A5079823850- Robot Manipulation and Learning
- Prosthetics and Rehabilitation Robotics
- Robotic Mechanisms and Dynamics
- Textile materials and evaluations
- Industrial Technology and Control Systems
- Industrial Vision Systems and Defect Detection
- Control Systems in Engineering
- Induction Heating and Inverter Technology
- Advanced Algorithms and Applications
- Fault Detection and Control Systems
- Reinforcement Learning in Robotics
- 3D Shape Modeling and Analysis
Shandong University
2023
Nanjing Institute of Railway Technology
2010
Given the problem of exploration and utilization, high interaction cost deep reinforcement learning is sometimes unacceptable. Moreover, model trained by cannot adapt to complex changeable assembly environment quickly owing weak generalization ability. Thus, knowledge transfer framework established for different robot peg-in-hole assemblies in this article reinforce ability utilization efficiency data. In framework, source domain through Proximal Policy Optimization algorithm. The accurately...
A robot screwing skill learning framework based on teaching–learning is proposed to improve the generalization ability of robots for different scenarios and objects, combined with experience a human operation. This includes task-based teaching, learning, summarization. We teach twist gather operation’s trajectories, define obstacles potential functions, counter twisting using skill-learning-based dynamic movement primitive (DMP) Gaussian mixture model–Gaussian regression (GMM-GMR). The...
Deformable object manipulation has been considered a challenging task for robots its complex dynamics and the infinite dimensional configuration space. Fabric unfolding takes on critical significance in textile industry household services. Accordingly, enabling to possess above-mentioned skill confirmed as crucial task. In this study, general framework is developed transferring human skills fabric manipulation. The comprises two key components (i.e., behavior cloning learn policy learning...