Learning safe neural network controllers with barrier certificates
From MaRDI portal
Publication:5918375
DOI10.1007/s00165-021-00544-5OpenAlexW3142708584MaRDI QIDQ5918375
J. C. P. Woodcock, Heng-Jun Zhao, Taolue Chen, Xia Zeng, Zhi-Ming Liu
Publication date: 30 August 2021
Published in: Formal Aspects of Computing (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2009.09826
neural networkscontroller synthesissafety verificationcontinuous dynamical systemsbarrier certificates
Related Items (3)
An iterative scheme of safe reinforcement learning for nonlinear systems via barrier certificate generation ⋮ Toward neural-network-guided program synthesis and verification ⋮ nncontroller
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Barrier certificates revisited
- Vector barrier certificates and comparison systems
- Automated and formal synthesis of neural barrier certificates for dynamical models
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Exponential-Condition-Based Barrier Certificate Generation for Safety Verification of Hybrid Systems
- Converse Barrier Certificate Theorems
- Compositional safety analysis using barrier certificates
- Providing a Basin of Attraction to a Target Region of Polynomial Systems by Computation of Lyapunov-Like Functions
- Converse Theorems for Safety and Barrier Certificates
- Over- and Under-Approximations of Reachable Sets With Series Representations of Evolution Functions
- Synthesizing barrier certificates using neural networks
- Case study
- Formal verification of neural network controlled autonomous systems
- Reachability analysis for neural feedback systems using regressive polynomial rule inference
- Verisig
- A Framework for Worst-Case and Stochastic Safety Verification Using Barrier Certificates
- Learning safe neural network controllers with barrier certificates
This page was built for publication: Learning safe neural network controllers with barrier certificates
