Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Weizhen, Duan, Chenda, Peng, Zhenghao, Liu, Yuxin, Zhou, Bolei
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2501.09167
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913653071020032
author Wang, Weizhen
Duan, Chenda
Peng, Zhenghao
Liu, Yuxin
Zhou, Bolei
author_facet Wang, Weizhen
Duan, Chenda
Peng, Zhenghao
Liu, Yuxin
Zhou, Bolei
contents Vision Language Models (VLMs) demonstrate significant potential as embodied AI agents for various mobility applications. However, a standardized, closed-loop benchmark for evaluating their spatial reasoning and sequential decision-making capabilities is lacking. To address this, we present MetaVQA: a comprehensive benchmark designed to assess and enhance VLMs' understanding of spatial relationships and scene dynamics through Visual Question Answering (VQA) and closed-loop simulations. MetaVQA leverages Set-of-Mark prompting and top-down view ground-truth annotations from nuScenes and Waymo datasets to automatically generate extensive question-answer pairs based on diverse real-world traffic scenarios, ensuring object-centric and context-rich instructions. Our experiments show that fine-tuning VLMs with the MetaVQA dataset significantly improves their spatial reasoning and embodied scene comprehension in safety-critical simulations, evident not only in improved VQA accuracies but also in emerging safety-aware driving maneuvers. In addition, the learning demonstrates strong transferability from simulation to real-world observation. Code and data will be publicly available at https://metadriverse.github.io/metavqa .
format Preprint
id arxiv_https___arxiv_org_abs_2501_09167
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Embodied Scene Understanding for Vision Language Models via MetaVQA
Wang, Weizhen
Duan, Chenda
Peng, Zhenghao
Liu, Yuxin
Zhou, Bolei
Computer Vision and Pattern Recognition
Robotics
Vision Language Models (VLMs) demonstrate significant potential as embodied AI agents for various mobility applications. However, a standardized, closed-loop benchmark for evaluating their spatial reasoning and sequential decision-making capabilities is lacking. To address this, we present MetaVQA: a comprehensive benchmark designed to assess and enhance VLMs' understanding of spatial relationships and scene dynamics through Visual Question Answering (VQA) and closed-loop simulations. MetaVQA leverages Set-of-Mark prompting and top-down view ground-truth annotations from nuScenes and Waymo datasets to automatically generate extensive question-answer pairs based on diverse real-world traffic scenarios, ensuring object-centric and context-rich instructions. Our experiments show that fine-tuning VLMs with the MetaVQA dataset significantly improves their spatial reasoning and embodied scene comprehension in safety-critical simulations, evident not only in improved VQA accuracies but also in emerging safety-aware driving maneuvers. In addition, the learning demonstrates strong transferability from simulation to real-world observation. Code and data will be publicly available at https://metadriverse.github.io/metavqa .
title Embodied Scene Understanding for Vision Language Models via MetaVQA
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2501.09167