List of Datasets

UAV

UPenn Fast Flight

VIO on fast vehicles

Quadcopter dataset for fast outdoor visual-inertial flight.

Metadata: Complete Metadata source documented Released 2018

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

Quick facts

Vehicle type
UAV
Environment
Outdoor
Data origin
Real-world
Sensor count
4
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

1 reported

GNSS

1 reported

LiDAR

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.
2D Other Not reported Not reported 5 Hz 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
Accuracy and notes
Reference notes
GPS position is aligned in time and yaw using horizontal velocity. Evaluation uses aligned x-y position error, so this is not a synchronized full-pose ground-truth system.

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

Camera intrinsics and stereo camera-to-IMU extrinsics are distributed in a Kalibr-compatible calibration file.

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

GPS is not synchronized with the stereo/IMU stream and must be aligned in time and yaw before evaluation.

The released reference is GPS position rather than an independent 6DoF ground-truth trajectory.

A laser scanner and downward-facing LiDAR appear on the flight platform, but the maintained dataset page lists only stereo images, IMU, and GPS in the released bags.

Each run follows the same approximately 300 m outbound-and-return runway path, so environmental diversity is limited.

Cameras

forward-stereo

Model
Point Grey CM3-U3-13Y3M-CS
Setup
Stereo
Count
1
Effective cameras
2
Modality
Grayscale
Resolution
960 x 800
Rate
40 Hz
Shutter
Global
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported

IMUs

VectorNav VN-100

Model
VectorNav VN-100
Count
1
Accel / gyro
200 / 200 Hz

GNSS

GPS receiver

Model or name
GPS receiver
Count
1
Rate
5 Hz
GNSS type
NOT REPORTED
Position output
Available
Velocity output
Available
Heading output
Not reported

LiDAR

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
Sun2018

BibTeX

@article{Sun2018,
  title = {Robust {{Stereo Visual Inertial Odometry}} for {{Fast Autonomous Flight}}},
  author = {Sun, Ke and Mohta, Kartik and Pfrommer, Bernd and Watterson, Michael and Liu, Sikang and Mulgaonkar, Yash and Taylor, Camillo J. and Kumar, Vijay},
  year = {2018},
  month = apr,
  journal = {IEEE Robotics and Automation Letters},
  volume = {3},
  number = {2},
  pages = {965--972},
  issn = {2377-3766, 2377-3774},
  doi = {10.1109/LRA.2018.2793349},
  urldate = {2023-10-04}
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy