye coordination training system based on a smooth pursuit eye movement and a guidance force field includes a virtual interactive scene module, a smooth pursuit eye movement detection module, a robot-assisted interception module and an impact force rendering module. The virtual interactive scene module can generate a virtual interactive scene having a virtual moving object and a virtual handle agent. The smooth pursuit eye movement detection module collects an eye movement signal of a user when the user performs pursuit eye movements on the virtual moving object to detect a smooth pursuit eye movement event. The robot-assisted interception module estimates a movement direction of the virtual moving object, generates an interception and guidance force field, and therefore generates assisting force to assist the user in interception. The impact force rendering module generates impact force according to an impact force computation model after collision is detected.

Abstract: The present disclosure discloses an electroencephalogram (EEG) emotion recognition method based on a spiking convolutional neural network. In the present disclosure, after EEG emotion data is preprocessed, a differential entropy feature is extracted and a time window is intercepted, and then a spiking convolutional encoder is configured to encode the EEG emotion data; a spiking convolutional feature extractor extracts a spiking data feature; and a spiking fully connected classifier performs learning and classification. In the present disclosure, a spiking neural network combining a spiking convolutional layer and a spiking fully connected layer is trained directly to achieve an objective of EEG emotion classification.

Abstract: An adaptive control method and system for an upper limb rehabilitation robot based on a game theory and surface Electromyography (sEMG) is disclosed. A movement trajectory that a robot is controlled to run within a training time is designed during subject operation. An sEMG-based Back Propagation Neural Network (BPNN) muscle force estimation model establishes a nonlinear dynamic relationship between an sEMG signal and end force by constructing a three-layer neural network. A human-computer interaction system is analyzed by the game theory principle, and a role of the robot is deduced. The control rate between the robot and a subject is updated by Nash equilibrium, and adaptive weight factors of the robot and the subject are determined. The robot adaptively adjusts the training mode thereof according to a movement intention of the subject during operation and a weight coefficient obtained by the game theory principle.

Abstract: Provided is a preparation method of an antibody-drug conjugate represented by Formula (I), or a pharmaceutically acceptable salt or stereoisomer thereof, or a solvate of the foregoing, wherein A, X, Y, L, D and a are as defined herein.

Abstract: An auxiliary support method based on variable stiffness supernumerary robotic limbs includes: obtaining data from a surface electromyography sensor and an inertial sensor; processing the data from the inertial sensor to determine whether a wearer has an operation intention; preprocessing the data from the surface electromyography sensor through full-wave rectification, low-pass filtering and normalization; using preprocessed surface electromyography to estimate a reference stiffness of an arm of the wearer; and mapping the reference stiffness of the arm to an impedance control model of the supernumerary robotic limbs. In the method, man-machine cooperation between human and the supernumerary robotic limbs in a task of overhead support is achieved by coordinating a stiffness of the human arm and a stiffness of the supernumerary robotic limbs, thereby reducing input of personnel in the task; and when the stiffness of the arm of the wearer decreases, the stiffness of the supernumerary robotic limbs increases.

Abstract: The present invention provides an anti-ErbB2 antibody-drug conjugate, a composition comprising the conjugate, a method for preparing the conjugate, and use of the conjugate.

Abstract: A wrist rehabilitation training system based on muscle coordination and variable stiffness impedance control includes the following modules: an electromyographic signal collection and preprocessing module, a muscle co-decomposition and mapping model obtaining module, a man-machine interactive control module, and a virtual reality serious game module; collects a surface electromyographic signal of a forearm of a user, obtains time-domain coordination through non-negative matrix factorization, establishes a position and stiffness estimation model, and controls motion of a target in a serious game through variable stiffness impedance control, so as to complete a training task.

Abstract: A palm-supported finger rehabilitation training device comprises a mounting base, a finger rehabilitation training mechanism mounted on the mounting base, and a driving mechanism for driving the finger rehabilitation training mechanism; wherein the finger rehabilitation training mechanism comprises four independent and structurally identical combined transmission devices for finger training corresponding to a forefinger, a middle finger, a ring finger and a little finger of a human hand, respectively, and the mounting base is provided with a supporting surface capable of supporting a human palm; wherein each combined transmission device for finger training comprises an MP movable chute, a PIP fingerstall, a DIP fingerstall and a connecting rod transmission mechanism; a force sensor is provided to acquire force feedback information to determine and control force stability, and a space sensor is provided to acquire space angle information to control space positions of fingers in real time.

Abstract: A rehabilitation glove based on a bidirectional driver of a honeycomb imitating structure, including five bidirectional drivers and a cotton glove. The drivers are fixed to a back of the glove through hook and loop fasteners. Each driver includes a hollow buckling air bag in a continuous bent state, a middle guide layer in a continuous bent state and a hollow stretching air bag. The buckling air bag and the middle guide layer are symmetrically arranged, and the stretching air bag in a straightened state is arranged below the middle guide layer. A novel bidirectional driver of a honeycomb imitating structure is provided, which may provide a patient with rehabilitation training in two degrees of freedom: buckling and stretching. A control algorithm of the bidirectional driver is further provided to perform force control output for the driver, which may better help the patient recover hand functions.

Abstract: The present disclosure discloses an automated calibration system and calibration method for a flexible robot actuator. The calibration system includes a support frame. A visual positioning system, a pressure measuring system and a pneumatic pressure control system are respectively installed on the support frame. The visual positioning system is configured to measure a relative displacement and an angle between two ends of the flexible actuator. The pneumatic pressure control system is configured to charge air into an actuating end of the flexible actuator and measure an input pneumatic pressure of the flexible actuator. The pressure measuring system includes a pressure gauge installed on the support frame through a vertical axis motor system, and the flexible actuator to be calibrated installed on the support frame through a horizontal axis motor system and a rotating motor system.

Abstract: A method for reducing hysteresis error and high frequency noise error of capacitive tactile sensors includes the following steps: step 1: calibration, specifically including positive stroke calibration to form n positive stroke curves and negative stroke calibration to form n negative stroke curves; step 2: averaging, specifically including positive stroke averaging to form an average positive stroke curve, negative stroke averaging to form an average negative stroke curve, and comprehensive averaging to form a comprehensive stroke curve; step 3: fitting modeling, to obtain a positive stroke fitting function, a negative stroke fitting function, and a comprehensive fitting function; step 4: measurement; step 5: noise filtering; step 6: stroke direction discrimination; and step 7: resolving, to obtain the force at the current time by using a corresponding fitting function based on the stroke direction discrimination result.