arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.01067cs.RO
收藏

基于AnyLoc的单目相机拓扑映射与导航

Topological Mapping and Navigation using a Monocular Camera based on AnyLoc

Graduate School of Science and Engineering, Hosei University(Hosei大学工学研究院);Future Robotics Technology Center (fuRo), Chiba Institute of Technology(Chiba技术大学未来机器人技术中心);Faculty of Science and Engineering, Hosei University(Hosei大学工学学院)

Wenzheng Zhang, Yoshitaka Hara, Sousuke Nakamura

AI总结:

基于AnyLoc的单目相机实现高效拓扑映射与导航,通过关键节点简化路径规划,提升导航成功率并降低计算成本。

摘要:

本文提出了一种基于单目相机的拓扑映射与导航方法。基于AnyLoc,关键帧被转换为描述符以构建拓扑关系,实现环检测和地图构建。与度量地图不同,拓扑地图通过关键节点而非精确坐标表示环境,从而简化路径规划和导航。视觉导航的动作通过将分割图像与目标节点关联的图像进行比较来确定。系统仅依赖单目相机,确保使用关键节点快速构建和导航地图。实验显示,在真实和仿真环境中,该方法能够有效实现环检测和导航,无需预训练。与基于ResNet的方法相比,该方法平均提高了60.2%的成功率,同时减少了时间和空间成本,为机器人和人类在各种场景中的导航提供了轻量级解决方案。

英文摘要:

This paper proposes a method for topological mapping and navigation using a monocular camera. Based on AnyLoc, keyframes are converted into descriptors to construct topological relationships, enabling loop detection and map building. Unlike metric maps, topological maps simplify path planning and navigation by representing environments with key nodes instead of precise coordinates. Actions for visual navigation are determined by comparing segmented images with the image associated with target nodes. The system relies solely on a monocular camera, ensuring fast map building and navigation using key nodes. Experiments show effective loop detection and navigation in real and simulation environments without pre-training. Compared to a ResNet-based method, this approach improves success rates by 60.2% on average while reducing time and space costs, offering a lightweight solution for robot and human navigation in various scenarios.

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。

↑