Christopher Watson

My name is Chris Watson and I'm a fourth year Ph.D. student at the University of Pennsylvania, where I am very fortunate to be advised by Rajeev Alur and Dinesh Jayaraman.

I work at the intersection of Robot Learning and Formal Methods. I study how human-provided and autonomously-discovered task structure can work together to scaffold effective learning. Ideally, a human would be able to specify a robot's task in a way that is intuitive, flexible enough to allow let the robot customize its approach to its unique capabilities, and exposes structure within the task to facilitate efficient learning. Oftentimes, a lot of the most interesting and useful task structure is not obvious to humans and must be discovered by the robot during learning. My research focus is to develop forms of specification that leave room for the robot to add its own learned information, learning algorithms that let the robot discover task structure from firsthand experience, training methodologies that harmoniously combine both sources of structure.

I am a proud member of Penn's PLClub and the ASSET center (where I was recently featured in an article that describes our goal of safe, explainable, and trustworthy AI!).

Papers

Teaching Assistantships

Activities

I've had the pleasure of being a student volunteer at POPL'22 and CCC'22, and of being a student at SSFT'22 and OPLSS'22.

Chris

Chris in a group picture
Spotted at OPLSS picture day

ccwatson at seas dot upenn dot edu