All sequences are obtained within the outdoor sites on the campus.
Since each sequence takes two laps around the same path, we also hope to contribute to the study of place recognition or SLAM.
Calibration parameter
TXT format including [R|t] between each link
Provided for each agent setup
Groundtruth Map
PCD format (Intensity / Colored pointcloud)
LiDAR Groundtruth (6DoF)
CSV format [time, x, y, z, qx, qy, qz, qw]
📦 DiTer_plusplus
├──📁 Calibration
│ ├──🧾 agent_a.txt
│ └──🧾 agent_b.txt
└──📁 GT
├──📁 Global map
│ ├──🧾 Global_map_dense.pcd
│ └──🧾 Global_map_sparse.pcd
├──📁 Park
│ ├──🧾 Park_GT.pcd
│ ├──📝 Park_in_day_gt.tum
│ ├──📝 Park_out_day_pose.tum
│ ├──📝 Park_in_night_pose.tum
│ └──📝 Park_out_night_pose.tum
├──📁 Lawn
│ ├──🧾 Lawn_GT.pcd
│ ├──📝 Lawn_upper_day_gt.tum
│ ├──📝 Lawn_lower_day_gt.tum
│ ├──📝 Lawn_upper_night_gt.tum
│ └──📝 Lawn_lower_night_gt.tum
└──📁 Forest
├──🧾 Forest_GT.pcd
├──📝 Forest_old_pose.tum
└──📝 Forest_new_pose.tum
📦 DiTer_plusplus
└──📁 Bag
├──📁 Park
│ ├──📥 Park_in_day.bag
│ ├──📥 Park_out_day.bag
│ ├──📥 Park_in_night.bag
│ └──📥 Park_out_night.bag
├──📁 Lawn
│ ├──📥 Lawn_upper_day.bag
│ ├──📥 Lawn_lower_day.bag
│ ├──📥 Lawn_upper_night.bag
│ └──📥 Lawn_lower_night.bag
└──📁 Forest
├──📥 Forest_old.bag
└──📥 Forest_new.bag
PARK-DAY
PARK-NIGHT
LAWN-DAY
LAWN-NIGHT
FOREST (Multi-session : 1-year)