Alena Rodionova, UPenn. “Foundations of Safe Autonomy: On-Board Verification and Formally-Constrained Machine Learning”

Position:  PhD Candidate

Current Institution:  University of Pennsylvania

Abstract:  Foundations of Safe Autonomy: On-Board Verification and Formally-Constrained Machine Learning

Autonomous vehicles (AVs) have driven millions of miles on public roads, but even the simplest scenarios such as a lane change maneuver, have not been certified for safety. As there is no systematic method to bound and minimize the risk of decisions made by the vehicle’s decision controller, the insurance liability of autonomous vehicles currently is entirely on the manufacturer. Because no single test can determine the safety of self-driving cars, there is a need for fundamental research on methods for assessing the safety of automated driving systems. The main objective of my research is to establish the foundations of Safe Autonomy — trustworthy and fair autonomy where people can safely trust, depend upon, and co-exist with autonomous systems in transportation.

Alena Rodionova is currently a PhD candidate in the Department of Electrical and Systems Engineering at the University of Pennsylvania. Her research is focused on formal analysis and verification of safety-critical systems such as medical devices and risk assessment verification and control of Cyber-Physical Systems such as autonomous vehicles. She received a bachelor’s degree and a master’s degree in mathematics from the Siberian Federal University (Russia) in 2012 and 2014, respectively. Before joining the University of Pennsylvania in 2017, she was with the Cyber-Physical Systems Group at TU Wien, Austria.