I direct the Robot Vision and Learning (RVL) lab at the University of Toronto. My research spans mobile robotics, computer vision, machine learning, planning and control. My goal is to develop methods that enable robots to efficiently learn how to perform reliably in outdoor environments and alongside humans. When human supervision and human-robot interaction are necessary, I want to enable people to effectively specify the desired behavior of their robots through as few interactive demonstrations as possible, without requiring them to write code. I am particularly interested in:

Robust imitation learning from visual data
Bayesian inverse reinforcement learning of cost functions
Planning and control under cost function and model uncertainty, as well as partial observability
Learning visual attention operators for robot exploration, navigation, and search
Shared autonomy and safe control for human-robot collaboration
Active semi-supervised learning for visual data
Perception and semantic video understanding
Field robotics and deployment in outdoor environments