Gyung Nam Han
Papers
1
Total Citations
5
H-Index
1
About
Gyung Nam Han is a robotics researcher whose work centers on skill learning, human-robot interaction, and autonomous manipulation. His primary contributions lie in developing methods for robots to acquire and refine complex manipulation skills from human demonstrations. In his highly cited work, "Skill learning using temporal and spatial entropies for accurate skill acquisition" (2013, 5 citations), Han introduced a novel approach that segments motion trajectories into four distinct portions based on spatial variations between demonstrations. By leveraging temporal and spatial entropy, his method enables robots to identify critical phases of a task—such as precise alignment or force application—and learn more accurate, generalizable skills. This work has influenced subsequent research in learning from demonstration and adaptive control. Han’s research bridges the gap between human expertise and robotic autonomy, with applications in manufacturing, assistive robotics, and dexterous manipulation. His contributions continue to shape how robots understand and replicate human-like precision in real-world tasks.
Research Focus
Key Achievements
Top Papers
- 1