Dr. Anca Dragan is an Assistant Professor in the Electrical Engineering and Computer Sciences Department at UC Berkeley. She runs the InterACT (Interactive Autonomy and Collaborative Technologies) Lab, which focuses on the (re)design of robotics algorithms for interaction and coordination with people. Anca got her PhD from the Robotics Institute at Carnegie Mellon in 2015 for her work on legible (goal-expressive) robot motion planning.
Since starting on the faculty at Berkeley in 2015, Anca’s research has focused on accounting for the influence that robot actions will have what people do in order to enhance coordination across autonomous driving and manipulation applications; on enabling robot transparency beyond motion goals; and on value alignment -- enabling robots to interactively learn the right objectives. Anca helped found and serves on the steering committee for the Berkeley AI Research (BAIR) Lab, and is a co-Pi on the Center for Human-Compatible AI.
She has won an NSF CAREER award, the Okawa Foundation award, and was on MIT Tech Review's 35 innovators under 35 list. Her research has been featured in The Atlantic, New Scientist, WIRED, IEEE Spectrum, and NPR.
Keynote: Perceiving Human Internal State
Robots perceive and act so that they can optimize their objective functions. They assume that somehow, their objective is exogenously specified. But in fact, they come from people: someone sits down and figures out what objective to write down in order to incentivize the right behavior. People are unfortunately imperfect, and this process often leads to misspecification. What is more, the robot usually gets shipped off to help not its designer, but an end-user. Ultimately what the robot should optimize is not exactly the objective that its designer intended, but rather the objective that it's end-user intends. In this talk, we will look at algorithms that enable robots to work together with designers and end-users to estimate what its true objective function ought to be.