A5023077721- Adaptive Control of Nonlinear Systems
- Muscle activation and electromyography studies
- Stroke Rehabilitation and Recovery
- Prosthetics and Rehabilitation Robotics
- Robot Manipulation and Learning
- Modular Robots and Swarm Intelligence
- Adaptive Dynamic Programming Control
- Iterative Learning Control Systems
- Dynamics and Control of Mechanical Systems
- Robotic Mechanisms and Dynamics
- EEG and Brain-Computer Interfaces
- Distributed Control Multi-Agent Systems
- Mechanical Circulatory Support Devices
- Advanced Algorithms and Applications
- Astro and Planetary Science
- Space Satellite Systems and Control
- Stability and Control of Uncertain Systems
- Robotic Path Planning Algorithms
- Piezoelectric Actuators and Control
- Vibration and Dynamic Analysis
- Structural Analysis and Optimization
- Vehicle Dynamics and Control Systems
- Advanced Control Systems Optimization
- Soft Robotics and Applications
- Reinforcement Learning in Robotics
Jilin Engineering Normal University
2022-2024
IRD Fuel Cells (Denmark)
2024
Changchun University of Technology
2013-2023
Wind Power Engineering (Japan)
2022
Energy Storage Systems (United States)
2022
Guidewire (United States)
2022
Cytoskeleton (United States)
2022
Twelfth Guangzhou City People's Hospital
2020-2021
Guangzhou Medical University
2020-2021
Facing Our Risk of Cancer Empowered
2021
In order to solve the problem which key information of facial expression missed under partial occlusion, this paper proposes a recognition method based on Weber Local Descriptor (WLD) histogram feature and decision fusion. Firstly, image is divided into several non-overlapping rectangle regions with equal size WLD used extract features each region. The purpose that face spatial be ready for subsequent Secondly, region further blocks sub-block computed combined as so discriminative accurately...
Abstract How to establish a self‐equilibrium configuration is vital for further kinematics and dynamics analyses of tensegrity mechanism. In this study, investigating form‐finding problems, concise efficient dynamic relaxation‐noise tolerant zeroing neural network (DR‐NTZNN) algorithm established through analysing the physical properties structures. addition, non‐linear constrained optimisation problem which transformed from solved by sequential quadratic programming algorithm. Moreover,...
The main technical challenge in decentralized control of modular and reconfigurable robots (MRRs) with torque sensor is related to the treatment interconnection term friction term. This paper proposed a modified adaptive sliding mode strategy for trajectory tracking MRRs. radial basis function (RBF) neural network used as an effective learning method approximate term, eliminating effect model uncertainty reducing controller gain. In addition, order provide faster convergence higher precision...
This paper presents a decentralized zero-sum optimal control method for MRMs with environmental collisions via an actor-critic-identifier (ACI) structure-based adaptive dynamic programming (ADP) algorithm. The model of the is formulated novel collision identification that deployed each joint module, in which local position and torque information are used to design compensation controller. A neural network (NN) identifier developed compensate uncertainties then, problem can be transformed...
In this paper, a novel RBF neural network-iterative learning control (RBFILC) methodology is proposed, investigated and analyzed for low limb rehabilitation robot (LLRR) to assist patients in passive training. The asymptotic stability of the RBFILC approach proposed verified via classical Lyapunov theory, which simulates behavior healthy human body by 3-degree freedoms (DOFs) sagittal plane LLRR system. Furthermore, MATLAB software utilized conduct simulation experiments on model. results...
In this paper, firstly, a high accuracy one-step-ahead numerical differentiation formula with O(τ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> ) pattern is proposed for discretization. Meanwhile, precision first-order derivative of the backward difference rule error given to approximate information. Then, two discrete-time zeroing-type models (HADTZTM) pattern, i.e., HADTZTM information known (HADTZTM-K) and unknown (HADTZTM-U), are...
In this paper, we propose a novel facial expression recognition method under partial occlusion based on Gabor multi-orientation features fusion and local binary pattern histogram sequence (LGBPHS). Firstly, the filter is adopted to extract multi-scale features. Secondly, magnitudes of different orientations in same scale will be fused according rule paper then are further encoded by using LBP operator. Finally, image divided into several non-overlapping rectangle units with equal size, each...