List of Datasets

UGV

i2Nav-Robot

Multi-sensor ground-robot navigation

Ten omnidirectional wheeled-robot sequences combining stereo vision, two solid-state LiDARs, radar, IMU, GNSS and wheel states with sequence-dependent fused 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
Indoor, Outdoor
Data origin
Real-world
Sensor count
10
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

2 reported

Radar

1 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.
6DoF GNSS / INS Inertial Explorer / navigation-grade IMU Not reported 200 Hz Partial · Playground00, Street00, Street01, Street02, Building02 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
Accuracy notes
Position described as centimetre-level; manufacturer roll/pitch ~0.01°, yaw ~0.02°.
Reference notes
GNSS/INS reference from navigation-grade IMU and receiver observations. Current official README assigns building02 to this method. Released fix outputs share receiver hardware; raw observations are withheld.
6DoF Other Prebuilt-map matching / navigation-grade IMU Not reported 200 Hz Partial · Building00, Building01, Parking00, Parking01, Parking02 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
RTK-controlled GoSLAM RS100i-MT survey map plus released AT128 map matching and high-grade IMU. Map uncertainty omitted from computed matching covariance.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

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

Parameters only

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

Notes

CAD translations and online estimated rotations are recommended initialization parameters; raw calibration sessions are not established.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Ten sequences cover 17.060 km and 14,204 seconds; GNSS files are absent for parking01 and parking02.

Current official documentation assigns building02 to GNSS/INS reference generation. The other building and parking references use prebuilt-map matching; both pipelines share released sensing.

Raw GNSS observations and prebuilt maps are explicitly withheld. Manufacturer accuracy values and map-matching covariance do not certify the full reference trajectory.

Official instructions warn that left/right wheel groups in ROS messages are reversed and must be exchanged. Four state groups do not establish four independently counted physical encoders.

Camera timestamps mark exposure start; exposure duration and software receive-time delays remain relevant despite PTP.

Cameras

Camera 1

Model
AVT Mako-G234
Setup
Stereo
Count
1
Effective cameras
2
Modality
Rgb
Resolution
1600 x 1200
Rate
10 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
One stereo system; timestamps are exposure-start rather than exposure-center.

IMUs

ADI ADIS16465

Model
ADI ADIS16465
Count
1
Accel / gyro
Not reported

Livox Mid360 integrated IMU

Model
TDK ICM40609
Count
1
Accel / gyro
Not reported

GNSS

Ublox F9P

Model or name
Ublox F9P
Count
1
Rate
1 Hz
GNSS type
RTK
Position output
Available
Velocity output
Not reported
Heading output
Not reported

NovAtel OEM719

Model or name
NovAtel OEM719
Count
1
Rate
1 Hz
GNSS type
RTK
Position output
Available
Velocity output
Not reported
Heading output
Not reported

LiDAR

Livox Mid360

Model or name
Livox Mid360
Count
1
Dimensions
3
Rate
10 Hz
Channels
6
Range
Not reported

Hesai AT128

Model or name
Hesai AT128
Count
1
Dimensions
3
Rate
10 Hz
Channels
128
Range
Not reported

Radar

Continental ARS548

Count
1
Released data
Point detections / point clouds
Frame rate
20 Hz
Doppler velocity
Available
Elevation angle
Available
Configured range
Not reported
Field of view
Not reported
Notes
Detection and object topics from one radar; Doppler. Hardware range 0.2–300 m.

Additional sensors

Wheel encoder

Name
Ranger Mini3 wheel speed/angle states
Count
1
Rate
50 Hz
Notes
Four wheel groups expose speed and steering angle; one CAN odometer topic. Physical encoder topology is not further specified.

Annotations

Reported annotation availability and task support.

Availability
Not reported
Format
Not reported
Class count
Not reported
Semantic segmentation Not available
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
tang2025i2navrobot

BibTeX

@misc{tang2025i2navrobot,
  author = {Hailiang Tang and Tisheng Zhang and Liqiang Wang and Xin Ding and Man Yuan and Zhiyu Xiang and Jujin Chen and Yuhan Bian and Shuangyan Liu and Yuqing Wang and Guan Wang and Xiaoji Niu},
  title = {i2Nav-Robot: A Large-Scale Indoor-Outdoor Robot Dataset for Multi-Sensor Fusion Navigation},
  year = {2025},
  url = {https://arxiv.org/abs/2508.11485v3}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy