Using Formal Models, Safety Shields and Certified Control to Validate AI-Based Train Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gruteser, Jan, Roßbach, Jan, Vu, Fabian, Leuschel, Michael
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915029949874176
author Gruteser, Jan
Roßbach, Jan
Vu, Fabian
Leuschel, Michael
author_facet Gruteser, Jan
Roßbach, Jan
Vu, Fabian
Leuschel, Michael
contents The certification of autonomous systems is an important concern in science and industry. The KI-LOK project explores new methods for certifying and safely integrating AI components into autonomous trains. We pursued a two-layered approach: (1) ensuring the safety of the steering system by formal analysis using the B method, and (2) improving the reliability of the perception system with a runtime certificate checker. This work links both strategies within a demonstrator that runs simulations on the formal model, controlled by the real AI output and the real certificate checker. The demonstrator is integrated into the validation tool ProB. This enables runtime monitoring, runtime verification, and statistical validation of formal safety properties using a formal B model. Consequently, one can detect and analyse potential vulnerabilities and weaknesses of the AI and the certificate checker. We apply these techniques to a signal detection case study and present our findings.
format Preprint
id arxiv_https___arxiv_org_abs_2411_14374
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Using Formal Models, Safety Shields and Certified Control to Validate AI-Based Train Systems
Gruteser, Jan
Roßbach, Jan
Vu, Fabian
Leuschel, Michael
Logic in Computer Science
Artificial Intelligence
Computer Vision and Pattern Recognition
The certification of autonomous systems is an important concern in science and industry. The KI-LOK project explores new methods for certifying and safely integrating AI components into autonomous trains. We pursued a two-layered approach: (1) ensuring the safety of the steering system by formal analysis using the B method, and (2) improving the reliability of the perception system with a runtime certificate checker. This work links both strategies within a demonstrator that runs simulations on the formal model, controlled by the real AI output and the real certificate checker. The demonstrator is integrated into the validation tool ProB. This enables runtime monitoring, runtime verification, and statistical validation of formal safety properties using a formal B model. Consequently, one can detect and analyse potential vulnerabilities and weaknesses of the AI and the certificate checker. We apply these techniques to a signal detection case study and present our findings.
title Using Formal Models, Safety Shields and Certified Control to Validate AI-Based Train Systems
topic Logic in Computer Science
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2411.14374