Qualification of Avionic Software based on Machine Learning : Challenges and Key Enabling Domains - IUT Blagnac
Article Dans Une Revue Journal of Aerospace Information Systems Année : 2024

Qualification of Avionic Software based on Machine Learning : Challenges and Key Enabling Domains

Résumé

Advances in machine learning (ML) open the way to innovating functions in the avionic domain, such as navigation/surveillance assistance (e.g. vision-based navigation, obstacle sensing, virtual sensing), speech-to-text applications, autonomous flight, predictive maintenance or cockpit assistance. Current standards and practices, which were defined and refined over decades with classical programming in mind, do not however support this new development paradigm. This article provides an overview of the main challenges raised by the use of ML in the demonstration of compliance with regulation requirements (i.e., software qualification), and a overview of literature relevant to these challenges, with particular focus on the issues of robustness, provability and explainability of ML results.


Fichier principal
Vignette du fichier
15845-AIAA_JAIS_Revision_1_flattened-2.pdf (3.34 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04668633 , version 1 (07-08-2024)

Identifiants

Citer

Guillaume Vidot, Christophe Gabreau, Ileana Ober, Iulian Ober. Qualification of Avionic Software based on Machine Learning : Challenges and Key Enabling Domains. Journal of Aerospace Information Systems, 2024, 21 (5), pp.367-379. ⟨10.2514/1.I011164⟩. ⟨hal-04668633⟩
18 Consultations
1 Téléchargements

Altmetric

Partager

More