I am in the final year of my PhD at Brown University advised by Professor Nora Ayanian. My research focuses on coordination in multi-agent, multi-robot systems, and robotics education. My primary research is on Multi-Agent Path Finding (MAPF). MAPF is the problem of finding non-conflicting paths for many agents in discrete environemnts represented with graphs. We study how we can use machine learning techniques to leverage existing algorithms to combine their strengths together. I also work on using robot systems (e.g. Crazyswarm) to make art and interactive demos in the hopes of making a robotics curriculum more accessible to students with diverse backgrounds.

Current Research Projects

Learning for Multi Agent Path Finding

Multi Agent path finding (MAPF) is the task of finding paths for a number of agents through an (typically discrete) environment that do not collide. This problem is of particular importance for warehouse robotics, where a large number of agents are operating within a confined space. We are attempting to use deep learning to speed up the solving time of some common algorithms for MAPF.

Past Research Projects

Human-Coordination Inspired Robotics

We have collected data from a large number of people playing a single shape formation game without, which requires high levels of coordination without any form of explicit communication. From an AI perspective, this is a very hard task. Humans complete the task in a decentralized way, with limited information about the game state, with large numbers of participants, and no explicit communication, all of which create difficulties for traditional AI planners. But humans can not only complete the task, but can also do so robustly. This project focuses on learning from the way that humans coordinate, to build robotic systems that are also able to reason about high numbers of agents in a robust way.