Download PDFOpen PDF in browser

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

43 pagesPublished: December 13, 2022

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. The goal of this report is to be a snapshot of the current landscape of tools and the types of benchmarks for which these tools are suited. The results of this iteration significantly outperform those of any previous year, demonstrating the continuous advancement of this community in the past decade.

Keyphrases: formal methods, Neural Network Control Systems, neural networks, reachability, verification

In: Goran Frehse, Matthias Althoff, Erwin Schoitsch and Jeremie Guiochet (editors). Proceedings of 9th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH22), vol 90, pages 142--184

Links:
BibTeX entry
@inproceedings{ARCH22:ARCH_COMP22_Category_Report_Artificial,
  author    = {Diego Manzanas Lopez and Matthias Althoff and Luis Benet and Xin Chen and Jiameng Fan and Marcelo Forets and Chao Huang and Taylor T Johnson and Tobias Ladner and Wenchao Li and Christian Schilling and Qi Zhu},
  title     = {ARCH-COMP22 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants},
  booktitle = {Proceedings of 9th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH22)},
  editor    = {Goran Frehse and Matthias Althoff and Erwin Schoitsch and Jeremie Guiochet},
  series    = {EPiC Series in Computing},
  volume    = {90},
  pages     = {142--184},
  year      = {2022},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/C1J8},
  doi       = {10.29007/wfgr}}
Download PDFOpen PDF in browser