Litcius/Paper detail

NeuReach: Learning Reachability Functions from Simulations

Dawei Sun, Sayan Mitra

2022Lecture notes in computer science13 citationsDOIOpen Access PDF

Abstract

Abstract We present , a tool that uses neural networks for predicting reachable sets from executions of a dynamical system. Unlike existing reachability tools, computes a reachability function that outputs an accurate over-approximation of the reachable set for any initial set in a parameterized family. Such reachability functions are useful for online monitoring, verification, and safe planning. implements empirical risk minimization for learning reachability functions. We discuss the design rationale behind the optimization problem and establish that the computed output is probably approximately correct. Our experimental evaluations over a variety of systems show promise. can learn accurate reachability functions for complex nonlinear systems, including some that are beyond existing methods. From a learned reachability function, arbitrary reachtubes can be computed in milliseconds. is available at https://github.com/sundw2014/NeuReach .

Topics & Concepts

ReachabilityParameterized complexityComputer scienceSet (abstract data type)Function (biology)Theoretical computer scienceReachability problemVariety (cybernetics)Mathematical optimizationAlgorithmArtificial intelligenceMathematicsProgramming languageBiologyEvolutionary biologyFormal Methods in VerificationFault Detection and Control SystemsAdversarial Robustness in Machine Learning
NeuReach: Learning Reachability Functions from Simulations | Litcius