Team
Yunhai Han
My name is Yunhai Han and I am a Robotics PhD student at Georgia Institute of Technology, advised under Prof. Harish Ravichandar. My research focus at Georgia Tech is about learning for contact-rich manipulation & Locomotion. I am also honoured to be an awardee of Robotics PhD fellowship from Georgia Tech’s Institute for Robotics and Intelligent Machines (IRIM). Before coming to Georgia Tech, I received my M.S. / B.S. in Mechanical Engineering from UCSD, 2021 and Yanshan University, 2019, respectively
Papers
- Safe Navigation of Bipedal Robots via Koopman Operator-Based Model Predictive Control — International Conference on Intelligent Robots and Systems (IROS), 2026
- OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies — Workshop on Tactile Sensing for Robotic Foundation Models, Robotics: Science and Systems (RSS) - Oral Spotlight, 2026
- Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video — Preprint, 2026
- Going with the Flow: Koopman Behavioral Models as Pseudo Planners for Visuo-Motor Dexterity — Preprint, 2026
- ImMimic: Cross-Domain Imitation from Human Videos via Mapping and Interpolation — Conference on Robot Learning (CoRL) - Oral, 2025
- AsymDex: Asymmetry and Relative Coordinates for RL-based Bimanual Dexterity — Preprint, 2025
- On the Surprising Effectiveness of Spectral Clipping in Learning Stable Linear and Latent-Linear Dynamical Systems — Preprint, 2025
- CIMER: Combining Imitation and Emulation to Learn Prehensile Dexterity from State-only Observations — IEEE International Conference on Robotics and Automation (ICRA), 2025
- AsymDex: Leveraging Asymmetry and Relative Motion in Learning Bimanual Dexterity — Workshop on Whole-body Control and Bimanual Manipulation: Applications in Humanoids and Beyond, Conference on Robot Learning (CoRL), 2024
- KOROL: Learning Visualizable Object Feature with Koopman Operator Rollout for Manipulation — Conference on Robot Learning (CoRL), 2024
- Learning Prehensile Dexterity by Imitating and Emulating State-only Observations — IEEE Robotics and Automation Letters, 2024
- On the Utility of Koopman Operator Theory in Learning Dexterous Manipulation Skills — Conference on Robot Learning (CoRL) - Oral, 2023