SignScene: 用于无地图导航的视觉标志接地
SignScene: Visual Sign Grounding for Mapless Navigation
AI总结：
提出SignScene，一种以标志为中心的空间语义表示方法，利用视觉语言模型将标志的语义指令与场景元素和导航动作对应，实现无地图导航，在114个查询中达到88%的接地准确率。
摘要：
导航标志使人类能够在没有地图的情况下导航陌生环境。本文研究机器人如何类似地利用标志在开放世界中进行无地图导航。一个核心挑战在于解读标志：现实世界的标志多样且复杂，其抽象语义内容需要与局部3D场景对应。我们将此形式化为标志接地问题，即将标志上的语义指令映射到相应的场景元素和导航动作。最近的视觉语言模型（VLM）具备完成此任务所需的语义常识和推理能力，但对空间信息的表示方式敏感。我们提出SignScene，一种以标志为中心的空间语义表示，捕获与导航相关的场景元素和标志信息，并以有利于有效推理的形式呈现给VLM。我们在涵盖九种不同环境类型的114个查询数据集上评估了我们的接地方法，实现了88%的接地准确率，显著优于基线。最后，我们证明该方法使Spot机器人仅使用标志即可在现实世界中进行无地图导航。
英文摘要：
Navigational signs enable humans to navigate unfamiliar environments without maps. This work studies how robots can similarly exploit signs for mapless navigation in the open world. A central challenge lies in interpreting signs: real-world signs are diverse and complex, and their abstract semantic contents need to be grounded in the local 3D scene. We formalize this as sign grounding, the problem of mapping semantic instructions on signs to corresponding scene elements and navigational actions. Recent Vision-Language Models (VLMs) offer the semantic common-sense and reasoning capabilities required for this task, but are sensitive to how spatial information is represented. We propose SignScene, a sign-centric spatial-semantic representation that captures navigation-relevant scene elements and sign information, and presents them to VLMs in a form conducive to effective reasoning. We evaluate our grounding approach on a dataset of 114 queries collected across nine diverse environment types, achieving 88% grounding accuracy and significantly outperforming baselines. Finally, we demonstrate that it enables real-world mapless navigation on a Spot robot using only signs.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
