Formal verification of neural network controlled autonomous systems

DOI10.1145/3302504.3311802MaRDI QIDQ5239231zbMATH OpenOpenAlexWikidataFDO

Authors Xiaowu Sun, Haitham Khedr, Yasser Shoukry

Publication date 22 October 2019

Published in Proceedings of the 22nd ACM International Conference on Hybrid Systems: Computation and Control (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1810.13072

zbMATH Keywords

formal verificationmachine learningsatisfiability solvers

Mathematics Subject Classification ID

Formal languages and automata (68Q45) Specification and verification (program logics, model checking, etc.) (68Q60) Control/observation systems governed by functional relations other than differential equations (such as hybrid and switching systems) (93C30)

Recommendations

• Verifying Neural Network Controlled Systems Using Neural Networks
• Reaching out towards fully verified autonomous systems
• Generating probabilistic safety guarantees for neural network controllers
• Verisig
• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning

Cited in

(18)

• Risk verification of stochastic systems with neural network controllers
• Verification of the ROS NavFn planner using executable specification languages
• Verisig
• Learning safe neural network controllers with barrier certificates
• Reluplex: a calculus for reasoning about deep neural networks
• T4V: exploring neural network architectures that improve the scalability of neural network verification
• Improved robust neural network for Sim2Real gap in system dynamics for end-to-end autonomous driving
• Verifying Neural Network Controlled Systems Using Neural Networks
• BERN-NN: Tight Bound Propagation For Neural Networks Using Bernstein Polynomial Interval Arithmetic
• Verifying generalization in deep learning
• Verification-guided programmatic controller synthesis
• Probabilistic reach-avoid for Bayesian neural networks
• Verifying the generalization of deep learning to out-of-distribution domains
• Iteratively synthesizing \(\epsilon\)-robust barrier certificates for neural network controlled systems
• Quantitative verification of learning-enabled systems using ProbStar reachability
• ProbStar temporal logic for verifying complex behaviors of learning-enabled systems
• Minimal modifications of deep neural networks using verification
• Verisig 2.0: verification of neural network controllers using Taylor model preconditioning

This page was built for publication: Formal verification of neural network controlled autonomous systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5239231)