List of Datasets

UGV

Trimbot Wageningen SLAM Dataset

Panoramic stereo SLAM and dense reconstruction

A garden robot dataset with five synchronized stereo pairs, projected sparse LiDAR, dense depth, semantic maps and refined camera poses.

Metadata: Complete Metadata needs review

Primary places to inspect, download, read about, or reproduce the dataset.

Download

Not reported

Code

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
UGV
Environment
Outdoor
Data origin
Real-world
Sensor count
11
Ground truth
Available
Calibration
Parameters Only
Annotations
Available

Sensor overview

High-level sensor availability before the detailed sensor records below.

Cameras

10 reported

IMUs

Not reported

GNSS

Not reported

LiDAR

1 reported

Radar

Not reported

Pitot tube

Not reported

Magnetometers

Not reported

Barometers

Not reported

UWB

Not reported

Ground truth

Reference scope, method, rate, coverage, and provenance.

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 Other Topcon PS Series Robotic Total Station and STIM300 IMU Not reported Not reported Full 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.
Hybrid
Reference notes
Total-station positions and strap-down inertial orientation form robot poses, transformed to cameras by calibration and refined using structure from motion, including occluded total-station observations. Device accuracy is not final pose accuracy.
Other Other Leica ScanStation P15 garden model Not reported Not reported Partial · Left-Camera Image Planes 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.
Hybrid
Reference notes
Fully dense depth maps are projected from scanned garden geometry using refined camera poses; they are reference products rather than a separate depth camera stream.

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

Rectified images, per-camera intrinsic parameters and distortion models are available. Kalibr used pinhole and radial-tangential models.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

RGB-colored reference point cloud is excluded because sequential color and scan acquisition creates foliage color artifacts.

Training and test observations come from the same half-day garden recording.

Cameras

panoramic-stereo

Model
Not reported
Setup
Stereo
Count
5
Effective cameras
10
Modality
Other
Resolution
752 x 480
Rate
Not reported
Shutter
Global
Lens type
Pinhole
HFOV
Not reported
VFOV
Not reported
Notes
Five stereo pairs form a panoramic ring: color left and grayscale right. Built from ten ONSemiconductors MT9V024 image sensors; this identifies sensor chips rather than a commercial camera model. Rig capture is 12 Hz, with one in ten raw frames retained in the release; 60 FPS is the individual-sensor maximum, not released cadence.

IMUs

Not reported

GNSS

Not reported

LiDAR

Velodyne Puck (VLP-16)

Model or name
Velodyne Puck (VLP-16)
Count
1
Dimensions
3
Rate
Not reported
Channels
16
Range
Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Not reported

Annotations

Reported annotation availability and task support.

Availability
Available
Format
Not reported
Class count
8
Semantic segmentation Available
Instance segmentation Not reported
Object detection Not reported
Optical flow Not reported
Depth ground truth Available

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