paper-with-me

홈 › Papers

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

2025-12-28 · Zhuonan Liu, Xinyu Zhang, Zishuo Wang, Runji Cai, Tomohito Kawabata, Qianyi Li, Xuance Peng, Tianze Yu, Zhen Xiong, Xuesu Xiao, Ling Xiao arxiv

Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (VLMs) provide a promising foundation for this task because they can integrate visual observations with language-based social knowledge. However, existing untuned VLMs still struggle to reliably understand fine-grained social norms, making task-specific fine-tuning essential. At the same time, no large-scale egocentric dataset is available this task. To address these challenges, we introduce MUSON, a multimodal dataset for short-horizon social navigation containing 10,110 egocentric samples collected across diverse indoor and outdoor social scenes. MUSON adopts a structured five-step chain-of-thought annotation framework comprising perception, prediction, reasoning, action, and explanation. It explicitly models static physical constraints and employs a standardized six-action decision space. Compared with existing social-navigation datasets, MUSON provides consistent annotations for reasoning, actions, and explanations. We evaluate ten representative small-to-medium VLMs on MUSON. Qwen3-VL-8B achieves the strongest decision-level performance, attaining the highest action accuracy of 0.7765 and Macro-F1 score of 0.7490, as well as the lowest collision rate of 0.0609. These results demonstrate that MUSON is an effective and reusable benchmark for advancing socially compliant navigation. The dataset is publicly available at https://github.com/MUSON-dataset/MUSON/releases/tag/v1.0.

📄 PDF Abstract BibTeX arXiv:2512.22867

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

SOPD-SocialNav: Selective On-Policy Distillation for Vision-Language Social Navigation

2026-07-22 · Xinyu Zhang, Zishuo Wang, Ling Xiao arxiv

Vision-language models have shown strong potential for social robot navigation by leveraging rich semantic understanding of complex environments and human behaviors. However, large scale VLMs are difficult to deploy on r…

Robot Navigation

Building Knowledge from Interactions: An LLM-Based Architecture for Adaptive Tutoring and Social Reasoning

2025-04-02 · Luca Garello, Giulia Belgiovine, Gabriele Russo, Francesco Rea 외

Integrating robotics into everyday scenarios like tutoring or physical training requires robots capable of adaptive, socially engaging, and goal-oriented interactions. While Large Language Models show promise in human-li…

Decision Making

FairCoT: Enhancing Fairness in Diffusion Models via Chain of Thought Reasoning of Multimodal Language Models

2024-06-13 · Zahraa Al Sahili, Ioannis Patras, Matthew Purver

In the domain of text-to-image generative models, biases inherent in training datasets often propagate into generated content, posing significant ethical challenges, particularly in socially sensitive contexts. We introd…

AttributeDiversityFairness

EmoTrans: A Benchmark for Understanding, Reasoning, and Predicting Emotion Transitions in Multimodal LLMs

2026-04-25 · He Hu, Tengjin Weng, Zebang Cheng, Yu Wang 외 arxiv

Recent multimodal large language models (MLLMs) have shown strong capabilities in perception, reasoning, and generation, and are increasingly used in applications such as social robots and human-computer interaction, whe…

Change Detection

MM-SCALE: Grounded Multimodal Moral Reasoning via Scalar Judgment and Listwise Alignment

2026-02-03 · Eunkyu Park, Wesley Hanwen Deng, Cheyon Jin, Matheus Kunzler Maldaner 외 arxiv

Vision-Language Models (VLMs) continue to struggle to make morally salient judgments in multimodal and socially ambiguous contexts. Prior works typically rely on binary or pairwise supervision, which often fail to captur…