Nam Jun Cho
Papers
4
Total Citations
43
H-Index
3
About
Nam Jun Cho is a robotics researcher whose work centers on enabling robots to learn, improve, and generalize complex motor skills, particularly for precision assembly tasks. His most influential contribution is a framework that combines imitation learning and self-learning to master peg-in-hole operations—a critical challenge in manufacturing automation. This work, which has garnered 30 citations, demonstrates how robots can acquire and refine both "hole search" and "peg insertion" skills. Cho has also pioneered methods for structuring motor skill transfer, showing that learning order based on motion complexity can significantly enhance reinforcement learning efficiency. His research on motion granularity—characterizing movements by their grossness and fineness—provides a novel lens for understanding skill acquisition in daily-life tasks. By modeling motor skills through Gaussian mixture models and evaluating transfer orders, Cho has advanced the field of robot learning, making assembly automation more adaptive and efficient. His work bridges the gap between human-like skill learning and robotic precision, offering practical pathways for industrial robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4