Safe-visor architecture for sandboxing (AI-based) unverified controllers in stochastic cyber-physical systems

DOI10.1016/j.nahs.2021.101110OpenAlexW3128899300MaRDI QIDQ2074755

Majid Zamani, Abolfazl Lavaei, Bingzhuo Zhong, Hongpeng Cao, Marco Caccamo

Publication date: 10 February 2022

Published in: Nonlinear Analysis. Hybrid Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2102.05490

zbMATH Keywords

approximate probabilistic relationsAI-based unverified controllerssafe-visor architecturestochastic cyber-physical systems

Mathematics Subject Classification ID

Computer science (68-XX) Systems theory; control (93-XX)

Cites Work

• Unnamed Item
• Model order reduction for linear and nonlinear systems: a system-theoretic perspective
• Hierarchical control system design using approximate simulation
• Stochastic optimal control. The discrete time case
• Compositional abstraction-based synthesis of general MDPs via approximate probabilistic relations
• Sandboxing controllers for stochastic cyber-physical systems
• Compositional construction of infinite abstractions for networks of stochastic control systems
• Quantitative automata-based controller synthesis for non-autonomous stochastic hybrid systems
• Game-Theoretic Methods for Robustness, Security, and Resilience of Cyberphysical Control Systems: Games-in-Games Principle for Optimal Cross-Layer Resilient Control Systems
• Shield Synthesis:
• A General Safety Framework for Learning-Based Control in Uncertain Robotic Systems
• Verification of General Markov Decision Processes by Approximate Similarity Relations and Policy Refinement

This page was built for publication: Safe-visor architecture for sandboxing (AI-based) unverified controllers in stochastic cyber-physical systems