Automotive

DDD20: DAVIS Driving Dataset 2020

End-to-end driving and steering prediction

51 hours of concurrent DAVIS events and grayscale frames with vehicle control and diagnostic measurements from road driving.

Metadata: Partial Metadata needs review

Quick facts

Vehicle type
Automotive
Environment
Outdoor
Data origin
Real-world
Sensor count
1
Ground truth
Available
Calibration
Not reported
Annotations
Not reported

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 DDD20: DAVIS Driving Dataset 2020
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 Vehicle CAN steering-wheel measurement Not reported 10 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.
Derived
Reference notes
Human steering-wheel angle in degrees serves as the prediction target, measured through the same vehicle stream released with the data. This is steering supervision, not a pose or trajectory reference; reference accuracy and channel coverage are not established.

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.

Camera viewpoints vary slightly between Ford Focus recordings.

Straight driving dominates steering labels.

DVS lacks static-feature information without temporal context; APS can suffer glare and exposure problems.

Cameras

davis

Model
DAVIS346B
Setup
Mono
Count
1
Effective cameras
1
Modality
Event
Resolution
346 x 260
Rate
Not reported
Shutter
Not Reported
Lens type
Not Reported
HFOV
Not reported
VFOV
Not reported
Notes
Concurrent DVS events and APS grayscale frames share optics. APS uses global shutter and varies from 8 to 50 fps, with additional limits in some recordings. DDD17 recordings use a 6 mm lens and 56-degree horizontal FOV; new DDD20 recordings use a Kowa 4.5 mm lens and 71-degree horizontal FOV. The asynchronous event rate is not a fixed frame rate. Ford Focus mounting varies slightly between days.

IMUs

Not reported

GNSS

Not reported

LiDAR

Not reported

Radar

Not reported

Pitot tube

Not reported

Additional sensors

Other sensor

Model
OpenXC Ford Reference vehicle interface
Name
Vehicle CAN control and diagnostics
Count
1
Rate
10 Hz
Notes
Approximately 10 Hz through OBDII. Table I lists example channels: accelerator position, brake status, engine speed, headlamps, latitude, longitude, odometer, steering angle, gear, vehicle speed and wipers. Per-recording field coverage is not specified; coordinate fields do not establish a separate released GNSS receiver.

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
hu2020ddd20

BibTeX

Not reported

Dataset corrections

Notice a specific issue after reviewing the page?

Report an inaccuracy