Conservative Safety Monitors of Stochastic Dynamical Systems

Abstract

Generating accurate runtime safety estimates for autonomous systems is vital to ensuring their continued proliferation. However, accurately reasoning about future system behaviors is generally too complex to do at runtime. To better reason about system safety at runtime, we propose a method for leveraging design time model checking results at runtime. Specifically, we model the system as a probabilistic automaton (PA) and compute bounded time reachability probabilities over the states of the PA at design time. At runtime, we combine distributions of state estimates with the safety probabilities from design time to produce a bounded time safety estimate. We argue that our approach produces well calibrated safety probabilities, assuming the estimated state distributions are well calibrated. We evaluate our approach using a case study of simulated water tanks.