I am a Ph.D. candidate in Mechanical Engineering at Dongguk University, Korea, advised by Professor Soo-Chul Lim, where I also earned my M.S. degree.

My research builds reinforcement learning methods that transfer reliably from simulation to the real world, enabling robots to perform dexterous and dynamic manipulation tasks.

Research Interests

• Reinforcement Learning for Robotics
• Sim-to-Real Transfer
• Bridging the Sim-to-Real Gap
• Robot Manipulation
• Dexterous Manipulation

Publications

Pixel2Catch: Multi-Agent Sim-to-Real Transfer for Agile Manipulation with a Single RGB Camera
Seongyong Kim, Junhyeon Cho, Kang-Won Lee, Soo-Chul Lim
IEEE Robotics and Automation Letters (RA-L), 2026 (Accepted)

Project Page Video Code

Progressive Policy Learning: A Hierarchical Framework for Dexterous Bimanual Manipulation
Kang-Won Lee, Jung-Woo Lee, Seongyong Kim, Soo-Chul Lim
Mathematics 2025, 13(22), 3585

Paper Video

Prediction of Delay-Free Scene for Quadruped Robot Teleoperation: Integrating Delayed Data with User Commands
Seunghyeon Ha*, Seongyong Kim*, Soo-Chul Lim
IEEE Robotics and Automation Letters, vol. 10, no. 3, pp. 2846–2853, March 2025
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2025) Oral & Poster Presentation

Paper Project Page Video Poster

* Equal contribution

Effects of Sensing Tactile Arrays, Shear Force, and Proprioception of Robot on Texture Recognition
Jung-Hwan Yang, Seongyong Kim, Soo-Chul Lim
Sensors 23, no. 6: 3201

Paper Video

Projects

Awards

Presentations

Work Experience