Uncertainty estimation for Cross-dataset performance in Trajectory prediction - Mines Paris Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Uncertainty estimation for Cross-dataset performance in Trajectory prediction

Résumé

While a lot of work has been carried on developing trajectory prediction methods, and various datasets have been proposed for benchmarking this task, little study has been done so far on the generalizability and the transferability of these methods across dataset. In this paper, we observe the performance of two of the latest state-of-the-art trajectory prediction methods across four different datasets (Argoverse, NuScenes, Interaction, Shifts). This analysis allows to gain some insights on the generalizability proprieties of most recent trajectory prediction models and to analyze which dataset is more representative of real driving scenes and therefore enables better transferability. Furthermore we present a novel method to estimate prediction uncertainty and show how it could be used to achieve better performance across datasets.
Fichier principal
Vignette du fichier
Cross_dataset_CoRL_full.pdf (2.07 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03918989 , version 1 (02-01-2023)

Identifiants

  • HAL Id : hal-03918989 , version 1

Citer

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde. Uncertainty estimation for Cross-dataset performance in Trajectory prediction. ICRA 2022 Fresh Perspectives on the Future of Autonomous Driving Workshop, May 2022, Philadeplhie, United States. ⟨hal-03918989⟩
24 Consultations
49 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More