UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Lu, Hao, Liu, Ziyang, Jiang, Guangfeng, Luo, Yuanfei, Chen, Sheng, Zhang, Yangang, Chen, Ying-Cong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915666625298432
author Lu, Hao
Liu, Ziyang
Jiang, Guangfeng
Luo, Yuanfei
Chen, Sheng
Zhang, Yangang
Chen, Ying-Cong
author_facet Lu, Hao
Liu, Ziyang
Jiang, Guangfeng
Luo, Yuanfei
Chen, Sheng
Zhang, Yangang
Chen, Ying-Cong
contents Autonomous driving (AD) systems struggle in long-tail scenarios due to limited world knowledge and weak visual dynamic modeling. Existing vision-language-action (VLA)-based methods cannot leverage unlabeled videos for visual causal learning, while world model-based methods lack reasoning capabilities from large language models. In this paper, we construct multiple specialized datasets providing reasoning and planning annotations for complex scenarios. Then, a unified Understanding-Generation-Planning framework, named UniUGP, is proposed to synergize scene reasoning, future video generation, and trajectory planning through a hybrid expert architecture. By integrating pre-trained VLMs and video generation models, UniUGP leverages visual dynamics and semantic reasoning to enhance planning performance. Taking multi-frame observations and language instructions as input, it produces interpretable chain-of-thought reasoning, physically consistent trajectories, and coherent future videos. We introduce a four-stage training strategy that progressively builds these capabilities across multiple existing AD datasets, along with the proposed specialized datasets. Experiments demonstrate state-of-the-art performance in perception, reasoning, and decision-making, with superior generalization to challenging long-tail situations.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09864
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving
Lu, Hao
Liu, Ziyang
Jiang, Guangfeng
Luo, Yuanfei
Chen, Sheng
Zhang, Yangang
Chen, Ying-Cong
Computer Vision and Pattern Recognition
Autonomous driving (AD) systems struggle in long-tail scenarios due to limited world knowledge and weak visual dynamic modeling. Existing vision-language-action (VLA)-based methods cannot leverage unlabeled videos for visual causal learning, while world model-based methods lack reasoning capabilities from large language models. In this paper, we construct multiple specialized datasets providing reasoning and planning annotations for complex scenarios. Then, a unified Understanding-Generation-Planning framework, named UniUGP, is proposed to synergize scene reasoning, future video generation, and trajectory planning through a hybrid expert architecture. By integrating pre-trained VLMs and video generation models, UniUGP leverages visual dynamics and semantic reasoning to enhance planning performance. Taking multi-frame observations and language instructions as input, it produces interpretable chain-of-thought reasoning, physically consistent trajectories, and coherent future videos. We introduce a four-stage training strategy that progressively builds these capabilities across multiple existing AD datasets, along with the proposed specialized datasets. Experiments demonstrate state-of-the-art performance in perception, reasoning, and decision-making, with superior generalization to challenging long-tail situations.
title UniUGP: Unifying Understanding, Generation, and Planing For End-to-end Autonomous Driving
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.09864