List of Datasets

UGV

S3E

Collaborative SLAM with limited overlap and inter-robot ranging

Eighteen collaborative runs use version-dependent stereo, LiDAR, IMU and UWB with partial heterogeneous references.

Metadata: Complete Metadata source documented Released 2022

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

Quick facts

Vehicle type
UGV
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
8
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

2 reported

IMUs

2 reported

GNSS

2 reported

LiDAR

1 reported

Radar

Not reported

Magnetometers

Not reported

Barometers

Not reported

UWB

1 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 + heading RTK GNSS Dual-antenna RTK Not reported Not reported Partial · Version Specific Reference Segments 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
Reference notes
Same released navigation source; outdoor tracks and building endpoints, not universal coverage.
6DoF GNSS / INS Postprocessed GNSS/INS Not reported Not reported Partial · Version Specific Reference Segments 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
Reference notes
v2 reference fuses navigation/IMU also present as inputs.
6DoF Motion capture Indoor motion capture 17 cameras Not reported Partial · Version Specific Reference Segments 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
Reference notes
Laboratory start/end reference explicitly described; do not infer full tracks from TXT pose format.

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

Per-agent calibration YAML provides intrinsic/extrinsic parameters. Complete raw calibration sessions and a universally measured synchronization bound are not established.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Eighteen collective runs involve three robots, with a missing Alpha recording in Square_2. Sensor counts describe the reported per-agent configuration, not one combined fleet-wide rigid rig.

The two platform versions differ: v1 supplies stereo imagery, while v2 supplies UWB and integrated navigation products. A generic homepage sensor overview does not establish every modality in every bag.

Outdoor RTK, v2 navigation and seventeen-camera indoor motion capture have distinct reference scopes. Endpoint measurements and TXT pose format do not prove continuous indoor reference coverage.

Merged ROS2 bags, per-agent references and calibration parameters are documented. Native inertial rates, reference accuracy and aggregate per-agent versus wall-clock distance/duration denominators remain unknown.

Cameras

Camera 1

Model
Not reported
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
1224 x 1024
Rate
10 Hz
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Per-agent v1 only; no camera in v2.

IMUs

Main per-agent IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS/INS embedded IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS

GNSS 1

Model or name
Not reported
Count
1
Rate
1 Hz
GNSS type
RTK
Position output
Available
Velocity output
Not reported
Heading output
Not reported

GNSS 2

Model or name
Not reported
Count
1
Rate
Not reported
GNSS type
GPS_IMU
Position output
Available
Velocity output
Available
Heading output
Available

LiDAR

LiDAR 1

Model or name
LiDAR 1
Count
1
Dimensions
3
Rate
10 Hz
Channels
16
Range
Not reported

Radar

Not reported

Additional sensors

UWB

Name
Inter-agent ranging
Count
1
Placement
platform
Rate
50 Hz
Role
peer
Notes
One receiver per robot; v2 only.

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
feng2024s3e

BibTeX

@ARTICLE{feng2024s3e,
    author={Feng, Dapeng and Qi, Yuhua and Zhong, Shipeng and Chen, Zhiqiang and Chen, Qiming and Chen, Hongbo and Wu, Jin and Ma, Jun},
    journal={IEEE Robotics and Automation Letters}, 
    title={S3E: A Multi-Robot Multimodal Dataset for Collaborative SLAM}, 
    year={2024},
    volume={},
    number={},
    pages={1-8},
    keywords={Multi-Robot SLAM;Data Sets for SLAM;SLAM},
    doi={10.1109/LRA.2024.3490402}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy