Verification-guided programmatic controller synthesis

DOI10.1007/978-3-031-30820-8_16MaRDI QIDQ6536130zbMATH OpenFDO

Authors Yuning Wang, He Zhu

Publication date 5 April 2024

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/978-3-031-30820-8_16

Mathematics Subject Classification ID

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

Recommendations

• Learning safe neural network controllers with barrier certificates
• Learning safe neural network controllers with barrier certificates
• Parameterized synthesis with safety properties
• Automated formal synthesis of provably safe digital controllers for continuous plants
• A learner-verifier framework for neural network controllers and certificates of stochastic systems

Cites work

• A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
• Abstract interpretation with higher-dimensional ellipsoids and conic extrapolation
• An introduction to deep reinforcement learning
• Formal verification of neural network controlled autonomous systems
• Reachability analysis for neural feedback systems using regressive polynomial rule inference
• Verifiably Safe Off-Model Reinforcement Learning
• Verisig

Cited in

(1)

• Run-time optimization for learned controllers through quantitative games

This page was built for publication: Verification-guided programmatic controller synthesis

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6536130)