A Formal Characterization of Black-Box System Safety Performance with Scenario Sampling
| Autor: | Keith Redmill, Bowen Weng, Linda Capito, Umit Ozguner |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Mathematical optimization Control and Optimization Computer science Biomedical Engineering System testing Initialization System safety Systems and Control (eess.SY) Electrical Engineering and Systems Science - Systems and Control Computer Science - Robotics symbols.namesake Artificial Intelligence Black box FOS: Electrical engineering electronic engineering information engineering Mechanical Engineering Sampling (statistics) Approximation algorithm Computer Science Applications Human-Computer Interaction Control and Systems Engineering symbols Computer Vision and Pattern Recognition Scenario testing Robotics (cs.RO) Gibbs sampling |
| DOI: | 10.48550/arxiv.2110.02331 |
| Popis: | A typical scenario-based evaluation framework seeks to characterize a black-box system's safety performance (e.g., failure rate) through repeatedly sampling initialization configurations (scenario sampling) and executing a certain test policy for scenario propagation (scenario testing) with the black-box system involved as the test subject. In this letter, we first present a novel safety evaluation criterion that seeks to characterize the actual operational domain within which the test subject would remain safe indefinitely with high probability. By formulating the black-box testing scenario as a dynamic system, we show that the presented problem is equivalent to finding a certain "almost" robustly forward invariant set for the given system. Second, for an arbitrary scenario testing strategy, we propose a scenario sampling algorithm that is provably asymptotically optimal in obtaining the safe invariant set with arbitrarily high accuracy. Moreover, as one considers different testing strategies (e.g., biased sampling of safety-critical cases), we show that the proposed algorithm still converges to the unbiased approximation of the safety characterization outcome if the scenario testing satisfies a certain condition. Finally, the effectiveness of the presented scenario sampling algorithms and various theoretical properties are demonstrated in a case study of the safety evaluation of a control barrier function-based mobile robot collision avoidance system. Comment: A shorter version of this manuscript has been accepted to be published at IEEE Robotics and Automation Letters (RA-L) |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|