Enregistré dans:
Détails bibliographiques
Auteurs principaux: Gulzar, Mahir, Muhammad, Yar, Muhammad, Naveed
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2504.11150
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908439341432832
author Gulzar, Mahir
Muhammad, Yar
Muhammad, Naveed
author_facet Gulzar, Mahir
Muhammad, Yar
Muhammad, Naveed
contents Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic participants). This paper presents a lane graph-based motion prediction model that first predicts graph-based goal proposals and later fuses them with cross attention over multiple contextual elements. We follow the famous encoder-interactor-decoder architecture where the encoder encodes scene context using lightweight Gated Recurrent Units, the interactor applies cross-context attention over encoded scene features and graph goal proposals, and the decoder regresses multimodal trajectories via Laplacian Mixture Density Network from the aggregated encodings. Using cross-attention over graph-based goal proposals gives robust trajectory estimates since the model learns to attend to future goal-relevant scene elements for the intended agent. We evaluate our work on nuScenes motion prediction dataset, achieving state-of-the-art results.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11150
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GC-GAT: Multimodal Vehicular Trajectory Prediction using Graph Goal Conditioning and Cross-context Attention
Gulzar, Mahir
Muhammad, Yar
Muhammad, Naveed
Computer Vision and Pattern Recognition
Machine Learning
Predicting future trajectories of surrounding vehicles heavily relies on what contextual information is given to a motion prediction model. The context itself can be static (lanes, regulatory elements, etc) or dynamic (traffic participants). This paper presents a lane graph-based motion prediction model that first predicts graph-based goal proposals and later fuses them with cross attention over multiple contextual elements. We follow the famous encoder-interactor-decoder architecture where the encoder encodes scene context using lightweight Gated Recurrent Units, the interactor applies cross-context attention over encoded scene features and graph goal proposals, and the decoder regresses multimodal trajectories via Laplacian Mixture Density Network from the aggregated encodings. Using cross-attention over graph-based goal proposals gives robust trajectory estimates since the model learns to attend to future goal-relevant scene elements for the intended agent. We evaluate our work on nuScenes motion prediction dataset, achieving state-of-the-art results.
title GC-GAT: Multimodal Vehicular Trajectory Prediction using Graph Goal Conditioning and Cross-context Attention
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2504.11150