UGV

Ground-Challenge

Multi-sensor SLAM corner cases

36 ground-robot trajectories emphasizing visual failures, wheel slip and degenerate movement.

Metadata: Complete Metadata needs review

Quick facts

Vehicle type
UGV
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
6
Ground truth
Available
Calibration
Not reported
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 Ground-Challenge
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.
Not reported LiDAR SLAM Fast-LIO2 Not reported 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
3 cm positioning accuracy was measured in a 15 by 15 m indoor validation room against a 16-camera motion capture system; no release-wide bound. The separate outdoor claim is cited Fast-LIO2 performance.
Reference notes
Estimated pseudo-ground truth from Velodyne LiDAR and Xsens IMU; motion capture is validation apparatus, not an established released reference stream.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Not reported
Processed parameters
Not reported
Raw calibration data
Not reported
Calibration targets
Not reported

Calibration data

Calibration reproducibility details are not reported.

Notes

Camera intrinsics use MATLAB Camera Calibration Toolbox; IMU calibration includes gyro/accelerometer white noise and random walk. Extrinsics use the IMU reference frame and the cited camera–IMU toolbox. Release of raw calibration sequences is not established.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Includes deliberate camera blockage, low texture, low light and motion blur.

Wheel slip, rotation with little translation, and wheel suspension deliberately violate common odometry assumptions.

Reference is LiDAR–IMU estimated pseudo-ground truth; validation accuracy is local.

Cameras

rgbd

Model
Realsense D435I
Setup
Rgbd
Count
1
Effective cameras
2
Modality
Rgbd
Resolution
640 x 480
Rate
15 Hz
Shutter
Not Reported
Lens type
Pinhole
HFOV
69 deg
VFOV
42.5 deg
Notes
RGB/depth both 640 by 480 at 15 Hz; listed FOV is RGB. Depth table specification is 0.1–10 m. Depth is pixel aligned to RGB; hardware synchronization is stated for RGB and embedded IMU.

IMUs

Realsense D435I embedded IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

Xsens IMU

Model
Xsens Mti-300
Count
1
Accel / gyro
Not reported

GNSS

Not reported

LiDAR

Velodyne VLP-16

Model or name
Velodyne VLP-16
Count
1
Dimensions
3
Rate
10 Hz
Channels
16
Range
Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Odometry

Model
AgileX
Count
1
Rate
25 Hz
Notes
Two-dimensional wheel odometry; two driving wheels. Raw individual wheel-encoder streams are not established by the PDF.

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