Research I work on computer vision, robotics and machine learning. I am interested in building agents that can intelligently interact with the physical world around them. I am currently focusing on two aspects: a) choice and design of representations that enable such interaction, and b) what and how to learn from active interaction. Some example problems that we are tackling include: building spatio-semantic and topological representations for visual navigation, skill discovery, learning for and from videos, and active visual leaning. My research is funded through National Science Foundation, DARPA Machine Common Sense Program, NASA, USDA/NSF AIFARMS National AI Institute, and Amazon.