MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Zhuonan, Zhang, Xinyu, Wang, Zishuo, Kawabata, Tomohito, Xiao, Xuesu, Xiao, Ling
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908735235948544
author Liu, Zhuonan
Zhang, Xinyu
Wang, Zishuo
Kawabata, Tomohito
Xiao, Xuesu
Xiao, Ling
author_facet Liu, Zhuonan
Zhang, Xinyu
Wang, Zishuo
Kawabata, Tomohito
Xiao, Xuesu
Xiao, Ling
contents Socially compliant navigation requires structured reasoning over dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. However, existing social navigation datasets often lack explicit reasoning supervision and exhibit highly long-tailed action distributions, limiting models' ability to learn safety-critical behaviors. To address these issues, we introduce MUSON, a multimodal dataset for short-horizon social navigation collected across diverse indoor and outdoor campus scenes. MUSON adopts a structured five-step Chain-of-Thought annotation consisting of perception, prediction, reasoning, action, and explanation, with explicit modeling of static physical constraints and a rationally balanced discrete action space. Compared to SNEI, MUSON provides consistent reasoning, action, and explanation. Benchmarking multiple state-of-the-art Small Vision Language Models on MUSON shows that Qwen2.5-VL-3B achieves the highest decision accuracy of 0.8625, demonstrating that MUSON serves as an effective and reusable benchmark for socially compliant navigation. The dataset is publicly available at https://huggingface.co/datasets/MARSLab/MUSON
format Preprint
id arxiv_https___arxiv_org_abs_2512_22867
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments
Liu, Zhuonan
Zhang, Xinyu
Wang, Zishuo
Kawabata, Tomohito
Xiao, Xuesu
Xiao, Ling
Computer Vision and Pattern Recognition
Robotics
Socially compliant navigation requires structured reasoning over dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. However, existing social navigation datasets often lack explicit reasoning supervision and exhibit highly long-tailed action distributions, limiting models' ability to learn safety-critical behaviors. To address these issues, we introduce MUSON, a multimodal dataset for short-horizon social navigation collected across diverse indoor and outdoor campus scenes. MUSON adopts a structured five-step Chain-of-Thought annotation consisting of perception, prediction, reasoning, action, and explanation, with explicit modeling of static physical constraints and a rationally balanced discrete action space. Compared to SNEI, MUSON provides consistent reasoning, action, and explanation. Benchmarking multiple state-of-the-art Small Vision Language Models on MUSON shows that Qwen2.5-VL-3B achieves the highest decision accuracy of 0.8625, demonstrating that MUSON serves as an effective and reusable benchmark for socially compliant navigation. The dataset is publicly available at https://huggingface.co/datasets/MARSLab/MUSON
title MUSON: A Reasoning-oriented Multimodal Dataset for Socially Compliant Navigation in Urban Environments
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2512.22867