A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems
Lists
Only you see this
Abstract
Signal Temporal Logic (STL) has become a popular tool for expressing formal requirements of Cyber-Physical Systems (CPS). The problem of verifying STL properties of neural network-controlled CPS remains a largely unexplored problem. In this paper, we present a model for the verification of Neural Network (NN) controllers for general STL specifications using a custom neural architecture where we map an STL formula into a feed-forward neural network with ReLU activation. In the case where both our plant model and the controller are ReLU-activated neural networks, we reduce the STL verification problem to reachability in ReLU neural networks. We also propose a new approach for neural network controllers with general activation functions; this approach is a sound and complete verification approach based on computing the Lipschitz constant of the closed-loop control system. We demonstrate the practical efficacy of our techniques on a number of examples of learning-enabled control systems.
BibTeX
@inproceedings{hashemi2023neurosymbolic,
author = {Navid Hashemi and Bardh Hoxha and Tomoya Yamaguchi and Danil V. Prokhorov and Georgios Fainekos and Jyotirmoy Deshmukh},
title = {{A Neurosymbolic Approach to the Verification of Temporal Logic Properties of Learning enabled Control Systems}},
booktitle = {ICCPS},
year = {2023},
url = {https://openreview.net/forum?id=vHsg05im2xg},
}Loading related content...