Presentation
Neural Barrier Certificates Synthesis of NN-Controlled Continuous Systems via Counterexample-Guided Learning
SessionLearn and Fuzz!
DescriptionThere is a pressing need to ensure the safety of closed-loop systems with NN controllers. To address this issue, we propose a novel approach for generating barrier certificates, which combines counterexample-guided learning with efficient SOS-based verification. Our proposed method offers an efficient verification procedure that solves three linear matrix inequality (LMI) constraint feasibility testing problems, instead of relying on an SMT solver to verify the barrier certificate conditions. We conduct comparison experiments on a set of benchmarks, demonstrating the advantages of our method in terms of efficiency and scalability, which enable effective verification of high-dimensional systems.
Event Type
Research Manuscript
TimeTuesday, June 251:45pm - 2:00pm PDT
Location3008, 3rd Floor
EDA
Design Verification and Validation