Fixed wing

ALFA

UAV fault detection and anomaly detection

Fixed-wing fault benchmark with 47 autonomous segments, fault-onset/type labels, and supporting raw flight, telemetry and autopilot logs.

Metadata: Complete Metadata needs review Released 2020

Quick facts

Vehicle type
Fixed wing
Environment
Outdoor
Data origin
Real-world
Sensor count
4
Ground truth
Available
Calibration
Not reported
Annotations
Available

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 ALFA
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.
Other Other Not reported Not reported 5 Hz Partial · Processed Fault Scenarios 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
Fault type/onset labels derived from commanded autopilot disabling parameters, not pose ground truth or independently measured actuator response. About 5 Hz; onset may lag by 0.2 s. Only processed fault scenarios carry these labels.

Calibration and synchronization

Reported calibration level, reproducibility signals, and supporting notes.

Level
Not reported
Processed parameters
Not reported
Raw calibration data
Not reported
Calibration targets
Not reported

Calibration data

Calibration reproducibility details are not reported.

Notes

Not reported

Known or intentional limitations

Reported constraints and characteristics to check before using the dataset.

47 processed cases include ten no-fault controls; the abstract wording does not establish 47 faulty flights.

Fault-onset topics can lag the injected event by up to 0.2 seconds.

Fault truth is absent from raw telemetry/dataflash collections and does not establish independent pose truth.

Sudden recoverable faults dominate; gradual and sensor faults are outside this release.

Measured airspeed is nonzero in 13 of the 47 processed sequences; 34 have zero-filled channels. The paper reports a 20–25 Hz commanded/measured topic rate; native sampling and a consistent recorded cadence are unverified. Commanded airspeed is a controller target. Probe model, airspeed convention and released differential pressure are unreported.

Cameras

Not reported

IMUs

Pixhawk dataflash inertial units

Model
Not reported
Count
2
Accel / gyro
Not reported

GNSS

Onboard GPS

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

LiDAR

Not reported

Radar

Not reported

Pitot tube

Pitot airspeed measurements

Model or name
Pitot airspeed measurements
Count
1
Rate
Not reported
Airspeed output
Available
Differential pressure
Not reported
Notes
Measured airspeed is nonzero in 13 of the 47 processed sequences; 34 have zero-filled channels. The paper reports a 20–25 Hz commanded/measured topic rate; native sampling and a consistent recorded cadence are unverified. Commanded airspeed is a controller target. Probe model, airspeed convention and released differential pressure are unreported.

Additional sensors

Not reported

Annotations

Reported annotation availability and task support.

Availability
Available
Format
ROS fault-status topics; CSV; MAT
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
keipour2021alfa

BibTeX

@article{keipour2021alfa,
  title = {ALFA: A Dataset for UAV Fault and Anomaly Detection},
  author = {Keipour, Azarakhsh and Mousaei, Mohammadreza and Scherer, Sebastian},
  year = {2021},
  journal = {The International Journal of Robotics Research},
  volume = {40},
  number = {2-3},
  pages = {515--520},
  doi = {10.1177/0278364920966642},
}

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy