UGV

THÖR

Human motion prediction and human-robot navigation

Indoor human and robot trajectories with head pose, grouping, eye gaze, stationary lidar and video.

Metadata: Complete Metadata needs review Released 2019

Quick facts

Vehicle type
UGV
Environment
Indoor
Data origin
Real-world
Sensor count
3
Ground truth
Available
Calibration
Not reported
Annotations
Available

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 THÖR
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 Motion capture Qualisys · Oqus 7+ 10 cameras 100 Hz Partial · Tracked Helmets and Robot Inside Capture Volume 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.
External
Accuracy notes
Reported 1 mm spatial discretization and 2 mm average residual tracking error after reference-system calibration; neither is an absolute trajectory accuracy guarantee.
Reference notes
Global helmet poses; small podium-adjacent blind spot, manually corrected identities and recovered tracks, plus automated reconstruction from incomplete marker detections.

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.

Controlled laboratory setting and prescribed roles; robot follows a fixed socially unaware route.

Eye gaze is released for only helmet 9; mocap spatial coverage and repaired-track qualifications apply.

Public and free for non-commercial purposes; no named license is supplied in the paper.

Cameras

tobii-scene

Model
Tobii Pro Glasses
Setup
Mono
Count
1
Effective cameras
1
Modality
Not Reported
Resolution
Not reported
Rate
25 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Helmet 9 scene video with gaze overlay; gaze sampling is separately 50 Hz.

stationary-rgb

Model
Not reported
Setup
Mono
Count
1
Effective cameras
1
Modality
Rgb
Resolution
Not reported
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Stationary environment camera mounted in a room corner; NTP synchronization not explicitly stated for it.

IMUs

Not reported

GNSS

Not reported

LiDAR

Velodyne

Model or name
Velodyne
Count
1
Dimensions
3
Rate
Not reported
Channels
Not reported
Range
Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Other sensor

Model
Tobii Pro Glasses
Name
Eye tracker
Count
1
Rate
50 Hz
Notes
Gaze for helmet 9 only. Scene camera is separately represented under cameras; the other three mounted headsets are excluded.

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 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