Our paper on distributionally robust safety filtering under arbitrary uncertainties has been accepted to IEEE Robotics and Automation Letters (RA-L)! We extend backup-based safety filtering to handle uncertainty with unknown distributions, while keeping online safety certification computationally efficient through a simple search over the switching time. The approach provides finite-sample probabilistic safety guarantees and works across a range of systems, from a Dubins vehicle to a high-speed racing car and a fighter jet.
Distributionally Robust Safety Under Arbitrary Uncertainties: A Safety Filtering Approach
Authors: Daniel M. Cherenson*, Haejoon Lee*, Taekyung Kim, Dimitra Panagou
Web Demo: https://backupsf.taekyung.me/drs
Abstract: We study how to ensure probabilistic safety for nonlinear systems under distributional ambiguity. Our approach builds on a backup-based safety filtering framework that switches between a high-performance nominal policy and a certified backup policy to ensure safety. To handle arbitrary uncertainties from ambiguous distributions, i.e., where the distribution is not of specific structure and the true distribution is unknown, we adopt a distributionally robust (DR) formulation using Wasserstein ambiguity sets. Rather than solving a high-dimensional DR trajectory optimization problem online, we exploit the structure of backup-based safety filtering to reduce safety certification to a one-dimensional search over the switching time between nominal and backup policies. We then develop a sampling-based certification procedure with finite-sample guarantees, where empirical failure probabilities are compared against a Wasserstein-inflated threshold. We validate our method across three systems, from a Dubins vehicle to a high-speed racing car and a fighter jet, demonstrating the broad applicability and computational efficiency.
