发表机构
Department of Robotics and Mechatronics Engineering, DGIST（大邱庆北科学技术院机器人与机电工程系）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出Mag4D-SLAM这一首个大规模室外地磁SLAM数据集，含多传感器同步测量与地面真值姿态。通过重复遍历实验分析磁场重复性等特性，支持偏航漂移缓解等研究，还能开启地磁传感补充其他模态及应对特殊情况的新研究。
AI 中文摘要
地磁传感提供了一种无需基础设施的绝对方向参考，对GNSS信号丢失和视觉退化具有鲁棒性，但尚无大规模室外机器人数据集支持其在SLAM中的系统研究。现有磁数据集局限于小规模室内环境，缺乏地磁SLAM研究所需的同步多模态传感、重复遍历结构和高精度6自由度地面真值。我们提出了Mag4D-SLAM，首个大规模室外地磁SLAM数据集。它包含14个序列，总长度超过18公里，有同步的激光雷达、相机、IMU、三轴磁力计和GNSS测量以及SE( )地面真值姿态，在成对的昼夜条件下沿结构化校园轨迹正反方向采集。通过重复遍历实验，分析了三个核心特性：不同记录时段（白天和夜间）的磁场重复性、无漂移全局航向估计以及用于跨时段地点识别的位置判别磁特征。Mag4D-SLAM旨在支持偏航漂移缓解、磁环闭合以及长期定位研究，并开启关于地磁传感如何补充视觉和激光雷达模态或在光照变化、结构重复和GNSS信号丢失的长期运行下提供备用线索的新研究问题。
英文摘要
Geomagnetic sensing offers an infrastructure-free, absolute orientation reference that is robust to GNSS denial and visual degradation, yet no large-scale outdoor robotics dataset supports its systematic study in SLAM. Existing magnetic datasets are confined to small-scale indoor environments and lack the synchronized multi-modal sensing, repeated-traversal structure, and high-precision 6-DoF ground truth required for geomagnetic SLAM research. We present Mag4D-SLAM, the first large-scale outdoor geomagnetic SLAM dataset. It comprises 14 sequences totaling over 18 km of synchronized LiDAR, camera, IMU, tri-axis magnetometer, and GNSS measurements with SE(3) ground-truth poses, collected along structured campus trajectories under paired day/night conditions in both forward and reverse directions. Through repeated-traversal experiments, we analyze three core properties: magnetic field repeatability across different recording sessions (daytime and nighttime), drift-free global heading estimation, and location-discriminative magnetic signatures for cross-session place recognition. Mag4D-SLAM is designed to support research on yaw drift mitigation, magnetic loop closure, and long-term localization and to open new research questions on how geomagnetic sensing can complement visual and LiDAR modalities or provide a fallback cue under illumination changes, structural repetition, and GNSS-denied long-term operation.
CommentsAccepted to IROS 2026. 8 pages, 8 figures. *Bibhutibhusan Nayak and Hyoseok Ju contributed equally to this work
