BIROn - Birkbeck Institutional Research Online

Learning safe neural network controllers with barrier certificates

Zhao, H. and Zeng, X. and Chen, Taolue and Liu, Z. and Woodcock, J. (2021) Learning safe neural network controllers with barrier certificates. Formal Aspects of Computing 33 (3), pp. 437-455. ISSN 0934-5043.

[img]
Preview
Text
faoc.pdf - Published Version of Record

Download (2MB) | Preview

Abstract

We provide a new approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions, which are represented by NNs as well. We train the controller-NN and barrier-NN simultaneously, achieving a verification-in-the-loop synthesis. We provide a prototype tool nncontroller with a number of case studies. The experiment results confirm the feasibility and efficacy of our approach.

Metadata

Item Type: Article
School: Birkbeck Faculties and Schools > Faculty of Science > School of Computing and Mathematical Sciences
Depositing User: Taolue Chen
Date Deposited: 13 Jun 2022 13:37
Last Modified: 12 Apr 2025 06:12
URI: https://eprints.bbk.ac.uk/id/eprint/48301

Statistics

6 month trend
114Downloads
6 month trend
180Hits

Additional statistics are available via IRStats2.

Archive Staff Only (login required)

Edit/View Item
Edit/View Item