Yu Men
Papers
6
Total Citations
65
H-Index
4
About
Yu Men is a leading researcher in robot skill generalization and transfer learning for industrial assembly tasks, with a particular focus on peg-in-hole and screwing operations. His work addresses one of robotics' most pressing challenges: enabling robots to adapt learned manipulation skills to new tasks without costly retraining or extensive human demonstration. Men's major contributions include developing feature-selected adaptation transfer methods that allow robots to generalize assembly skills across different tasks, reducing environmental interaction costs by up to 50% compared to traditional deep reinforcement learning approaches. His most cited paper (25 citations) introduces a novel framework for skill generalization that minimizes robot wear and tear during learning. Men also pioneered the use of fuzzy logic-based reward functions for deep deterministic policy gradient algorithms, enabling robots to handle dynamic contact changes during assembly of weak-stiffness parts. His ensemble transfer strategy, which leverages domain differences between tasks, has been recognized for its practical industrial applications. With over 65 total citations across six publications from 2022-2025, Men's work is increasingly influential in advancing robot autonomy for manufacturing. His research bridges the gap between theoretical transfer learning and real-world industrial deployment, making him a key figure in the next generation of adaptive robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5Research on Robot Screwing Skill Method Based on Demonstration Learning3 citations · 2023
- 6