发表机构
School of Computer Science & Technology, Beijing Institute of Technology（北京理工大学计算机科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对社会导航模拟平台不足的问题，介绍了基于3D高斯点云渲染的SONG平台，利用其进行场景和化身表示等，还策划了SONG-Bench及评估套件，通过评估发现相关问题，证明微调数据可提高现实环境成功率，为研究提供测试平台。
AI 中文摘要
社会导航已从简化的2D环境发展到更通用的基于视觉的环境，机器人需要仅通过车载视觉观察来实现符合社会规范的行为。然而，支持性模拟平台并未跟上步伐：现有选项要么缺乏视觉观察，要么缺乏移动的人类化身，要么在外观和行人行为方面缺乏真实世界的逼真度，对推进基于视觉的社会导航支持有限。我们引入了SONG，一个由3D高斯点云渲染（3DGS）驱动的社会导航平台。它利用3DGS进行场景和化身表示，使用大语言模型生成的语义基础轨迹驱动行人，并通过轨迹条件生成器合成他们的全身运动以产生连续、自然的运动。在该平台之上，我们策划了SONG-Bench，一组按难度分层的评估情节，并提出了一套涵盖有效性、安全性和社会合规性的多维度量套件。对代表性导航基线的系统评估揭示了三个发现：（a）基于视觉的社会导航远未解决；（b）关键的安全缺陷先于社交礼仪；（c）真实世界的数据比模型规模更重要。至关重要的是，我们证明在我们策划的数据上进行微调可有效提高在现实世界环境中的成功率。我们希望我们的平台为下一代基于视觉的社会导航研究提供一个忠实且严格的测试平台。
英文摘要
Social navigation has progressed from simplified 2D environments toward a more general vision-based setting, in which a robot needs to achieve socially compliant behavior purely from onboard visual observations. Yet supporting simulation platforms have not kept pace: existing options either lack visual observations, lack moving human avatars, or fall short of real-world fidelity in appearance and pedestrian behavior, offering limited support for advancing vision-based social navigation. We introduce SONG, a SOcial Navigation platform powered by 3D Gaussian splatting (3DGS). It leverages 3DGS for both scene and avatar representations, drives pedestrians using semantically grounded trajectories generated by a large language model, and synthesizes their full-body motion with a trajectory-conditioned generator to produce continuous, natural movement. On top of the platform, we curate SONG-Bench, a set of evaluation episodes stratified by difficulty, and propose a multi-dimensional metric suite covering effectiveness, safety, and social compliance. A systematic evaluation of representative navigation baselines reveals three findings: (a) vision-based social navigation is far from solved; (b) a critical safety deficit precedes social etiquette; (c) real-world data matters more than model scale. Crucially, we demonstrate that fine-tuning on our curated data effectively improves the success rate in real-world environments. We hope our platform provides a faithful and rigorous testbed for the next generation of vision-based social navigation research.
