Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Linhan, Yang, Zichong, Bai, Chen, Zhang, Guoxiang, Liu, Xiaotong, Zheng, Xiaoyin, Long, Xiao-Xiao, Lu, Chang-Tien, Lu, Cheng
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915761324294144
author Wang, Linhan
Yang, Zichong
Bai, Chen
Zhang, Guoxiang
Liu, Xiaotong
Zheng, Xiaoyin
Long, Xiao-Xiao
Lu, Chang-Tien
Lu, Cheng
author_facet Wang, Linhan
Yang, Zichong
Bai, Chen
Zhang, Guoxiang
Liu, Xiaotong
Zheng, Xiaoyin
Long, Xiao-Xiao
Lu, Chang-Tien
Lu, Cheng
contents End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited improvements. This limitation is compounded by the inherent ambiguity of driving: each scene typically provides only a single human trajectory, making it difficult to learn multimodal behaviors. In this work, we propose Drive-JEPA, a framework that integrates Video Joint-Embedding Predictive Architecture (V-JEPA) with multimodal trajectory distillation for end-to-end driving. First, we adapt V-JEPA for end-to-end driving, pretraining a ViT encoder on large-scale driving videos to produce predictive representations aligned with trajectory planning. Second, we introduce a proposal-centric planner that distills diverse simulator-generated trajectories alongside human trajectories, with a momentum-aware selection mechanism to promote stable and safe behavior. When evaluated on NAVSIM, the V-JEPA representation combined with a simple transformer-based decoder outperforms prior methods by 3 PDMS in the perception-free setting. The complete Drive-JEPA framework achieves 93.3 PDMS on v1 and 87.8 EPDMS on v2, setting a new state-of-the-art.
format Preprint
id arxiv_https___arxiv_org_abs_2601_22032
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
Wang, Linhan
Yang, Zichong
Bai, Chen
Zhang, Guoxiang
Liu, Xiaotong
Zheng, Xiaoyin
Long, Xiao-Xiao
Lu, Chang-Tien
Lu, Cheng
Computer Vision and Pattern Recognition
End-to-end autonomous driving increasingly leverages self-supervised video pretraining to learn transferable planning representations. However, pretraining video world models for scene understanding has so far brought only limited improvements. This limitation is compounded by the inherent ambiguity of driving: each scene typically provides only a single human trajectory, making it difficult to learn multimodal behaviors. In this work, we propose Drive-JEPA, a framework that integrates Video Joint-Embedding Predictive Architecture (V-JEPA) with multimodal trajectory distillation for end-to-end driving. First, we adapt V-JEPA for end-to-end driving, pretraining a ViT encoder on large-scale driving videos to produce predictive representations aligned with trajectory planning. Second, we introduce a proposal-centric planner that distills diverse simulator-generated trajectories alongside human trajectories, with a momentum-aware selection mechanism to promote stable and safe behavior. When evaluated on NAVSIM, the V-JEPA representation combined with a simple transformer-based decoder outperforms prior methods by 3 PDMS in the perception-free setting. The complete Drive-JEPA framework achieves 93.3 PDMS on v1 and 87.8 EPDMS on v2, setting a new state-of-the-art.
title Drive-JEPA: Video JEPA Meets Multimodal Trajectory Distillation for End-to-End Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.22032