I am a Mechanical Engineering Ph.D. student at UC Berkeley, advised by Prof. Negar Mehr in the ICON Lab. My research focuses on learning decentralized multi-agent coordination policies, with an emphasis on generative modeling, imitation learning, and enabling robots to coordinate effectively without explicit communication. I am particularly interested in developing generalizable robot learning methods that enable diverse collaborative behaviors with limited demonstrations.
Previously, I worked in the Intelligent Autonomy Lab at Yale University under Dr. Ian Abraham.
Residual Denoising Enables Sample-Efficient Multi-Agent Coordination on Demand
Dayi Ethan Dong,
Maulik Bhatt,
Aayushi Shrivastava,
Lasse Peters,
Negar Mehr
arXiv preprint, 2026
Website •
Github •
Paper
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
Dayi Ethan Dong*,
Maulik Bhatt*,
Seoyeon Choi,
Negar Mehr
International Conference on Robotics and Automation (ICRA) 2026
Website •
Github •
Paper
Ergodic Exploration over Meshable Surfaces
Dayi Ethan Dong,
Albert Xu,
Geordan Gutow,
Howie Choset,
Ian Abraham
International Conference on Robotics and Automation (ICRA) 2025
Paper
Leveraging Large Language Models for Effective and Explainable Multi-Agent Credit Assignment
Kartik Nagpal,
Dayi Ethan Dong,
Jean-Baptiste Bouvier,
Negar Mehr
Autonomous Agents and Multiagent Systems (AAMAS) 2025
Website •
Paper
Time-optimal Ergodic Search: Multiscale Coverage in Minimum Time
Dayi Ethan Dong,
Henry Berger,
Ian Abraham
International Journal of Robotics Research
Github •
Paper
Time Optimal Ergodic Search
Dayi Ethan Dong,
Henry Berger,
Ian Abraham
Robotics: Science and Systems (RSS) 2023
Best Paper Award •
Github •
Paper
Safety-critical Ergodic Exploration in Cluttered Environments via Control Barrier Functions
Cameron Lerch,
Dayi Ethan Dong,
Ian Abraham
International Conference on Robotics and Automation (ICRA) 2023
Github •
Paper