2018 · 58 citations · 16 references
EngineeringComputer EngineeringSystems EngineeringCyber-physical SystemsRoboticsSafety EngineeringControl Of Dynamical SystemsControl System DesignControl SystemsControl TheoryController DesignSafety-critical SystemsActivation FunctionsFormal Safety VerificationNeural Network ControlReachability AnalysisSafety Property VerificationSafety VerificationSafety-critical ControlVerification Of Neural Network Controllers
In this work, the reachable set estimation and safety verification problems for a class of piecewise linear systems equipped with neural network controllers are addressed. The neural network is considered to consist of Rectified Linear Unit (ReLU) activation functions. A layer-by-layer approach is developed for the output reachable set computation of ReLU neural networks. The computation is formulated in the form of a set of manipulations for a union of polytopes. Based on the output reachable set for neural network controllers, the output reachable set for a piecewise linear feedback control system can be estimated iteratively for a given finite-time interval. With the estimated output reachable set, the safety verification for piecewise linear systems with neural network controllers can be performed by checking the existence of intersections of unsafe regions and output reach set. A numerical example is presented to illustrate the effectiveness of our approach.
16
Intriguing properties of neural networks
Christian Szegedy, Wojciech Zaremba, Ilya Sutskever et al. · arXiv (Cornell University) · 2013 · 5.7K citations · Full text
Neural networks for control systems—A survey
Kate Hunt, Daniel Sbárbaro, R. Żbikowski et al. · Automatica · 1992 · 1.9K citations