UAV, UGV, Quadruped, Handheld
SubT-MRS
SLAM robustness across sensor degradation and heterogeneous robots
Real-world multi-robot LiDAR, fisheye, thermal and inertial recordings stress SLAM under subterranean, off-road and extreme visibility conditions.
Access links
Primary places to inspect, download, read about, or reproduce the dataset.
Quick facts
- Vehicle type
- UAV, UGV, Quadruped, Handheld
- Environment
- Indoor, Outdoor
- Data origin
- Real-world
- Sensor count
- 7
- Ground truth
- Available
- Calibration
- Parameters Only
- Annotations
- Not reported
Sensor overview
High-level sensor availability before the detailed sensor records below.
Ground truth
Reference scope, method, rate, coverage, and provenance.
| Scope | Method | Reference system | Count | Rate | Coverage |
Reference provenance
|
|---|---|---|---|---|---|---|
| 6DoF | Other | Reference-map alignment with visual/LiDAR/inertial fusion · FARO Focus 3D S120 | Not reported | Not reported | Unknown |
Reference provenance
Hybrid
|
|
||||||
Calibration and synchronization
Reported calibration level, reproducibility signals, and supporting notes.
- Level
- Parameters Only
- Processed parameters
- Available
- Raw calibration data
- Not reported
- Calibration targets
- Not reported
Parameters only
Processed calibration parameters are reported, but raw calibration data is not reported.
Notes
Kalibr camera/IMU, CAD LiDAR/IMU, sunlight-heated 7×9 thermal board and static Allan variance; downloadable raw calibration inventory is not established.
Known or intentional limitations
Reported constraints and characteristics to check before using the dataset.
This entry covers real-world recordings. The separately released TartanAir simulation used by challenge tooling is not merged into its origin or totals.
Sensor packs and availability vary across aerial, legged, ground and handheld platforms. Ambiguous printed image dimension order remains unknown.
Survey maps constrain input-based visual/LiDAR/inertial reference generation. Scanner precision does not certify trajectory accuracy, and complete downloadable reference coverage remains unverified.
Calibration parameters are documented; complete raw sessions and a universal achieved timing bound remain unknown.
Cameras
Camera 1
- Model
- Leopard Imaging LI-XAVIER
- Setup
- Fisheye
- Count
- 4
- Effective cameras
- 4
- Modality
- Rgb
- Resolution
- Not reported
- Rate
- 24 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Figure prints 686×816 pixels without unambiguous width/height convention; standard pack, not every platform.
Camera 2
- Model
- FLIR Boson
- Setup
- Mono
- Count
- 1
- Effective cameras
- 1
- Modality
- Thermal
- Resolution
- Not reported
- Rate
- 60 Hz
- Shutter
- Not Reported
- Lens type
- Not Reported
- HFOV
- Not reported
- VFOV
- Not reported
- Notes
- Figure prints 512×640 pixels; scalar dimensions left unknown pending orientation confirmation.
IMUs
Epson M-G365
- Model
- Epson M-G365
- Count
- 1
- Accel / gyro
- Not reported
GNSS
Not reported
LiDAR
Velodyne VLP16
- Model or name
- Velodyne VLP16
- Count
- 1
- Dimensions
- 3
- Rate
- 10 Hz
- Channels
- Not reported
- Range
- Not reported
Radar
Not reported
Additional sensors
Not reported
Annotations
Reported annotation availability and task support.
- Availability
- Not reported
- Format
- Not reported
- Class count
- Not reported
Semantic segmentation
Not reported
Instance segmentation
Not reported
Object detection
Not reported
Optical flow
Not reported
Depth ground truth
Not reported
Citation
Citation key and BibTeX kept at the end of the page for reference.
@misc{zhao2024subtmrs,
author = {Shibo Zhao and Yuanjun Gao and Tianhao Wu and Damanpreet Singh and Rushan Jiang and Haoxiang Sun and Mansi Sarawata and Yuheng Qiu and Warren Whittaker and Ian Higgins and Yi Du and Shaoshu Su and Can Xu and John Keller and Jay Karhade and Lucas Nogueira and Sourojit Saha and Ji Zhang and Wenshan Wang and Chen Wang and Sebastian Scherer},
title = {SubT-MRS Dataset: Pushing SLAM Towards All-weather Environments},
year = {2024},
url = {https://openaccess.thecvf.com/content/CVPR2024/html/Zhao_SubT-MRS_Dataset_Pushing_SLAM_Towards_All-weather_Environments_CVPR_2024_paper.html}
}Dataset corrections
Notice a specific issue after reviewing the page?
Report an inaccuracy