ARCH-COMP20 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants

Taylor T Johnson; Diego Manzanas Lopez; Patrick Musau; Hoang-Dung Tran; Elena Botoeva; Francesco Leofante; Amir Maleki; Chelsea Sidrane; Jiameng Fan; Chao Huang

doi:10.29007/9xgv

ARCH-COMP20 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants

33 pages•Published: September 25, 2020

Taylor T. Johnson, Diego Manzanas Lopez, Patrick Musau, Hoang-Dung Tran, Elena Botoeva, Francesco Leofante, Amir Maleki, Chelsea Sidrane, Jiameng Fan and Chao Huang

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 2020. In the second edition of this AINNCS category at ARCH-COMP, four tools have been applied to solve seven different benchmark problems, (in alphabetical order): NNV, OVERT, ReachNN*, and VenMAS. This report is a snapshot of the current landscape of tools and the types of benchmarks for which these tools are suited. Due to the diversity of problems, lack of a shared hardware platform, and the early stage of the competition, we are not ranking tools in terms of performance, yet the presented results probably provide the most complete assessment of current tools for safety verification of NNCS.

Keyphrases: Artificial Intelligence, hybrid systems, Neural Network Control Systems, neural networks, verification

In: Goran Frehse and Matthias Althoff (editors). ARCH20. 7th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH20), vol 74, pages 107--139

Links:	https://easychair.org/publications/paper/Jvwg
	https://doi.org/10.29007/9xgv

BibTeX entry

@inproceedings{ARCH20:ARCH_COMP20_Category_Report_Artificial,
  author    = {Taylor T Johnson and Diego Manzanas Lopez and Patrick Musau and Hoang-Dung Tran and Elena Botoeva and Francesco Leofante and Amir Maleki and Chelsea Sidrane and Jiameng Fan and Chao Huang},
  title     = {ARCH-COMP20 Category Report: Artificial Intelligence and Neural Network Control Systems (AINNCS) for Continuous and Hybrid Systems Plants},
  booktitle = {ARCH20. 7th International Workshop on Applied Verification of Continuous and Hybrid Systems (ARCH20)},
  editor    = {Goran Frehse and Matthias Althoff},
  series    = {EPiC Series in Computing},
  volume    = {74},
  pages     = {107--139},
  year      = {2020},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/Jvwg},
  doi       = {10.29007/9xgv}}

Download PDF Open PDF in browser