A5039684680- Muscle activation and electromyography studies
- EEG and Brain-Computer Interfaces
- Soft Robotics and Applications
- Shape Memory Alloy Transformations
- Advanced Sensor and Energy Harvesting Materials
- Gaze Tracking and Assistive Technology
- Iterative Learning Control Systems
- Stroke Rehabilitation and Recovery
- Neuroscience and Neural Engineering
- Piezoelectric Actuators and Control
- Prosthetics and Rehabilitation Robotics
- Robot Manipulation and Learning
- Non-Invasive Vital Sign Monitoring
- Modular Robots and Swarm Intelligence
- Robotics and Sensor-Based Localization
- Tactile and Sensory Interactions
- Robotic Path Planning Algorithms
- Control Systems in Engineering
- Advanced Fiber Optic Sensors
- Neural Networks and Applications
- Power Line Inspection Robots
- Advanced Vision and Imaging
- Quality and Safety in Healthcare
- Motor Control and Adaptation
- Adhesion, Friction, and Surface Interactions
Shenyang Institute of Automation
2012-2024
Chinese Academy of Sciences
2012-2024
State Key Laboratory of Robotics
2021-2024
Zhejiang University of Technology
2021
University of Hong Kong
2021
City University of Hong Kong
2021
Nankai University
2021
Chiba Institute of Technology
2021
King University
2021
Peking University
2021
In order to reduce the gap between laboratory environment and actual use in daily life of human-machine interaction based on surface electromyogram (sEMG) intent recognition, this paper presents a benchmark dataset sEMG non-ideal conditions (SeNic). The mainly consists 8-channel signals, electrode shifts from an 3D-printed annular ruler. A total 36 subjects participate our data acquisition experiments 7 gestures conditions, where factors 1) shifts, 2) individual difference, 3) muscle...
A multifunctional myoelectric prosthetic hand is a perfect gift for an upper-limb amputee, however, the control not so good now. Here, paper presents comparative study on electromyography (EMG) pattern recognition based PCA and LDA anthropomorphic robotic hand. Four channels of surface EMG (sEMG) signals were recorded from subject's forearm. Time-domain analysis, frequency-domain wavelet transform nonlinear entropy analysis fractal done fourteen kinds features extracted sEMG signals. The...
In sEMG-based recognition systems, accuracy is severely worsened by disturbances, such as electrode shifts doffing/donning. Traditional models are fixed or static, with limited abilities to work in the presence of disturbances. this paper, a transfer learning method proposed reduce impact shifts. method, novel activation angle introduced locate electrodes within polar coordinate system. An adaptive transformation utilized correct electrode-shifted sEMG samples. The based on estimated...
Neural information decomposed from electromyography (EMG) signals provides a new path of EMG-based human-machine interface. Instead the motor unit decomposition-based method, this work presents novel neural interface for human gait tracking based on muscle synergy, high-level control to collaborate groups performing movements. Three classical synergy extraction approaches include Principle Component Analysis (PCA), Factor (FA), and Nonnegative Matrix Factorization (NMF), are employed...
How to learn informative representations from Electromyography (EMG) signals is of vital importance for myoelectric control systems. Traditionally, hand-crafted features are extracted individual EMG channels and combined together pattern recognition. The spatial topological information between different can also be informative, which seldom considered. This paper presents a radically novel approach extract structural within diverse based on the symmetric positive definite (SPD) manifold....
As a friendly tool, the soft gripper can be used directly for grasping vulnerable objects in underwater environments. These tasks are generally performed by teleoperation based on visual feedback, rather than actuators’ sensing information. However, vision sensors’ function may restricted some complex environments with poor visibility and narrow spaces. This will greatly reduce efficiency of operations. Therefore, actuators strongly require an organism‐like perception system to sense...
Electromyography (EMG) has some good abilities for bionic mechanical hand's control and researchers have proposed many kinds of methods EMG classification. Principal Components Analysis (PCA) which is an ideal tool dimension reduction was introduced Linear Discriminant (LDA) performs outstandingly on This paper does a comparative study PCA LDA classification, mainly including raw EMG, features, features. Here five time-domain features four frequency-domain are selected. The hand motions...
In this paper, an active modeling and control scheme is developed for Shape Memory Alloy (SMA) actuators to eliminate the negative influences caused by uncertainties in its dynamics. First, a nonlinear SMA dynamic model based on Liang empirical models built linearized, all due time-varying parameters, external disturbances, as well linearization, are considered error of linearized model. Secondly, Kalman filter constructed estimate real time, which intends improve accuracy actively. Finally,...
Deep‐sea exploration remains a challenging task as the extreme hydrostatic pressure environment, darkness, and suspended sediment launch severely hinder capability of deep‐sea vehicles. As complement to underwater camera, tactile perception becomes especially important in situations where machine vision is limited. However, sensors utilized deep sea, which should be able detect changes only hundreds pascals under high pressure, are still lacking. To tackle challenge imposed by simulated...
With coexisting-cooperative-cognitive robots gradually appearing in daily life, an instinct and efficient human-robot interaction (HRI) is becoming more challenging necessary. Surface electromyography (sEMG) signals, as one of mainstream manners the interactions, are employed to predict human intentions. In this paper, provide natural assistance for standing up sitting down, sEMG signals acquired from active muscles one's lower limb utilized continuous movements. A temporally smoothed...
Patients who have lost limb control ability, such as upper amputation and high paraplegia, are usually unable to take care of themselves. Establishing a natural, stable, comfortable human-computer interface (HCI) for controlling rehabilitation assistance robots other controllable equipments will solve lot their troubles. In this study, complete limbs-free face-computer (FCI) framework based on facial electromyography (fEMG) including offline analysis online mechanical was proposed. Six...
In this paper, a new robust adaptive control method has been proposed for nonlinear systems with uncertainties. This combines the advantages of self-tuning and sliding mode control. A simple parameterization model is first derived based on linear dynamic unmodeled dynamics. Based modified surface, design procedure indirect concept. controller consists four parts: 1) system parameters estimation; 2) dynamics 3) weighting polynomials updating; 4) law calculation. The key merits are as follows:...
Gait can reflect human biological status during walking, which be used for disease detect, identity verification or robot control, etc. Traditionally, gait analysis only classifies a cycle into few discrete stages. In this paper, will decoded continuously using surface electromography (sEMG). The angle of knee joint and ankle walking at different speed estimated the same time by proposed scheme. Four domain features combined together task. Six estimation methods compared best performance...
Rehabilitation level evaluation is an important part of the automatic rehabilitation training system. As a general rule, this process manually performed by doctors using chart-based ordinal scales which can be both subjective and inefficient. In paper, novel approach based on ensemble learning proposed automatically evaluates stroke patients' multi-channel sEMG signals to problem. The correlation between levels actions investigated suitable for assessment are selected. Then, features...
Shape memory alloy (SMA) has been utilized as the material of smart actuators due to miniaturization and lightweight. However, nonlinearity hysteresis SMA seriously affect precise control. In this article, a novel disturbance compensation-based adaptive control scheme is developed improve performance actuator system. Firstly, nominal model constructed based on physical process. Next, an estimator online update not only unmeasured system states but also total disturbance. Then, controller,...
The paper presents the modeling and linear control of shape memory alloy (SMA) actuator. A complete system mathematical model SMA actuator is constructed, all uncertain parameters are evaluated through nonlinear least squares method from Matlab parameter estimation tool. feedback linearization (FBL) theory applied, transformed to so that mature can be used. In this paper, a simple gain matrix utilized establish Hurwitz, achieves output position tracking, ensures stability. Two schemes, FBL...
Electromyography (EMG) shows excellent potential for human-machine interaction (HMI) tasks. It reflects the physiological intention of human beings, which contributes to a more intuitive interface. The sequence EMG signals acquiring during period is most commonly used feature extraction and gesture recognition. instant graph, always thought be useless due too much noise inside it, can also recognize movement intention. This work explores new path patterns without engineering, using both deep...
Soft pneumatic actuators/robotics have received significant interest in the medical and health fields, due to their intrinsic elasticity simple control strategies for enabling desired interactions. However, current soft hand exoskeletons often exhibit uniform deformation, mismatch profile of interacting objects, seldom quantify assistive effects during activities daily life (ADL), such as extension angle predicted joint stiffness. The lack quantification poses challenges effective...