I am an M.S. student in Robotics at Dongguk University, Korea, in the Interactive Robotics Lab advised by Professor Soo-Chul Lim.
My research focuses on reinforcement learning and imitation learning for robotic manipulation, with an emphasis on closing the sim-to-real gap — building high-fidelity digital twins, collecting data through humanoid teleoperation, and deploying learned policies on real robots.
Research interests: Humanoid Manipulation · Sim-to-Real Transfer · Imitation Learning · Dexterous Hand 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)
Projects
Development of Intelligent Autonomous Manipulation Technology for Humanoids with Reduced Dependency on Real-World Data
Jul 2025 – Present
Robot Motion Generation AI based on Multimodal Vision/Tactile Information Driven by Language Model
Mar 2025 – Present
Awards
First Prize (Grand Prize), 2024 AIoT Creative Integrated Design Competition, Dongguk University Center for Engineering Education Innovation
Nov 2024
Minister's Award, 2024 Creative Integrated Design Competition, Ministry of Trade, Industry and Energy (MOTIE)
Nov 2024
3rd Place, 10th 2024 R-BIZ Challenge, Korean Agency for Technology and Standards (KATS)
Oct 2024