List of Datasets

UGV

Industrial Environment Multi-Sensor Dataset

Industrial vehicle indoor tracking with Wi-Fi, inertial, and odometry data

Six indoor trolley trajectories with four Wi-Fi interfaces, dual IMUs, wheel displacement and intermittent surveyed-marker pose references.

Metadata: Complete Metadata source documented Released 2023

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

Code

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
UGV
Environment
Indoor
Data origin
Real-world
Sensor count
5
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

Not reported

IMUs

2 reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Magnetometers

2 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 + heading Surveyed markers Camera-detected ArUco tag network 22 markers Not reported Partial · Visible Tag Intervals 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
The paper calls the result high accuracy but gives no numeric reference accuracy.
Reference notes
A separate downward-looking camera detects 22 surveyed floor tags. The released references give planar vehicle position and heading during tag visibility; between-tag interpolation is a separate processing choice. The reference video is not established as a released 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
Floor-plan points and camera/tag geometry

Parameters only

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

Notes

Floor-plan calibration coordinates are released. Raw sensor-calibration sessions are not established. IMUs start without prior calibration; their NDOF mode performs online magnetometer calibration.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

The four physical Wi-Fi interfaces produce four RSS files plus an averaged RSS file; the merged output does not increase the device count.

Ground-truth timing is irregular and limited to intervals with visible floor tags. Full-trajectory reference accuracy is not quantified; interpolation between tags is not direct measurement.

The trolley is manually pushed. Its industrial-vehicle classification describes the recording platform and intended task, not an autonomous driving system.

The BNO055 IMUs begin without prior calibration, and Wi-Fi fingerprinting depends on the recorded building layout and access-point configuration.

Python parsing, analysis, plotting, fingerprinting and dead-reckoning scripts are included inside the dataset archive; a separate code repository and the collection video are not established.

Cameras

Not reported

IMUs

Low-cost orientation IMUs

Model
Adafruit BNO055
Count
2
Accel / gyro
20 / 20 Hz

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Additional sensors

Magnetometer

Model
BNO055-integrated magnetometers
Count
2
Rate
20 Hz
Notes
Magnetometer components of the same two BNO055 IMUs, not two additional sensor packages.

Wheel encoder

Model
US Digital A2
Count
1
Rate
50 Hz
Notes
Wheel-attached absolute encoder; each released sample contains incremental displacement and absolute wheel angle.

Other sensor

Model
Edimax EW7811-Un
Name
Wi-Fi RSS interfaces
Count
4
Notes
Four independently recorded RSS interfaces observe 27 access points. The fifth RSS file averages their observations and is not a fifth interface. Mean Wi-Fi scan period is 1.614 s.

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
silva2023industrial

BibTeX

@article{silva2023industrial,
  author = {Silva, Ivo and Pendão, Cristiano and Torres-Sospedra, Joaquín and Moreira, Adriano},
  title = {Industrial Environment Multi-Sensor Dataset for Vehicle Indoor Tracking with {Wi-Fi}, Inertial and Odometry Data},
  journal = {Data},
  year = {2023},
  volume = {8},
  number = {10},
  pages = {157},
  doi = {10.3390/data8100157}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy