Mag4D-SLAM Dataset: A Repeated-Traversal Multi-Modal 4D Geomagnetic Dataset for Localization and Mapping

2026-07-24

AI Summary

This work addresses the lack of large-scale outdoor multimodal datasets in geomagnetic SLAM research, which has been limited to small indoor environments, unsynchronized sensors, and absent ground truth. We present the first large-scale outdoor geomagnetic SLAM dataset, spanning over 18 kilometers and featuring synchronized LiDAR, camera, IMU, triaxial magnetometer, and GNSS measurements, along with high-precision SE(3) ground truth. Data were collected under structured trajectories with repeated traversals in both directions and across day–night cycles. This dataset enables, for the first time, analyses of geomagnetic field repeatability, drift-free global heading estimation, and cross-session place recognition, thereby demonstrating the potential of geomagnetic signals as a robust localization cue in vision- or LiDAR-degraded scenarios and establishing a critical data foundation for geomagnetic-aided SLAM.

Abstract

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.

Problem

• geomagnetic SLAM
• large-scale outdoor dataset
• multi-modal sensing
• repeated traversal
• 6-DoF ground truth

Innovation

• geomagnetic SLAM
• multi-modal dataset
• repeated traversal
• magnetic repeatability
• yaw drift mitigation