M2DCD-SLAM: A Multi-Modal Campus Dataset for Robust SLAM Evaluation in Semi-Structured Outdoor Environments

M2DCD-SLAM is a multi-modal campus dataset for robust SLAM evaluation in semi-structured outdoor environments. The dataset contains seven handheld multi-modal sequences collected in representative campus outdoor scenes, including college building areas, library surroundings, academic building areas, open pedestrian routes, vegetation-rich regions, and bridge/waterfront segments. Each sequence provides a ROS bag containing RGB images from an Intel RealSense D455 camera, Livox MID-360 LiDAR measurements, and IMU measurements from the built-in IMU of the Livox MID-360. The dataset also provides raw RTK-GNSS records, RTK trajectories converted to local ENU coordinates in TUM format, calibration and configuration files, FAST-LIVO2 baseline trajectories, ATE evaluation results, and auxiliary scripts for RTK-to-TUM conversion and trajectory evaluation. The RTK-GNSS trajectories correspond to the RTK antenna position. The measured LiDAR-to-RTK lever arm is provided separately for users who require LiDAR-center compensation. The RGB image data were manually checked before public release, and no clearly identifiable personal information was observed in the released image streams.