DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: jia, Feiyang, Liu, Lin, Song, Ziying, Jia, Caiyan, Ye, Hangjun, Hao, Xiaoshuai, Chen, Long
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911427596386304
author jia, Feiyang
Liu, Lin
Song, Ziying
Jia, Caiyan
Ye, Hangjun
Hao, Xiaoshuai
Chen, Long
author_facet jia, Feiyang
Liu, Lin
Song, Ziying
Jia, Caiyan
Ye, Hangjun
Hao, Xiaoshuai
Chen, Long
contents End-to-end (E2E) autonomous driving has recently attracted increasing interest in unifying Vision-Language-Action (VLA) with World Models to enhance decision-making and forward-looking imagination. However, existing methods fail to effectively unify future scene evolution and action planning within a single architecture due to inadequate sharing of latent states, limiting the impact of visual imagination on action decisions. To address this limitation, we propose DriveWorld-VLA, a novel framework that unifies world modeling and planning within a latent space by tightly integrating VLA and world models at the representation level, which enables the VLA planner to benefit directly from holistic scene-evolution modeling and reducing reliance on dense annotated supervision. Additionally, DriveWorld-VLA incorporates the latent states of the world model as core decision-making states for the VLA planner, facilitating the planner to assess how candidate actions impact future scene evolution. By conducting world modeling entirely in the latent space, DriveWorld-VLA supports controllable, action-conditioned imagination at the feature level, avoiding expensive pixel-level rollouts. Extensive open-loop and closed-loop evaluations demonstrate the effectiveness of DriveWorld-VLA, which achieves state-of-the-art performance with 91.3 PDMS on NAVSIMv1, 86.8 EPDMS on NAVSIMv2, and 0.16 3-second average collision rate on nuScenes. Code and models will be released in https://github.com/liulin815/DriveWorld-VLA.git.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06521
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
jia, Feiyang
Liu, Lin
Song, Ziying
Jia, Caiyan
Ye, Hangjun
Hao, Xiaoshuai
Chen, Long
Computer Vision and Pattern Recognition
Robotics
End-to-end (E2E) autonomous driving has recently attracted increasing interest in unifying Vision-Language-Action (VLA) with World Models to enhance decision-making and forward-looking imagination. However, existing methods fail to effectively unify future scene evolution and action planning within a single architecture due to inadequate sharing of latent states, limiting the impact of visual imagination on action decisions. To address this limitation, we propose DriveWorld-VLA, a novel framework that unifies world modeling and planning within a latent space by tightly integrating VLA and world models at the representation level, which enables the VLA planner to benefit directly from holistic scene-evolution modeling and reducing reliance on dense annotated supervision. Additionally, DriveWorld-VLA incorporates the latent states of the world model as core decision-making states for the VLA planner, facilitating the planner to assess how candidate actions impact future scene evolution. By conducting world modeling entirely in the latent space, DriveWorld-VLA supports controllable, action-conditioned imagination at the feature level, avoiding expensive pixel-level rollouts. Extensive open-loop and closed-loop evaluations demonstrate the effectiveness of DriveWorld-VLA, which achieves state-of-the-art performance with 91.3 PDMS on NAVSIMv1, 86.8 EPDMS on NAVSIMv2, and 0.16 3-second average collision rate on nuScenes. Code and models will be released in https://github.com/liulin815/DriveWorld-VLA.git.
title DriveWorld-VLA: Unified Latent-Space World Modeling with Vision-Language-Action for Autonomous Driving
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2602.06521