外观
论文arXiv 2610.1832115 天前
CoSMO：面向开放世界安全机器人导航的保形语义建图
原文链接：CoSMO: Conformal Semantic Mapping for Open-World Safe Robot Navigation（arXiv 2610.18321 · 发布日期：2026-10-13）
CoSMO: Conformal Semantic Mapping for Open-World Safe Robot Navigation
CoSMO将VLM嵌入校准为覆盖集和安全膨胀，在MP3D与四足机器人上验证开放世界安全导航。
核心要点
- 安全导航需结合几何避障与语义安全距离，且相关类别会随新环境探索扩展。
- 方法用保形预测将VLM嵌入转为校准覆盖集，并构建动态危险词表的安全感知障碍膨胀。
- MP3D实验中，相比仅几何基线，CoSMO将语义碰撞减少61.6%，并保持形式覆盖保证。
- 真机四足机器人实验显示泛化能力，长期经验覆盖率为90.73%，目标为90%；项目网站已给出。
验证范围与局限：验证范围为Matterport3D (MP3D)数据集实验和四足机器人真机实验中的安全导航。
英文摘要 (Abstract)
Safe autonomous navigation requires not only geometric obstacle avoidance but also semantic awareness. Different object categories demand different safety clearances, and the set of relevant categories may expand as the robot explores novel environments. Vision-language models (VLMs) offer rich semantic representations for building maps of unknown scenes, yet their confidence scores are poorly calibrated, making raw predictions unreliable for safety-critical planning. Conformal prediction (CP) can provide coverage guarantees, but existing methods assume a fixed label set and stationary data, limiting their use in open-world settings. We propose Conformal Semantic Mapping for Open-World Safe Robot Navigation (CoSMO), a semantic safety mapping framework that transforms VLM embeddings into calibrated coverage sets and safety-aware obstacle dilations over a dynamically expanding hazard vocabulary, even under distribution shift. Experiments on the Matterport3D (MP3D) dataset show that CoSMO reduces semantic collisions by 61.6% relative to a geometry-only baseline, while maintaining formal coverage guarantees even under delayed expert feedback. Real-world experiments on a quadruped robot further demonstrate generalization by achieving long-run empirical coverage of 90.73% against the 90% target. Project website: https://yangming911.github.io/cosmo-page/.
作者：Shuqi Wang, Yiwei Zheng, Pingrui Zhang, Yue Gao, Xiang Yin
来源
本页事实对应的公开页面，以原文为准。