Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Bukhari, Syed Ali Asadullah, Flinkow, Thomas, Inkarbekov, Medet, Pearlmutter, Barak A., Monahan, Rosemary
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917843908427776
author Bukhari, Syed Ali Asadullah
Flinkow, Thomas
Inkarbekov, Medet
Pearlmutter, Barak A.
Monahan, Rosemary
author_facet Bukhari, Syed Ali Asadullah
Flinkow, Thomas
Inkarbekov, Medet
Pearlmutter, Barak A.
Monahan, Rosemary
contents The increased reliance of self-driving vehicles on neural networks opens up the challenge of their verification. In this paper we present an experience report, describing a case study which we undertook to explore the design and training of a neural network on a custom dataset for vision-based autonomous navigation. We are particularly interested in the use of machine learning with differentiable logics to obtain networks satisfying basic safety properties by design, guaranteeing the behaviour of the neural network after training. We motivate the choice of a suitable neural network verifier for our purposes and report our observations on the use of neural network verifiers for self-driving systems.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14163
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report
Bukhari, Syed Ali Asadullah
Flinkow, Thomas
Inkarbekov, Medet
Pearlmutter, Barak A.
Monahan, Rosemary
Logic in Computer Science
Computer Vision and Pattern Recognition
Machine Learning
The increased reliance of self-driving vehicles on neural networks opens up the challenge of their verification. In this paper we present an experience report, describing a case study which we undertook to explore the design and training of a neural network on a custom dataset for vision-based autonomous navigation. We are particularly interested in the use of machine learning with differentiable logics to obtain networks satisfying basic safety properties by design, guaranteeing the behaviour of the neural network after training. We motivate the choice of a suitable neural network verifier for our purposes and report our observations on the use of neural network verifiers for self-driving systems.
title Creating a Formally Verified Neural Network for Autonomous Navigation: An Experience Report
topic Logic in Computer Science
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2411.14163