This is a preprint and may not have undergone formal peer review
Zhao, Hengjun, Zeng, Xia, Chen, Taolue et al. (2 more authors) (2020) Learning Safe Neural Network Controllers with Barrier Certificates. [Preprint]
Abstract
We provide a novel 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: | Preprint |
---|---|
Authors/Creators: |
|
Keywords: | eess.SY,cs.AI,cs.LG,cs.SY |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Depositing User: | Pure (York) |
Date Deposited: | 08 Jun 2023 23:17 |
Last Modified: | 04 Dec 2024 00:25 |
Status: | Published |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:200199 |