ARCH-COMP23 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants

Diego Manzanas Lopez; Matthias Althoff; Marcelo Forets; Taylor T Johnson; Tobias Ladner; Christian Schilling

doi:10.29007/x38n

Download PDF Open PDF in browser

ARCH-COMP23 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants

37 pages•Published: October 18, 2023

Diego Manzanas Lopez, Matthias Althoff, Marcelo Forets, Taylor T. Johnson, Tobias Ladner and Christian Schilling

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 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 2023. In the fifth edition of this AINNCS category at ARCH-COMP, three tools have been applied to solve ten different benchmark problems, which are CORA, JuliaReach and NNV. In reusing the benchmarks from the last iteration, we demonstrate the continuous progress in developing these tools: Two out of three tools can verify more instances than in the 2022 iteration. A novelty of this year’s iteration is the shared computation hardware that allows for a fairer comparison among the participants.

Keyphrases: formal verification, Neural Network Control Systems, Neural Network Verification, neural networks, verification

In: Goran Frehse and Matthias Althoff (editors). Proceedings of 10th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH23), vol 96, pages 89--125

Links:	https://easychair.org/publications/paper/Vfq4b
	https://doi.org/10.29007/x38n

BibTeX entry

@inproceedings{ARCH23:ARCH_COMP23_Category_Report_Artificial,
  author    = {Diego Manzanas Lopez and Matthias Althoff and Marcelo Forets and Taylor T Johnson and Tobias Ladner and Christian Schilling},
  title     = {ARCH-COMP23 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants},
  booktitle = {Proceedings of 10th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH23)},
  editor    = {Goran Frehse and Matthias Althoff},
  series    = {EPiC Series in Computing},
  volume    = {96},
  pages     = {89--125},
  year      = {2023},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/Vfq4b},
  doi       = {10.29007/x38n}}

Download PDF Open PDF in browser