ARCH-COMP24 Category Report: Artificial Intelligence and Neural Network Control System(AINNCS) for Continuous and Hybrid Systems Plants


Por: Lopez D.M., Althoff M., Benet L., Blab C., Forets M., Jia Y., Johnson T.T., Kranzl M., Ladner T., Linauer L., Neubauer P., Neubauer S.A., Schilling C., Zhang H., Zhong X.

Publicada: 1 ene 2024
Resumen:
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 2024. In the 8th edition of this AINNCS category at ARCH-COMP, five tools have been applied to solve 12 benchmarks, which are CORA, CROWN-Reach, GoTube, JuliaReach, and NNV. This is the year with the largest interest in the community, with two new, and three previous participants. Following last year’s trend, despite the additional challenges presented, the verification results have improved year-over-year. In terms of computation time, we can observe that the previous participants have improved as well, showing speed-ups of up to one order of magnitude, such as JuliaReach on the TORA benchmark with ReLU controller, and NNV on the TORA benchmark with both heterogeneous controllers. © 2024, EasyChair. All rights reserved.

Filiaciones:
Lopez D.M.:
 Vanderbilt University, Nashville, TN, United States

Althoff M.:
 Technische Universität München (TUM), Munich, Germany

Benet L.:
 Instituto de Ciencias Físicas, Universidad Nacional Autónoma de México (UNAM), Mexico

Blab C.:
 DatenVorsprung GmbH, Vienna, Austria

Forets M.:
 Universidad de la República, Montevideo, Uruguay

Jia Y.:
 University of Illinois Urbana-Champaign, Urbana, IL, United States

Johnson T.T.:
 Vanderbilt University, Nashville, TN, United States

Kranzl M.:
 DatenVorsprung GmbH, Vienna, Austria

Ladner T.:
 Technische Universität München (TUM), Munich, Germany

Linauer L.:
 DatenVorsprung GmbH, Vienna, Austria

Neubauer P.:
 DatenVorsprung GmbH, Vienna, Austria

Neubauer S.A.:
 DatenVorsprung GmbH, Vienna, Austria

Schilling C.:
 Aalborg University, Aalborg, Denmark

Zhang H.:
 University of Illinois Urbana-Champaign, Urbana, IL, United States

Zhong X.:
 University of Illinois Urbana-Champaign, Urbana, IL, United States
ISSN: 23987340
Editorial
EasyChair
Tipo de documento: Conference Paper
Volumen: 103 Número:
Páginas: 64-121
imagen All Open Access; Bronze Open Access