Integrity Management of the Reachable Space With Lane Grid Maps - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Intelligent Vehicles Année : 2022

Integrity Management of the Reachable Space With Lane Grid Maps

Résumé

For an autonomous vehicle, reliable situation understanding is a key point towards safe navigation. A wrong prediction of the upcoming situation may lead to hazardous cases by providing improper information to the decision-making process. It is therefore of great importance to estimate the driving areas reachable by the other interacting road users without introducing misleading information. This paper presents how integrity of prediction information can be handled given the imperfection of objects prediction using a spatial representation of the situation at a tactical level, called lane grid map, which relies on the topological layer of a high-definition map. We demonstrate experimentally, using real data, how the spatial sampling step of the grid representation can be used to manage the integrity of the prediction information. Moreover, handling interactions during the prediction makes it possible to handle some particular situations safely. We show how some interactions can be exploited thanks to the neutralization concept. To quantify the integrity of the prediction, we propose to use two metrics, namely False Negative Rate and Neutralized Time Interval. Experiments have been carried out with three experimental vehicles to evaluate the integrity of the prediction using these metrics.
Fichier principal
Vignette du fichier
2022_Integrity_Management_of_the_Reachable_Space_with_Lane_Grid_Maps.pdf (11.72 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03952380 , version 1 (15-12-2023)

Identifiants

Citer

Corentin Sanchez, Philippe Xu, Philippe Bonnifait, Alexandre Armand. Integrity Management of the Reachable Space With Lane Grid Maps. IEEE Transactions on Intelligent Vehicles, 2022, 8 (4), pp.3178-3190. ⟨10.1109/TIV.2022.3225071⟩. ⟨hal-03952380⟩
60 Consultations
11 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More