Quadruped

M-SEVIQ

Agile quadruped perception and sensor fusion

Stereo event and RGB-D recordings with inertial and joint data from a Unitree Go2 in varied indoor/outdoor lighting, including active near-infrared illumination.

Metadata: Complete Metadata needs review

Quick facts

Vehicle type
Quadruped
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
6
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

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 M-SEVIQ
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 RTK GNSS RTK-GPS 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.
Unknown
Reference notes
Table I identifies RTK-GPS as ground-truth pose; RTK is separately logged with independent timestamps. The paper does not establish orientation, accuracy or indoor coverage.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Parameters Only
Processed parameters
Available
Raw calibration data
Not reported
Calibration targets
checkerboard

Parameters only

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

Notes

Event intrinsics use checkerboard observations; RealSense intrinsics and RGB/depth transforms use manufacturer parameters. RGB-to-robot extrinsics use CAD and event stereo extrinsics use eKalibr. Parameters are stated to be available online.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Reflections, close obstacles and repetitive indoor scenes challenge perception.

Exact released sequence count is unresolved across the source descriptions.

Cameras

stereo-events

Model
Prophesee EVK4
Setup
Stereo
Count
1
Effective cameras
2
Modality
Event
Resolution
1280 x 720
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
41.4 deg
VFOV
23.6 deg
Notes
Left and right asynchronous event buffers are recorded; active NIR conditions are part of the collection.

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
Color and rectified depth are recorded; the overview's up-to-90-fps specification does not establish delivered cadence.

IMUs

D435i-integrated IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

Unitree Go2 IMU

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Other sensor

Name
Joint encoders
Count
12
Notes
Unitree joint data are recorded with robot IMU in the low-state topic; these are limb-joint encoders.

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
cao2026mseviq

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy