Bring what only
you can bring.

• Multi-agent coordination
• Game theory
• Intelligent transportation systems

Do smarter agents necessarily make better teams? I study multi-agent coordination: how autonomous agents can make better decisions together. My research combines game theory and multi-agent learning to align individual decisions with collective goals, especially for safer, more efficient transportation.

• Autonomous Systems
• Multi-Agent Decision-Making
• Collective Intelligence

I study how autonomous systems and people can make better decisions together. My research focuses on coordination, learning, and strategic interaction among multiple agents in complex environments, with applications to mixed-autonomy transportation. The goal is to design systems that are safer, more efficient, and beneficial at the collective level.

• Game-Theoretic Transportation Modeling
• Intelligent Transportation Systems
• Large Language Models (LLMs)

My research studies how drivers, automated vehicles, and mobility operators make strategic decisions in shared transportation systems. I combine game-theoretic equilibrium modeling, traffic simulation and data, and LLM-assisted model discovery to understand merging behavior, mixed-autonomy coordination, and competition on congested networks.

• AMoD
• Reinforcement Learning
• Machine Learning

I study how autonomous taxi fleets should reposition empty vehicles across cities. I compare different optimization goals and measure the tradeoff between profit and equity across supply-and-demand conditions.

• Reinforcement Learning

I study how autonomous vehicles can help reduce traffic congestion. Through the MAPLE project, I build and run traffic simulations to evaluate our coordination framework and measure its effects on mixed-autonomy traffic efficiency.