Hojin Lee

Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University of Munich (TUM)

profile_nofilter.jpg

Carl-Zeiss-Straße 8

Munich, 85748

My research focuses on uncertainty quantification, adaptive and robust learning-based systems, active learning for perception and planning, representation learning in unstructured environments, hierarchical reinforcement learning, and human-in-the-loop reinforcement learning for robotic applications.

I received my Ph.D. in Mechanical Engineering from the High Assurance Mobility Control Lab at the Ulsan National Institute of Science and Technology (UNIST), Republic of Korea, where I worked on uncertainty-aware planning and control for autonomous systems.

My previous research includes distributed optimal control and estimation for multi-agent systems, agent-to-agent interaction prediction and intent inference, off-road navigation, and continual learning for autonomous systems.

selected publications

  1. continual_ral_2025.png
    Continual Learning for Traversability Prediction With Uncertainty-Aware Adaptation
    Hojin Lee, Yunho Lee, Daniel A Duecker, and Cheolhyeon Kwon
    IEEE Robotics and Automation Letters, 2025
  2. iet2024.png
    Linear quadratic control and estimation synthesis for multi-agent systems with application to formation flight
    Hojin Lee, Chanyong Lee, Jusang Lee, and Cheolhyeon Kwon
    IET Control Theory & Applications, 2024
  3. ral2024.png
    Kernel-based Metrics Learning for Uncertain Opponent Vehicle Trajectory Prediction in Autonomous Racing
    Hojin Lee, Youngim Nam, Sanghun Lee, and Cheolhyeon Kwon
    IEEE Robotics and Automation Letters, 2024
  4. icra2023.png
    Learning-based Uncertainty-aware Navigation in 3D Off-Road Terrains
    Hojin Lee, Junsung Kwon, and Cheolhyeon Kwon
    In 2023 IEEE International Conference on Robotics and Automation (ICRA), 2023