Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approach

TL;DR

This paper introduces a multi-fidelity Bayesian optimization framework to efficiently identify safety violations in learning-based control systems using simulators of varying accuracy levels.

Contribution

It presents a novel multi-fidelity Bayesian approach for falsification that reduces computational costs by leveraging simulators with different fidelity levels.

Findings

More efficient than full-fidelity Bayesian optimization

Effective across various Gym environments

Reduces computational costs in safety testing

Abstract

Testing controllers in safety-critical systems is vital for ensuring their safety and preventing failures. In this paper, we address the falsification problem within learning-based closed-loop control systems through simulation. This problem involves the identification of counterexamples that violate system safety requirements and can be formulated as an optimization task based on these requirements. Using full-fidelity simulator data in this optimization problem can be computationally expensive. To improve efficiency, we propose a multi-fidelity Bayesian optimization falsification framework that harnesses simulators with varying levels of accuracy. Our proposed framework can transition between different simulators and establish meaningful relationships between them. Through multi-fidelity Bayesian optimization, we determine both the optimal system input likely to be a counterexample and the appropriate fidelity level for assessment. We evaluated our approach across various Gym environments, each featuring different levels of fidelity. Our experiments demonstrate that multi-fidelity Bayesian optimization is more computationally efficient than full-fidelity Bayesian optimization and other baseline methods in detecting counterexamples. A Python implementation of the algorithm is available at https://github.com/SAILRIT/MFBO_Falsification.