Optimizing Falsification for Learning-Based Control Systems: A Multi-Fidelity Bayesian Approach
This work addresses safety testing for learning-based control systems, offering an incremental improvement in efficiency for domain-specific applications.
The paper tackles the falsification problem in learning-based control systems by proposing a multi-fidelity Bayesian optimization framework to identify counterexamples that violate safety requirements, demonstrating improved computational efficiency over full-fidelity methods in Gym environments.
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.