Learning Autonomous Vehicle Safety Concepts from Demonstrations

Abstract-- Evaluating the safety of an autonomous vehicle (AV) depends on the behavior of surrounding agents which can be heavily influenced by factors such as environmental context and informally-defined driving etiquette. A key challenge is in determining a minimum set of assumptions on what constitutes reasonable foreseeable behaviors of other road users for the development of AV safety models and techniques. In this paper, we propose a data-driven AV safety design methodology that first learns "reasonable" behavioral assumptions from data, and then synthesizes an AV safety concept using these Figure 1: Evaluating the safety of an autonomous vehicle (AV) learned behavioral assumptions. We borrow techniques from depends on what constitutes as reasonable foreseeable behaviors of control theory, namely high order control barrier functions other road users. For example, determining whether the autonomous and Hamilton-Jacobi reachability, to provide inductive bias car (blue) is currently in a safe state depends on how the human to aid interpretability, verifiability, and tractability of our driver (red) may behave (e.g., speed up or swerve away).