A5101741969- Robot Manipulation and Learning
- Muscle activation and electromyography studies
- Soft Robotics and Applications
- Hydraulic and Pneumatic Systems
- Elevator Systems and Control
Zhujiang Hospital
2023-2024
Southern Medical University
2023-2024
Purpose To address the challenge of maintaining stable contact force when a robot end-effector interacts with an unknown environment, this paper aims to propose control algorithm based on radial basis function (RBF) neural network stiffness prediction and reinforcement learning. Design/methodology/approach Based traditional controller, learning is used find optimal parameters control. enhance convergence speed learning, RBF fit predicted environment stiffness, then combined Gaussian model,...
To address traditional impedance control methods' difficulty with obtaining stable forces during robot-skin contact, a force based on the Gaussian mixture model/Gaussian regression (GMM/GMR) algorithm fusing different compensation strategies is proposed. The contact relationship between robot end effector and human skin established through an model. allow to adapt flexible environments, reinforcement learning algorithms strategy mechanics model compensate for strategy. Two environment...
To address the problem that traditional force control methods have difficulty obtaining stable forces during a robot massage, algorithm based on residual reinforcement learning is proposed. An initial strategy of massage first constructed with impedance control, but often fluctuates when skin environment unknown to robot. A then used analyze relationship between contact state and offset displacement compensate for residuals controller. speed up search compensation strategy, neural network...