Research

Our interest here focuses on efficient and effective algorithms to solve challenging Multi-Agent Path Finding (MAPF) problems via a variety of AI and optimization technologies. We are particularly interested in scalable path planning algorithms that can handle hundreds to thousands of agents while considering temporal constraints, dynamic obstacles, and heterogeneous agent capabilities.

We are interested in addressing the challenges of coordinating large-scale Unmanned Aerial Vehicle (UAV) fleets in shared and dynamic airspace. Our research focuses on preflight planning systems that handle temporal No-Fly Zones (NFZs), heterogeneous vehicle profiles, and strict delivery deadlines for urban air mobility applications.

We are interested in learning-based approaches for coordinating teams of agents in complex environments. Our focus includes combining various machine learning techniques such as Bayesian learning, reinforcement learning, large language models (LLMs), diffusion models, and flow matching with classical planning methods to achieve scalable and robust multi-agent coordination.

I contribute to various projects spanning different domains and applications. These projects showcase my diverse interests and collaborative work across multiple research areas.