Work

Demo

Year: 2019

Type: conference-paper

Abstract: This abstract presents Verisig, a scalable tool for verifying safety properties of closed-loop systems with neural network (NN) controllers. Verisig transforms the NN into an equivalent hybrid system and composes this hybrid system with the plant's. This abstract describes this transformation and outlines the tool's building blocks.

Source: IEEE Workshop on Design Automation for CPS and IoT (DESTION)

DOI: 10.1145/3313151.3313164

Authors: Radoslav Ivanov, James Weimer, Oleg Sokolsky, Insup Lee

Institution: University of Pennsylvania

Language: English

Topic: Formal Methods in Verification

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: bronze

Funders: Defense Advanced Research Projects Agency, Office of Naval Research Global

Awards: G2624035430, G5057914180