Learning safe neural network controllers with barrier certificates

DOI10.1007/978-3-030-62822-2_11zbMath1503.93022arXiv2009.09826OpenAlexW3108060258MaRDI QIDQ5918787

Taolue Chen, Heng-Jun Zhao, J. C. P. Woodcock, Zhi-Ming Liu, Xia Zeng

Publication date: 1 September 2022

Published in: Dependable Software Engineering. Theories, Tools, and Applications (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2009.09826

zbMATH Keywords

neural networkscontroller synthesissafety verificationcontinuous dynamical systemsbarrier certificates

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Nonlinear systems in control theory (93C10) Synthesis problems (93B50) Specification and verification (program logics, model checking, etc.) (68Q60)

Related Items

Verifying Neural Network Controlled Systems Using Neural Networks ⋮ Compositional synthesis of control barrier certificates for networks of stochastic systems against \(\omega\)-regular specifications ⋮ Learning safe neural network controllers with barrier certificates

Uses Software

• nncontroller