Yunlei Shi
Papers
4
Total Citations
41
H-Index
2
About
Yunlei Shi is a robotics researcher whose work sits at the intersection of robotic manipulation, machine learning, and human-robot interaction. His research focuses on two principal challenges in modern robotics: enabling robots to grasp and manipulate unknown objects effectively, and programming robots to handle contact-rich assembly tasks safely and adaptively. Shi's most recognized contribution is FFHNet (2022), a deep learning framework that generates diverse, high-quality multi-fingered robotic grasps for unknown objects in real-time — a problem that had long eluded the field — earning 24 citations and establishing him as a notable voice in dexterous manipulation research. Complementing this, his work on impedance adaptation through reinforcement learning and Contact Dynamic Movement Primitives (2022, 13 citations) addresses the critical challenge of making robots robust to variations in contact geometry during force-sensitive tasks. His additional research explores sim-to-real transfer using CycleGAN and force control, as well as hybrid learning frameworks that combine demonstration and exploration for constrained assembly environments. Collectively, Shi's contributions advance the goal of deploying flexible, intelligent robotic systems capable of operating reliably in real-world industrial and collaborative settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4