By the same authors

Learning Safe Neural Network Controllers with Barrier Certificates

Research output: Working paper

Author(s)

Department/unit(s)

Publication details

DatePublished - 18 Sep 2020
Volumeabs/2009.09826
Original languageEnglish

Publication series

NameCoRR

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.

    Research areas

  • Continuous dynamical systems, Controller synthesis, Neural networks, Safety verification, Barrier certificates

Discover related content

Find related publications, people, projects, datasets and more using interactive charts.

View graph of relations