ARCH-COMP22 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants

Diego Manzanas Lopez, Matthias Althoff, Luis Benet, Xin Chen, Jiameng Fan, Marcelo Forets, Chao Huang, Taylor T. Johnson, Tobias Ladner, Wenchao Li, Christian Schilling, Qi Zhu

Research output: Contribution to journalConference articlepeer-review

18 Scopus citations

Abstract

This report presents the results of a friendly competition for formal verification of continuous and hybrid systems with artificial intelligence (AI) components. Specifically, machine learning (ML) components in cyber-physical systems (CPS), such as feedforward neural networks used as feedback controllers in closed-loop systems are considered, which is a class of systems classically known as intelligent control systems, or in more modern and specific terms, neural network control systems (NNCS). We more broadly refer to this category as AI and NNCS (AINNCS). The friendly competition took place as part of the workshop Applied Verification for Continuous and Hybrid Systems (ARCH) in 2022. In the fourth edition of this AINNCS category at ARCH-COMP, four tools have been applied to solve 10 different benchmark problems. There are two new participants: CORA and POLAR, and two previous participants: JuliaReach and NNV.

Original languageEnglish (US)
Pages (from-to)142-184
Number of pages43
JournalEPiC Series in Computing
Volume90
DOIs
StatePublished - 2022
Event9th International Workshop on Applied Verification of Continuous and Hybrid Systems, ARCH 2022 - Munich, Germany
Duration: Sep 5 2022Sep 5 2022

Funding

The material presented in this report is based upon work supported by the National Science Foundation (NSF) under grant numbers FMiTF 2220401, 2220426, 2220426, EPCN 2028001, CCF 1646497, CCF 1834324, CNS 1834701, IIS 1724341, the Defense Advanced Research Projects Agency (DARPA) Assured Autonomy program through contract number FA8750-18-C-0089, the US Air Force Research Laboratory (AFRL) under contract number FA8650-16-C-2642, the Air Force Office of Scientific Research (AFOSR) under contract number FA9550-22-1-0019, and the Office of Naval Research (ONR) grant N00014-19-1-2496. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation thereon. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of AFOSR, AFRL, DARPA, or NSF. Luis Benet acknowledges support from PAPIIT grant IG-101122. Christian Schilling acknowledges the support from DIREC -Digital Research Centre Denmark and the Villum Investigator Grant S4OS. Tobias Ladner gratefully acknowledges financial support from the project FAI funded by the German Research Foundation (DFG) under project number 286525601.

ASJC Scopus subject areas

  • General Computer Science

Fingerprint

Dive into the research topics of 'ARCH-COMP22 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants'. Together they form a unique fingerprint.

Cite this