List of Datasets

UGV

NCLT

Long-term SLAM

Indoor and outdoor Segway-based long-term SLAM dataset with omnidirectional RGB cameras, IMU, GNSS/RTK, Hokuyo, Velodyne, and GPS/IMU/laser ground truth.

Metadata: Complete Metadata source documented Released 2016

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

Code

Not reported

Supplementary

Not reported

Quick facts

Vehicle type
UGV
Environment
Indoor, Outdoor
Data origin
Real-world
Sensor count
17
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

6 reported

IMUs

2 reported

GNSS

2 reported

LiDAR

3 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.
6DoF LiDAR SLAM Not reported Not reported 100 Hz Full 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 and notes
Accuracy notes
RTK GPS can exceed 10 m error near buildings and is often unavailable indoors; LiDAR constraints and odometry support the joint solution.
Reference notes
A joint SLAM graph fuses RTK GPS, 3D LiDAR scan matching, and odometry across all sessions. Odometry interpolation supplies poses where graph nodes are absent.

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

Sensor-to-body transforms, Ladybug3 intrinsics/extrinsics, and dense distortion/undistortion maps are provided; several additional sensor transforms were manually calibrated.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

RTK GPS is often unavailable indoors and can exceed 10 m error near buildings because of multipath; LiDAR constraints and odometry support the provided ground-truth solution.

Sessions span seasonal change but intentionally exclude adverse rain and snowfall to avoid damaging the platform.

Ladybug3 images use automatic exposure and JPEG compression.

Cameras

omni-rgb

Model
Point Grey Ladybug3
Setup
Omnidirectional
Count
6
Effective cameras
6
Modality
Rgb
Resolution
1600 x 1200
Rate
5 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

IMUs

Microstrain 3DM-GX3-45

Model
Microstrain 3DM-GX3-45
Count
1
Accel / gyro
100 / 100 Hz

Single-axis fiber-optic gyro

Model
KVH DSP-3000
Count
1
Accel / gyro
Accel not reported / gyro 100 Hz

GNSS

Garmin 18x

Model or name
Garmin 18x
Count
1
Rate
5 Hz
GNSS type
GPS
Position output
Available
Velocity output
Available
Heading output
Not reported

NovAtel DL-4 Plus

Model or name
NovAtel DL-4 Plus
Count
1
Rate
1 Hz
GNSS type
RTK
Position output
Available
Velocity output
Available
Heading output
Not reported

LiDAR

Hokuyo UTM-30LX

Model or name
Hokuyo UTM-30LX
Count
1
Dimensions
2
Rate
40 Hz
Channels
1
Range
30 m

Hokuyo URG-04LX

Model or name
Hokuyo URG-04LX
Count
1
Dimensions
2
Rate
10 Hz
Channels
1
Range
4 m

Velodyne HDL-32E

Model or name
Velodyne HDL-32E
Count
1
Dimensions
3
Rate
10 Hz
Channels
32
Range
100 m

Additional sensors

Magnetometer

Model
Microstrain 3DM-GX3-45
Name
Integrated magnetometer
Count
1
Rate
100 Hz

Odometry

Name
Segway 6DoF odometry
Count
1
Rate
100 Hz

Wheel encoder

Name
Segway wheel-velocity encoders
Count
2

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
Carlevaris-Bianco2016

BibTeX

@article{Carlevaris-Bianco2016,
  title = {University of {{Michigan North Campus}} Long-Term Vision and Lidar Dataset},
  author = {{Carlevaris-Bianco}, Nicholas and Ushani, Arash K and Eustice, Ryan M},
  year = {2016},
  month = aug,
  journal = {The International Journal of Robotics Research},
  volume = {35},
  number = {9},
  pages = {1023--1035},
  issn = {0278-3649, 1741-3176},
  doi = {10.1177/0278364915614638},
  urldate = {2023-10-04},
  langid = {english}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy