Towards Trustworthy Autonomy: Robust, Informative Predictions and Intuitive Control Frameworks
While a future with ubiquitous autonomy approaches, the transition will not be instantaneous. This suggests: (1) levels of autonomy will be introduced incrementally and (2) autonomous vehicles must be capable of driving with humans on the road. Consequently, human drivers must be rigorously modeled in a manner that is easily integrated into control. We present robust, predictive modeling methods and innovative design approaches for optimizing interaction between humans and autonomy. These techniques were applied in safety systems for semiautonomous frameworks and autonomous vehicles that mimic nuanced human interactions. Such systems demonstrate improved predictability and trustworthiness, crucial characteristics for pervasive autonomy.
Katie is currently a PhD Candidate in Electrical Engineering and Computer Science at the University of California, Berkeley, advised by Professor Ruzena Bajcsy. Prior to that, she received a B.S.E. from Arizona State University in 2012 and a M.S. from UC Berkeley in 2015. Her research considers the integration of autonomy into human dominated fields, in terms of safe interaction in everyday life, with a strong emphasis on novel modeling methods, experimental design, and control frameworks. She received the Demetri Angelakos Memorial Achievement Award for her contributions to the community. Beyond research, Katie enjoys outreach, reading, and learning new trivia.