List of Datasets

UGV

PRED18

Event/frame vision for predator-prey robot target localization

DAVIS event and intensity recordings from robot chasing in a laboratory arena, with manually labelled prey image location and size.

Metadata: Complete Metadata needs review

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

Download

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
UGV
Environment
Indoor
Data origin
Real-world
Sensor count
1
Ground truth
Available
Calibration
Not reported
Annotations
Available

Sensor overview

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

Cameras

1 reported

IMUs

Not reported

GNSS

Not reported

LiDAR

Not 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.
2D Manual annotation jAER TargetLabeler 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
Manual labels become ambiguous at quantized position boundaries; no direct metric distance ground truth is supplied for the distance evaluation.
Reference notes
Prey image position and bounding-box size were manually labelled in jAER. These are image-space object labels, not a platform trajectory or Vicon pose reference.

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

Not reported

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Manual position and size quantization causes ambiguity near category boundaries.

Approximately half the examples are non-visible prey; small distant prey is difficult to classify.

Walking people can dominate event histograms even when the robots remain still.

Cameras

davis

Model
DAVIS
Setup
Mono
Count
1
Effective cameras
1
Modality
Event
Resolution
240 x 180
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
81 deg
VFOV
Not reported
Notes
One DAVIS provides DVS events and auxiliary APS frames. APS recording is stated as 15 fps, while results report approximately 17 Hz mean (Figure 15: 16.76 Hz). Original APS dimensions are 240x180. CNN inputs use 36x36, 54x54 or 72x72 images and 5000-event histograms, including raw and background-filtered variants. Histogram production spans 0.02–1580 Hz; the 500 Hz cap is runtime processing throughput, not event sampling.

IMUs

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
Available
Format
Not reported
Class count
Not reported
Semantic segmentation Not reported
Instance segmentation Not reported
Object detection Available
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