AI for unstructured field robotics: model-based learning and planning under uncertainty, using minimal sensing/actuation and contact-rich dynamics to deliver safe, data-efficient, field-ready autonomy.

Autonomous Decision-Making Under Uncertainty, Belief Space Planning, Semantic Perception and Simultaneous Localization and Mapping (SLAM), and Probabilistic Inference in Single- & Multi-Agent Systems.

Automated Planning, Artificial Intelligence, Robotics.

Multi-agent AI, multi-robot systems, collaborative AI, multi-agent environment design, integrated task and motion planning for robotics, and multi-agent reinforcement learning.

Developing efficient, provably high-quality algorithms for motion planning and search in complex systems such as surgical robotics and warehouse automation. My work bridges basic theory and practice.

I aim to endow individual robots and multi-robot teams with theory-driven and practical algorithms for tackling complex tasks in the real world.

My research focuses on AI and machine learning, with an emphasis on robotics applications. My long term goal is to bring robots into human-centered domains such as homes and hospitals. Towards this goal, some fundamental questions need to be solved, such as how can machines learn models of their environments that are useful for performing tasks, and how to learn behavior from interaction in an interpretable and safe manner. Most of my work falls under the framework of reinforcement learning, and its connections to representation learning and planning.