Papers
7
Total Citations
180
H-Index
5
About
Byungchan Kim’s research lies at the intersection of human motor control, robotic manipulation, and machine learning, with a central focus on enabling robots to perform contact tasks with human-like dexterity. His most influential work, “Impedance Learning for Robotic Contact Tasks Using Natural Actor-Critic Algorithm” (2009, 103 citations), pioneered a framework that allows robots to adaptively modulate their arm impedance—a key human strategy for handling uncertain environments. By combining reinforcement learning with human motor control theory, Kim provided a principled method for robots to learn stiffness and damping parameters autonomously. His 2009 study on estimating multijoint stiffness from electromyogram signals using artificial neural networks (36 citations) further bridged neuroscience and robotics, offering a data-driven approach to decode human arm compliance. Kim also contributed to practical robotic control, including methods for managing impulsive contact forces in mobile manipulators (2010, 19 citations). His work on equilibrium point control using biologically-inspired redundant actuation (2013) and early machine learning-based impedance control (2006) helped lay the groundwork for learning-based physical interaction. Through these contributions, Kim has advanced the understanding of how robots can acquire and replicate the adaptive, compliant behaviors that make human manipulation so effective.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7