Accéder directement au contenu Accéder directement à la navigation
Nouvelle interface
Communication dans un congrès

THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling

Abstract : In this paper, we propose THOMAS, a joint multi-agent trajectory prediction framework allowing for an efficient and consistent prediction of multi-agent multimodal trajectories. We present a unified model architecture for simultaneous agent future heatmap estimation, in which we leverage hierarchical and sparse image generation for fast and memory-efficient inference. We propose a learnable trajectory recombination model that takes as input a set of predicted trajectories for each agent and outputs its consistent reordered recombination. This recombination module is able to realign the initially independent modalities so that they do no collide and are coherent with each other. We report our results on the Interaction multi-agent prediction challenge and rank 1 st on the online test leaderboard.
Liste complète des métadonnées

https://hal-mines-paristech.archives-ouvertes.fr/hal-03683506
Contributeur : Thomas Gilles Connectez-vous pour contacter le contributeur
Soumis le : mardi 31 mai 2022 - 16:36:46
Dernière modification le : samedi 22 octobre 2022 - 05:10:42

Fichier

THOMAS_ICLR.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-03683506, version 1

Citation

Thomas Gilles, Stefano Sabatini, Dzmitry Tsishkou, Bogdan Stanciulescu, Fabien Moutarde. THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling. International Conference on Learning Representations, Apr 2022, Virtuel, France. ⟨hal-03683506⟩

Partager

Métriques

Consultations de la notice

29

Téléchargements de fichiers

24