List of Datasets

Quadruped

DiTer++

Multi-robot SLAM in multi-session environments

Legged-robot RGB, thermal, LiDAR and motion recordings across LAWN, PARK and FOREST, with surveyed prior maps and map-localized reference trajectories.

Metadata: Complete Metadata needs review

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

Download

Not reported

Code

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
Quadruped
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
12
Ground truth
Available
Calibration
Not reported
Annotations
Not reported

Sensor overview

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

Cameras

5 reported

IMUs

4 reported

GNSS

Not reported

LiDAR

3 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.
Not reported Other Leica survey-map reference · RTC360 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.
Hybrid
Reference notes
Robot scans are deskewed with modified Point-LIO and Leg-KILO and localized on an external surveyed prior map using a GLIL-based factor graph. Prior-map dynamic objects and unreliable points are manually removed. Maps for all three named sites are provided; map photometry and intensity support evaluation.

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

Each agent underwent the earlier DiTer calibration procedure to obtain inter-sensor extrinsics; distribution of parameters and raw calibration recordings is not specified.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Dynamic legged motion can impair inertial estimation, visual tracking and point-cloud deskewing.

Narrow scenes challenge LiDAR odometry and SLAM; the text and Figure 8 disagree on site attribution.

RGB and thermal monocular odometry has scale ambiguity; the metric benchmarks focus on LiDAR.

Cameras

agent-a-rgbd

Model
Intel Realsense D435i
Setup
Rgbd
Count
1
Effective cameras
2
Modality
Rgbd
Resolution
Not reported
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Agent-A table lists ground depth and front color image topics.

agent-b-rgb

Model
Intel Realsense D435i
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
Agent-B table lists front color; depth availability is not established for this configuration.

agent-a-thermal

Model
FLIR Boson ADK
Setup
Mono
Count
1
Effective cameras
1
Modality
Thermal
Resolution
Not reported
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Agent-A thermal images and camera information.

agent-b-thermal

Model
FLIR Boson ADK
Setup
Mono
Count
1
Effective cameras
1
Modality
Thermal
Resolution
Not reported
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Agent-B thermal images and camera information.

IMUs

Agent-A external IMU

Model
Microstrain 3DM-GX5-25
Count
1
Accel / gyro
Not reported

Agent-B external IMU

Model
Microstrain 3DM-GV7
Count
1
Accel / gyro
Not reported

Unitree-GO1 built-in IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

Unitree-GO2 built-in IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS

Not reported

LiDAR

Ouster OS1-32

Model or name
Ouster OS1-32
Count
1
Dimensions
Not reported
Rate
Not reported
Channels
32
Range
Not reported

Ouster OS1-64/128

Model or name
Ouster OS1-64/128
Count
1
Dimensions
Not reported
Rate
Not reported
Channels
Not reported
Range
Not reported

Unitree L1

Model or name
Unitree L1
Count
1
Dimensions
Not reported
Rate
Not reported
Channels
Not reported
Range
Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Other sensor

Name
Agent-A robot joint and contact sensors
Count
1
Notes
Unitree-GO1 built-in robot data in high_state; the physical IMU is listed separately.

Other sensor

Name
Agent-B robot joint and contact sensors
Count
1
Notes
Unitree-GO2 built-in robot data in high_state; the physical IMU is listed separately.

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
Not reported

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy