UGV, UAV

AirMuseum

Multi-robot stereo-visual and inertial SLAM

Five coordinated indoor scenarios recorded by three ground robots and a drone, with stereo imagery, inertial measurements and reconstruction-derived pose references.

Metadata: Complete Metadata needs review

Quick facts

Vehicle type
UGV, UAV
Environment
Indoor
Data origin
Real-world
Sensor count
12
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.

Ground-truth references for AirMuseum
Scope Method Reference system Count Rate Coverage Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
6DoF Structure from motion AprilCube marker network 5 AprilCubes Not reported Unknown Reference provenance
External
Measured using equipment independent of the platform’s normal onboard sensor pipeline.
Derived
Computed primarily from the dataset’s own recorded sensors.
Hybrid
Combines independent reference equipment with onboard measurements.
Derived
Accuracy notes
Reconstruction reprojection errors are pixel diagnostics, not metric position or angular accuracy guarantees.
Reference notes
Colmap exhaustive image matching and bundle adjustment produce reconstruction-derived trajectories; AprilCube observations constrain scale. Timestamped text gives body-frame position and quaternion in a world frame.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Parameters Only
Processed parameters
Available
Raw calibration data
Not reported
Calibration targets
AprilGrid

Parameters only

Processed calibration parameters are reported, but raw calibration data is not reported.

Notes

Kalibr spatial and temporal camera–IMU calibration, intrinsics, equidistant distortion coefficients, camera-to-IMU extrinsics and clock delay; marker IDs and camera-relative poses are supplied.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Sparse visual features and low parallax in the North area; reflective-floor illumination difficulties.

Ground robot motion may provide limited multidirectional inertial excitation and include vibration or leaps.

D435i depth imagery and its additional integrated IMU are described as planned future augmentation.

Cameras

robot_stereo

Model
IDS UL124xLE
Setup
Stereo
Count
4
Effective cameras
8
Modality
Grayscale
Resolution
640 x 512
Rate
20 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
One stereo rig per robot; drone present in scenarios 3–5. Two monochrome cameras per rig, 4 mm lenses, 26 cm baseline, auto-shutter enabled. Auto-shutter does not establish global or rolling readout. ROS bags split cam100 plus IMU from complementary cam101 images.

IMUs

Ground robot IMUs

Model
MPU-9250
Count
3
Accel / gyro
Not reported

DJI-M100 integrated IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Pitot tube

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.

Citation key
Not reported

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy