Attala, Ziggy orcid.org/0000-0002-4641-5354, Cavalcanti, Ana Lucia Caneca orcid.org/0000-0002-0831-1976, Foster, Simon David orcid.org/0000-0002-9889-9514 et al. (2 more authors) (2025) Process-Algebraic Semantics for Verifying Intelligent Robotic Control Software. In: NASA Formal Methods:17th International Symposium, NFM 2025, Williamsburg, VA, USA, June 11–13, 2025, Proceedings. The 17th NASA Formal Methods Symposium (NFM 2025), 11-13 Jun 2025 Lecture Notes in Computer Science. Springer Cham, USA.
Abstract
Verification of robotic systems that use neural networks is a challenge. We focus on how we can verify robotic software modules where one or more of the controllers are implemented by a neural network. We present a formal technique supported by tools to model and verify control software involving neural networks. Our technique enables reasoning about the reactive, communication-based, properties of a system through a process-algebraic lens. We support our framework with a link to state-of-the-art ANN verification techniques, using them to prove contextual properties of a neural network. Our approach is flexible, platform-independent, and focuses on the logic of neural network models, instead of on a training method or specific use case.
Metadata
Item Type: | Proceedings Paper |
---|---|
Authors/Creators: |
|
Keywords: | verification,Circus,theorem proving,Isabelle,Marabou |
Dates: |
|
Institution: | The University of York |
Academic Units: | The University of York > Faculty of Sciences (York) > Computer Science (York) |
Date Deposited: | 08 Oct 2025 12:00 |
Last Modified: | 08 Oct 2025 14:40 |
Published Version: | https://doi.org/10.1007/978-3-031-93706-4 |
Status: | Published online |
Publisher: | Springer Cham |
Series Name: | Lecture Notes in Computer Science |
Identification Number: | 10.1007/978-3-031-93706-4 |
Related URLs: | |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:232695 |