Accéder directement au contenu Accéder directement à la navigation
Chapitre d'ouvrage

On the Use of Generative Adversarial Networks for Aircraft Trajectory Generation and Atypical Approach Detection

Abstract : Aircraft approach flight path safety management provides procedures that guide the aircraft to intercept the final approach axis and runway slope before landing. In order to detect atypical behavior, this paper explores the use of data generative models to learn real approach flight path probability distributions and identify flights that do not follow these distributions. Through the use of Generative Adversarial Networks (GAN), a GAN is first trained to learn real flight paths, generating new flights from learned distributions. Experiments show that the new generated flights follow realistic patterns. Unlike trajectories generated by physical models, the proposed technique, only based on past flight data, is able to account for external factors such as Air Traffic Control (ATC) orders, pilot behavior or meteorological phenomena. Next, the trained GAN is used to identify abnormal trajectories and compare the results with a clustering technique combined with a functional principal component analysis. The results show that reported non compliant trajectories are relevant.
Type de document :
Chapitre d'ouvrage
Liste complète des métadonnées

https://hal-enac.archives-ouvertes.fr/hal-03644195
Contributeur : Daniel Delahaye Connectez-vous pour contacter le contributeur
Soumis le : mardi 19 avril 2022 - 07:41:15
Dernière modification le : jeudi 21 avril 2022 - 03:29:47

Lien texte intégral

Identifiants

Collections

Citation

Gabriel Jarry, Daniel Delahaye, Nicolas Couellan. On the Use of Generative Adversarial Networks for Aircraft Trajectory Generation and Atypical Approach Detection. Springer. Air Traffic Management and Systems IV. Selected Papers of the 6th ENRI International Workshop on ATM/CNS. Lecture Notes in Electrical Engineering 731., 2021, 978-981-33-4669-7. ⟨10.1007/978-981-33-4669-7_13⟩. ⟨hal-03644195⟩

Partager

Métriques

Consultations de la notice

11