A5066790771- Prosthetics and Rehabilitation Robotics
- Muscle activation and electromyography studies
- Robot Manipulation and Learning
- Stroke Rehabilitation and Recovery
- Control and Dynamics of Mobile Robots
- Advanced Sensor and Control Systems
- Robotic Locomotion and Control
- EEG and Brain-Computer Interfaces
- Soft Robotics and Applications
- Adaptive Control of Nonlinear Systems
- Robotic Mechanisms and Dynamics
- Advanced Algorithms and Applications
- Vehicle Dynamics and Control Systems
- Robotic Path Planning Algorithms
- Teleoperation and Haptic Systems
- Gaze Tracking and Assistive Technology
- Fault Detection and Control Systems
- Hydraulic and Pneumatic Systems
- Industrial Technology and Control Systems
- Neuroscience and Neural Engineering
- Advanced Computational Techniques and Applications
- Balance, Gait, and Falls Prevention
- Iterative Learning Control Systems
- Advanced Memory and Neural Computing
- Advanced Sensor and Energy Harvesting Materials
Huazhong University of Science and Technology
2016-2025
Beijing Automation Control Equipment Institute
2019-2025
ShanghaiTech University
2024
Kunming University
2023-2024
University of Illinois Urbana-Champaign
2024
East China Jiaotong University
2024
Beihang University
2007-2024
CCCC Wuhan Harbour Engineering Design and Research (China)
2023-2024
CCCC Highway Consultants (China)
2024
Shanghai Jiao Tong University
2024
In this note, a high-order disturbance observer for class of underactuated robotic systems with mismatched uncertainties is proposed. To improve its estimation performance, choice method optimal gain matrices the obtained as solution an optimization problem. A based sliding mode control also designed system disturbance. The stabilities both and controlled closed-loop are proved by Lyapunov theorem. Simulations on benchmark Acrobot demonstrate efficiency proposed approaches.
In this paper, a novel high-order disturbance observer (HODO) for the mobile wheeled inverted pendulum (MWIP) system is first proposed. Based on choice method of optimal gain matrices, estimation accuracy HODO can be improved. Combining proposed and sliding mode control (SMC), new strategy designed balance speed MWIP system. The boundness error proved stability closed-loop achieved through appropriate selection surface coefficients. effectiveness all methods verified by experiments real
Abstract Traditional human emotion recognition is based on electroencephalogram (EEG) data collection technologies which rely plenty of rigid electrodes and lack anti‐interference, wearing comfort, portability. Moreover, a significant distribution difference in EEG also results low classification accuracy. Here, on‐skin biosensors with adhesive hydrophobic bilayer hydrogel (AHBH) as interfaces for high accuracy are proposed. The AHBH achieves remarkable adhesion (59.7 N m −1 ) by combining...
Abstract Recent advances in flexible wearable devices have boosted the remarkable development of for human–machine interfaces, which are great value to emerging cybernetics, robotics, and Metaverse systems. However, effectiveness existing approaches is limited by quality sensor data classification models with high computational costs. Here, a novel gesture recognition system triboelectric smart wristbands an adaptive accelerated learning (AAL) model proposed. The array well deployed...
There has been increasing interest in a type of underactuated mechanical systems, mobile-wheeled inverted-pendulum (MWIP) models, which are widely used the field autonomous robotics and intelligent vehicles. Robust-velocity-tracking problem MWIP systems is investigated this study. In velocity-control problem, model uncertainties accompany uncertain equilibriums, make controller design become more difficult. Two sliding-mode-control (SMC) methods proposed for both capable handling parameter...
An intelligent cane robot is designed for aiding the elderly and handicapped people's walking. The consists of a stick, group sensors, an omnidirectional basis driven by three Swedish wheels. Recognizing user's walking intention plays important role in motion control our robot. To quantitatively describe intention, concept called "intentional direction (ITD)" proposed. Both state model observation ITD are obtained enumerating possible modes analyzing relationship between human–robot...
Recognition of the wearer's motion intention plays an important role in study power-assist robots. In this paper, intention-guided control strategy is proposed and applied to upper-limb exoskeleton. Meanwhile, a human-robot interface comprised force-sensing resistors (FSRs) designed estimate upper limb real time. Moreover, new concept called "intentional reaching direction (IRD)" quantitatively describe intention. Both state model observation IRD are obtained by studying behavior modes...
This paper presents an integrated interval type-2 fuzzy logic approach that simultaneously models and controls underactuated mobile two-wheeled inverted pendulum (MTWIP), which suffers from modeling uncertainties external disturbances. The control objective is to attain the desired position direction while keeping MTWIP balanced. It achieved by integrating four systems (IT2 FLSs): first IT2 FLS describes dynamics of using a Takagi-Sugeno model, second balance also third fourth FLSs its...
The class imbalance problem has been known to hinder the learning performance of classification algorithms. Various real-world tasks such as text categorization suffer from this phenomenon. We demonstrate that active is capable solving problem.
In this brief, a dynamic model of mobile wheeled inverted pendulum (MWIP) system is improved considering friction forces, and nonlinear disturbance observer (NDO)-based surface controller investigated to control the MWIP system. Using coordinate transformation, non-Class-I type underactuated presented as semistrict feedback form, which convenient for design. A together with an NDO designed stabilize plant. The proposed approach can compensate external disturbances uncertainties improve...
A wearable, portable, low-cost, and easy-to-use upper extremity exoskeleton robot, RUPERT, is presented here for clinical in-home therapies of patients who have survived a stroke. The robot system has five degrees-of-freedom driven by compliant safe pneumatic muscles. Its primary function to assist the movement an affected arm in 3-D space perform daily training program virtual environment. Subjects are recruited experiments both therapies. While using most subjects exhibited significant...
In this paper, a phenomenological model of pneumatic muscle is established consisting contractile element, spring and damping element in parallel. To verify the practicability (PM) modeling, dynamic surface control (DSC) characterized by convenient design good transient performance employed for realizing PM tracking control. However, parametric uncertainty inevitable modeling as friction unknown external disturbances exist system. These errors variables can undermine deteriorate systems....
Traffic problems such as pollution and congestion are becoming more serious in urban areas. A potential solution to these is develop narrow vehicles that occupy less space have lower emissions. There has been increasing interest underactuated mechanical systems, i.e., mobile wheeled inverted pendulum (MWIP) models, which widely used the field of autonomous robotics intelligent vehicles. novel vehicle based on an MWIP a movable seat, called UW-Car, investigated this paper. The dynamic model...
Takagi–Sugeno–Kang (TSK) fuzzy systems are very useful machine learning models for regression problems. However, to our knowledge, there has not existed an efficient and effective training algorithm that ensures their generalization performance also enables them deal with big data. Inspired by the connections between TSK neural networks, we extend three powerful network optimization techniques, i.e., minibatch gradient descent (MBGD), regularization, AdaBound, systems, propose novel...
An intelligent walking-aid cane robot is developed for assisting the elderly and physically challenged with walking. A motion control method proposed based on human walking intention estimation. Moreover, safety investigated both elderly. The fall detection prevention concepts are to guarantee of while robot. However, deficiency that it can be overturned easily because its small size light weight. Therefore, a controllable universal joint designed adjusting tilted angle stick. stability...
Takagi-Sugeno-Kang (TSK) fuzzy systems are flexible and interpretable machine learning models; however, they may not be easily optimized when the data size is large, and/or dimensionality high. This article proposes a minibatch gradient descent (MBGD) based algorithm to efficiently effectively train TSK classifiers. It integrates two novel techniques: First, uniform regularization (UR), which forces rules have similar average contributions output, hence increase generalization performance of...
Human activity recognition (HAR) based on the wearable device has attracted more attention from researchers with sensor technology development in recent years. However, personalized HAR requires high accuracy of recognition, while maintaining model's generalization capability is a major challenge this field. This paper designed compact wireless node, which combines an air pressure and inertial measurement unit (IMU) to provide multi-modal information for model training. To solve user...
The dynamic properties and non-linear control of the pneumatic muscle actuator (PMA) were investigated in this study for use a specially designed hand rehabilitation device. phenomenological model PMA was established lower pressure range applicable rehabilitation. experimental results show that PMA's characteristics can be approximated by piecewise functions. In order to improve performance robustness accurate trajectory tracking, sliding mode based on disturbance observer (SMCBNDO)...