Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?
基于图像的机器人地理定位:黑盒视觉语言模型是否已经足够?
机构 * University of Southampton(南安普顿大学) ; MyWay srl ; Queensland University of Technology(昆士兰科技大学) ; University of Essex(埃塞克斯大学)
AI总结 本文首次系统研究黑盒生成式视觉语言模型作为独立零样本地理定位系统的潜力,发现其在粗粒度定位上表现良好,但在细粒度定位上因现实变化而显著退化。
Comments Accepted to the ICRA 2026 Workshop on Multi-Modal Spatial AI for Robust Navigation and Open-World Understanding (MM-SpatialAI)