List of Datasets

Automotive

Ford Multi-AV Seasonal

Multi-vehicle seasonal localization, mapping and cooperation

Seasonally repeated multi-vehicle camera/LiDAR and navigation logs include sensor calibration, offline pose references and reflectivity/3D maps.

Metadata: Complete Metadata source documented Released 2020

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

Supplementary

Not reported

Quick facts

Vehicle type
Automotive
Environment
Outdoor
Data origin
Real-world
Sensor count
13
Ground truth
Available
Calibration
Parameters Only
Annotations
Not reported

Sensor overview

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

Cameras

7 reported

IMUs

1 reported

GNSS

1 reported

LiDAR

4 reported

Radar

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.
6DoF LiDAR SLAM Offline SLAM/full bundle adjustment Not reported Not reported 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.
Derived
Reference notes
Bundle-adjusted reference reuses onboard LiDAR/navigation observations. All logs include this pose product; the paper maximum 200 Hz pose publication cadence is not an established uniform reference sampling rate. Raw integrated GNSS and reflectivity-localized pose are separate products.

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

Provided sensor intrinsics/extrinsics and reflectivity calibration.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

Seven cameras and four LiDARs describe each vehicle. Two stereo systems contain four physical cameras; fleet size and total log count remain unverified.

The average 66 km route length is not aggregate dataset distance. Seasonal Michigan driving does not establish balanced coverage of all weather or traffic conditions.

Maximum ROS publication cadences are not native IMU/GNSS component rates or a uniform reference cadence; native rates remain unknown where not established.

Bundle-adjusted ground truth and reflectivity-localized pose reuse onboard measurements. Localization baseline errors do not establish independent reference accuracy.

Standalone encoder distribution, exact synchronization error, complete archive totals and independently measured trajectory accuracy remain unknown.

Cameras

Camera 1

Model
Point Grey Flea3 GigE
Setup
Stereo
Count
2
Effective cameras
4
Modality
Rgb
Resolution
Not reported
Rate
15 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Two stereo systems, each containing two approximately 1.3 MP cameras.

Camera 2

Model
Point Grey Flea3 GigE
Setup
Mono
Count
2
Effective cameras
2
Modality
Rgb
Resolution
Not reported
Rate
15 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Side cameras, approximately 1.3 MP each.

Camera 3

Model
Point Grey Flea3 GigE
Setup
Mono
Count
1
Effective cameras
1
Modality
Rgb
Resolution
Not reported
Rate
6 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Forward dash camera, approximately 5 MP.

IMUs

Applanix POS LV

Model
Not reported
Count
1
Accel / gyro
Not reported

GNSS

Applanix POS LV

Model or name
Applanix POS LV
Count
1
Rate
Not reported
GNSS type
DGNSS
Position output
Available
Velocity output
Not reported
Heading output
Not reported

LiDAR

Velodyne HDL-32E

Model or name
Velodyne HDL-32E
Count
4
Dimensions
3
Rate
10 Hz
Channels
32
Range
Not reported

Radar

Not reported

Additional sensors

Not reported

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
agarwal2020fordmultiavseasonal

BibTeX

@misc{agarwal2020fordmultiavseasonal,
  author = {Agarwal, Siddharth and Vora, Ankit and Pandey, Gaurav and Williams, Wayne and Kourous, Helen and McBride, James},
  title = {Ford Multi-AV Seasonal Dataset},
  year = {2020},
  eprint = {2003.07969},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2003.07969v1}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy