Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System

Autonomous Centerline Tracking (ACT) enables an uninhabited aircraft system (UAS) to be guided down the center of the runway, using a camera-based Deep Neural Network (DNN). ACT is safety-critical. Guidelines by the European Union Aviation Safety Agency (EASA) for machine-learning based systems list...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuning He, Johann Schumann
Format: Article
Language:English
Published: The Prognostics and Health Management Society 2024-10-01
Series:International Journal of Prognostics and Health Management
Subjects:
Online Access:https://papers.phmsociety.org/index.php/ijphm/article/view/3860
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850280323100704768
author Yuning He
Johann Schumann
author_facet Yuning He
Johann Schumann
author_sort Yuning He
collection DOAJ
description Autonomous Centerline Tracking (ACT) enables an uninhabited aircraft system (UAS) to be guided down the center of the runway, using a camera-based Deep Neural Network (DNN). ACT is safety-critical. Guidelines by the European Union Aviation Safety Agency (EASA) for machine-learning based systems list numerous assurance objectives that must be met toward Verification and Validation (V&V), and certification. We extend our analysis framework SYSAI (System Analysis using Statistical AI) to support meeting assurance objectives for a system with AI/ML (Artificial Intelligence / Machine Learning) components and describe a combination with a runtime monitoring architecture that also supports advanced risk mitigation to support safety assurance of a complex AI-based aerospace system.
format Article
id doaj-art-2015353fe3e44e589f9edf636d68663c
institution OA Journals
issn 2153-2648
language English
publishDate 2024-10-01
publisher The Prognostics and Health Management Society
record_format Article
series International Journal of Prognostics and Health Management
spelling doaj-art-2015353fe3e44e589f9edf636d68663c2025-08-20T01:48:48ZengThe Prognostics and Health Management SocietyInternational Journal of Prognostics and Health Management2153-26482024-10-01153110https://doi.org/10.36001/ijphm.2024.v15i3.3860Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking SystemYuning He0Johann Schumann1NASA Ames Research CenterKBR/Wyle, NASA ARCAutonomous Centerline Tracking (ACT) enables an uninhabited aircraft system (UAS) to be guided down the center of the runway, using a camera-based Deep Neural Network (DNN). ACT is safety-critical. Guidelines by the European Union Aviation Safety Agency (EASA) for machine-learning based systems list numerous assurance objectives that must be met toward Verification and Validation (V&V), and certification. We extend our analysis framework SYSAI (System Analysis using Statistical AI) to support meeting assurance objectives for a system with AI/ML (Artificial Intelligence / Machine Learning) components and describe a combination with a runtime monitoring architecture that also supports advanced risk mitigation to support safety assurance of a complex AI-based aerospace system.https://papers.phmsociety.org/index.php/ijphm/article/view/3860complex safety-critical systemsafe aistatistical v&v framework
spellingShingle Yuning He
Johann Schumann
Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System
International Journal of Prognostics and Health Management
complex safety-critical system
safe ai
statistical v&v framework
title Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System
title_full Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System
title_fullStr Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System
title_full_unstemmed Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System
title_short Statistical Analysis and Runtime Monitoring for an AI-based Autonomous Centerline Tracking System
title_sort statistical analysis and runtime monitoring for an ai based autonomous centerline tracking system
topic complex safety-critical system
safe ai
statistical v&v framework
url https://papers.phmsociety.org/index.php/ijphm/article/view/3860
work_keys_str_mv AT yuninghe statisticalanalysisandruntimemonitoringforanaibasedautonomouscenterlinetrackingsystem
AT johannschumann statisticalanalysisandruntimemonitoringforanaibasedautonomouscenterlinetrackingsystem