Robust Inference and Verification of Temporal Logic Classifier-in-the-loop Systems

Abstract: Autonomous systems embedded with machine learning modules often rely on deep neural networks for classifying different objects of interest in the environment or different actions or strategies to take for the system. Due to the non-linearity and high-dimensionality of deep neural networks, the interpretability of the autonomous systems is compromised. Besides, the machine learning methods in autonomous systems are mostly data-intensive and lack commonsense knowledge and reasoning that are natural to humans. In this paper, we propose the framework of temporal logic classifier-in-the-loop systems. The temporal logic classifiers can output different actions to take for an autonomous system based on the environment, such that the behavior of the autonomous system can satisfy a given temporal logic specification. Our approach is robust and provably-correct, as we can prove that the behavior of the autonomous system can satisfy a given temporal logic specification in the presence of (bounded) disturbances.