Learning safe neural network controllers with barrier certificates
Hengjun Zhao, Xia Zeng, Taolue Chen, Zhiming Liu, Jim Woodcock
Abstract
Abstract We provide a new approach to synthesize controllers for nonlinear continuous dynamical systems with control against safety properties. The controllers are based on neural networks (NNs). To certify the safety property we utilize barrier functions, which are represented by NNs as well. We train the controller-NN and barrier-NN simultaneously, achieving a verification-in-the-loop synthesis. We provide a prototype tool nncontroller with a number of case studies. The experiment results confirm the feasibility and efficacy of our approach.
Topics & Concepts
Computer scienceArtificial neural networkTheory of computationController (irrigation)Nonlinear systemControl (management)Property (philosophy)Control engineeringArtificial intelligenceControl theory (sociology)EngineeringAlgorithmPhilosophyQuantum mechanicsAgronomyPhysicsBiologyEpistemologyAdversarial Robustness in Machine LearningModel Reduction and Neural NetworksFault Detection and Control Systems