Our mission is to develop theoretical foundations and practical algorithms for interactive robot learning. Our group is focused on formalizing interactions and how to learn from diverse sources of data to build sample-efficient, human-aligned, and interactive robot policies. We leverage tools from machine learning, control theory, and cognitive science for building robots that can seamlessly coordinate with, collaborate with, compete with, or influence humans.

Foundation Models
for Robotics
Interactive Robot Learning
Human-AI/Robot Interaction