avatar

Kanghyun Ryu

Ph.D. Student
University of California, Berkeley
kanghyun.ryu@berkeley.edu


About Me

Hi! I am a Ph.D. student in Mechanical Engineering at the University of California, Berkeley. I am a part of the ICON lab where I am advised by Prof. Negar Mehr. My research interest lies in robot learning, with a particular focus on reinforcement learning, foundation models for robot learning, and multi-agent reinforcement learning.

During my Ph.D., I worked at the Honda Research Institute (HRI) as a research intern, where I developed motion planning algorithms for autonomous driving. Before joining UC Berkeley, I received my B.S. in Aerospace Engineering, from Seoul National University, South Korea.

Research Interests

News

Publications

  1. Preprint
    CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks
    S. Choi*, K. Ryu*, J. Ock, and N. Mehr (*Equal contribution)
    Preprint, 2025.
    Arxiv Code Project Page

  2. ITSC
    IANN-MPPI: Interaction-Aware Neural Network-Enhanced Model Predictive Path Integral Approach for Autonomous Driving
    K. Ryu, M. Sung, P. Gupta, J. D'sa, F. M. Tariq, D. Isele, and S. Bae
    International Conference on Intelligent Transportation Systems (ITSC), 2025.
    Arxiv Project Page

  3. RSS
    DDAT: Diffusion policies enforcing Dynamically Admissible robot Trajectories
    JB. Bouvier, K. Ryu, K. Nagpal, Q. Liao, K. Sreenath, and N. Mehr
    Robotics: Science and Systems (RSS), 2025.
    Arxiv Code Project Page

  4. Risk-Sensitive Orbital Debris Collision Avoidance using Distributionally Robust Chance Constraints
    K. Ryu, JB. Bouvier, S. Lalani, S. Eggl, and N. Mehr
    AIAA SCITECH Forum, 2025.
    Arxiv

  5. ICRA
    CurricuLLM: Automatic Task Curricula Design for Learning Complex Robot Skills using Large Language Models
    K. Ryu, Q. Liao, Z. Li, P. Delgosha, K. Sreenath, and N. Mehr
    International Conference on Robotics and Automation (ICRA), 2025.
    Arxiv Code Project Page

  6. Adaptive Learning from Demonstration in Heterogeneous Agents: Concurrent Minimization and Maximization of Surprise in Sparse Reward Environments
    E. Clark*, K. Ryu*, and N. Mehr (*Equal contribution)
    Learning for Dynamics & Control Conference (L4DC), 2024.
    Arxiv Code

  7. ICRA
    Integrating Predictive Motion Uncertainties with Distributionally Robust Risk-Aware Control for Safe Robot Navigation in Crowds
    K. Ryu and N. Mehr
    International Conference on Robotics and Automation (ICRA), 2024.
    Arxiv Code

  8. Performance Comparison between EKF and UKF in GPS/INS Low Observability Conditions
    K. Ryu, J. Kang, and D. Lee
    The 21th International Conference on Control, Automation, and Systems (ICCAS), 2021.
    Arxiv

Services

Conference Reviewers

Journal Reviewers

Work & Teaching Experiences

Work Experience

Teaching Experience

Honors & Awards

Fellowship

Honors

Travel Grants


Powered by Jekyll and Minimal Light theme.