List of Datasets

UGV

ROVER

Visual SLAM across seasons and lighting conditions

Thirty-nine outdoor ground-robot recordings with RGB, RGB-D, stereo and inertial streams, plus external total-station position references.

Metadata: Complete Metadata source documented Released 2025

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

Supplementary

Not reported

Quick facts

Vehicle type
UGV
Environment
Outdoor
Data origin
Real-world
Sensor count
9
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

5 reported

IMUs

3 reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Magnetometers

1 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.
3D position Total station Tracked prism · Leica TS16 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.
External
Accuracy notes
The 1 mm + 1.5 ppm figure is a total-station device specification, not a demonstrated whole-trajectory error bound.
Reference notes
Variable 2–5 Hz position measurements from a tracked prism; no orientation reference. Line-of-sight completeness is not quantified.

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

Kalibr camera/IMU and CAD prism transforms; raw sessions not established.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Campus Large Summer has no Pi Camera data; Campus Large Dusk and Garden Small Winter have no D435i IMU data. Park has no winter recording because of heavy slippage.

The approximately 7.2 km and 311 minutes are collection totals, not per-sequence values. Thirty-nine recordings span four seasons from July 2023 to September 2024.

The total station supplies position rather than full pose. Its variable rate, line-of-sight coverage and device specification do not establish a uniform trajectory accuracy bound.

Clock alignment is reported at millisecond level using GNSS-referenced NTP; this does not establish common hardware triggering for all cameras.

Separate accelerometer and gyroscope rates differ from the generated ROS combined-message cadence. Raw calibration-session availability remains unverified.

Cameras

Camera 1

Model
Joy IT Pi Camera
Setup
Mono
Count
1
Effective cameras
1
Modality
Rgb
Resolution
640 x 480
Rate
30 Hz
Shutter
Rolling
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Absent from Campus Large Summer; other camera availability differs from the D435i IMU omissions.

Camera 2

Model
Intel RealSense D435i
Setup
Rgbd
Count
1
Effective cameras
2
Modality
Rgbd
Resolution
640 x 480
Rate
30 Hz
Shutter
Other
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
RGB rolling shutter; depth global shutter. Mixed stream shutter cannot be one uniform global value.

Camera 3

Model
Intel RealSense T265
Setup
Stereo
Count
1
Effective cameras
2
Modality
Grayscale
Resolution
848 x 800
Rate
30 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

IMUs

Intel RealSense D435i integrated IMU

Model
Not reported
Count
1
Accel / gyro
100 / 200 Hz

Intel RealSense T265 integrated IMU

Model
Not reported
Count
1
Accel / gyro
65 / 200 Hz

VectorNav VN100

Model
VectorNav VN100
Count
1
Accel / gyro
65 / 65 Hz

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Additional sensors

Magnetometer

Model
VectorNav VN100
Name
VN100 magnetometer component
Count
1
Rate
65 Hz
Notes
Component of the listed VN100 package, not an additional physical device.

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
schmidt2025rover

BibTeX

@article{schmidt2025rover,
  author = {Schmidt, Fabian and Daubermann, Julian and Mitschke, Marcel and Blessing, Constantin and Meyer, Stephan and Enzweiler, Markus and Valada, Abhinav},
  title = {{ROVER}: A Multiseason Dataset for Visual {SLAM}},
  journal = {IEEE Transactions on Robotics},
  year = {2025},
  volume = {41},
  pages = {4005--4022},
  doi = {10.1109/TRO.2025.3577026}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy