Yuhwan Kwon
Papers
2
Total Citations
6
H-Index
1
About
Yuhwan Kwon is a robotics researcher whose work focuses on bridging the gap between simulation and real-world robotic manipulation, with a particular emphasis on visual model predictive control (MPC) and imitation learning. His key contributions address two critical challenges in robotics: transferring control policies from simulated environments to physical robots with minimal human intervention, and enabling robots to learn and execute long-horizon tasks with diverse goals through human demonstrations. Kwon's most cited work, "Randomized-to-Canonical Model Predictive Control for Real-World Visual Robotic Manipulation" (2022, 5 citations), tackles the sim-to-real transfer problem by proposing a method that reduces the human effort typically required for one-shot transfer, offering a more practical pathway for deploying visual MPC in real-world settings. His subsequent research, "ISPIL: Interactive Sub-Goal-Planning Imitation Learning for Long-Horizon Tasks With Diverse Goals" (2024, 1 citation), addresses distribution mismatch issues in imitation learning, enabling robots to handle complex, multi-step tasks with varying objectives more effectively. Through these contributions, Kwon is advancing the practical applicability of robotic learning systems, making them more adaptable and efficient for real-world deployment.
Research Focus
Key Achievements
Top Papers
- 1
- 2