World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model Article Swipe

MAKE IMPACT

Zebin Xing , Qichao Zhang , Yuhang Zheng , Yinfeng Gao , Zhongpu Xia , Peng Jia · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2507.00603

End-to-end autonomous driving directly generates planning trajectories from raw sensor data, yet it typically relies on costly perception supervision to extract scene information. A critical research challenge arises: constructing an informative driving world model to enable perception annotation-free, end-to-end planning via self-supervised learning. In this paper, we present World4Drive, an end-to-end autonomous driving framework that employs vision foundation models to build latent world models for generating and evaluating multi-modal planning trajectories. Specifically, World4Drive first extracts scene features, including driving intention and world latent representations enriched with spatial-semantic priors provided by vision foundation models. It then generates multi-modal planning trajectories based on current scene features and driving intentions and predicts multiple intention-driven future states within the latent space. Finally, it introduces a world model selector module to evaluate and select the best trajectory. We achieve perception annotation-free, end-to-end planning through self-supervised alignment between actual future observations and predicted observations reconstructed from the latent space. World4Drive achieves state-of-the-art performance without manual perception annotations on both the open-loop nuScenes and closed-loop NavSim benchmarks, demonstrating an 18.1\% relative reduction in L2 error, 46.7% lower collision rate, and 3.75 faster training convergence. Codes will be accessed at https://github.com/ucaszyp/World4Drive.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2507.00603

PDF

https://arxiv.org/pdf/2507.00603

OA Status

green

OpenAlex ID

https://openalex.org/W4416887510

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4416887510

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2507.00603

Digital Object Identifier

Title

World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-07-01

Full publication date if available

Authors

Zebin Xing, Qichao Zhang, Yuhang Zheng, Yinfeng Gao, Zhongpu Xia, Peng Jia

List of authors in order

Landing page

https://arxiv.org/abs/2507.00603

Publisher landing page

PDF URL

https://arxiv.org/pdf/2507.00603

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2507.00603

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload