Papers
4
Total Citations
33
H-Index
3
About
Yunpeng He is a rising researcher at the forefront of intelligent robotic systems, with key contributions spanning agile manufacturing, sim-to-real transfer learning, and continual learning for industrial robots. His work addresses critical challenges in deploying autonomous robots in complex, unstructured environments. He is perhaps best known for his design and implementation of an agent-based robotic system for agile manufacturing, detailed in a 2022 case study on the ARIAC 2021 competition, which has garnered 16 citations and serves as a foundational reference for adaptive manufacturing workflows. He has also pioneered a Kalman Filter-based one-shot sim-to-real transfer learning approach (9 citations), enabling deep reinforcement learning algorithms to bridge the simulation-to-reality gap without extensive physical sampling—a breakthrough for equipment safety and lifespan. More recently, He has tackled the problem of catastrophic forgetting in robot continual learning, introducing a guided policy search method enhanced with memory-aware synapses (7 citations). His latest work explores fuzzy second-order integral terminal adaptive sliding mode control for marine cable-driven parallel grinding robots, demonstrating his versatility in applying advanced control theory to specialized domains.
Research Focus
Key Achievements
Top Papers
- 1
- 2Kalman Filter-Based One-Shot Sim-to-Real Transfer Learning9 citations · 2023
- 3
- 4