highD ist ein Datensatz von naturalistischen Fahrzeugtrajektorien, die auf deutschen Autobahnen aufgenommen wurden. Mit einer Drohne werden typische Einschränkungen etablierter Verkehrsdatenerfassungsmethoden wie z. B. Okklusionen durch die Luftperspektive überwunden. Der Verkehr wurde an sechs verschiedenen Orten erfasst und umfasst mehr als 110 500 Fahrzeuge.

highD is a dataset of naturalistic vehicle trajectories recorded on German highways. Using a drone, typical limitations of established traffic data acquisition methods, such as occlusions are overcome due to the aerial perspective. Traffic was recorded at six different locations and comprises more than 110 500 vehicles.

[Logo: HighD+]

The highD Dataset was created for the safety validation of highly automated vehicles but is also suitable for many other tasks such as the analysis of traffic patterns or the parameterization of driver models . While the highD dataset is freely available for scientific and non-commercial purposes, we offer commercial automotive users the possibility to purchase a commercial license and services based on highD as highD+.

In addition to the approx. 44 500 km in the highD data set, fka currently has a further 10 500 km of highway data at its disposal. This is constantly being expanded. You are welcome to contact us if you are interested in further data on specific locations.

HighDplus Service Portfolio

Commercial Rights of Use

Acquire the rights to commercially use the dataset and develop your own commercial applications and solutions.


We offer analyses, evaluations and also the parameterization of models on the basis of the dataset.

Individual Solutions

At your request we can offer you individual solutions.

[Fotomontage: HighD Diagram]

Not only do we offer probably the largest and most accurate vehicle trajectory dataset currently available, but we are also experts in using the dataset for a variety of automated driving applications. This enables us to offer you an extensive package of services around highD+ Dataset:

  • Extraction and parameterization of scenarios
  • Evaluation and concepts for the safety validation of automated driving functions
  • Parameterization of driver models
  • Training of prediction models
  • Impact assessment of automated driving functions
  • Representation of relevant scenarios in the simulation
  • Representation of relevant scenarios in the highly dynamic driving simulator
  • Presentation of relevant scenarios on test tracks (e.g. the Aldenhoven Testing Center)
  • Testing with coupling of real driving tests and simulation
  • Parameterization of traffic flow simulations

We have the data, know its application and have defined the interfaces.

Learn all about HighDplus. We will be happy to advise you.

Please enter your first name.
Please enter your last name.
Please enter your company.
Please enter your position.
Please enter your Email address.
Please enter your Phone number.
I am interested in
Please select what you are interested in.
Please give information about your (research) project and what you would like to use the dataset for (100 characters minimum).
Ungültige Eingabe

Ihr Ansprechpartner

Your contact

[Foto: Julian Bock]

Julian Bock M.Sc.
Manager Artificial Intelligence

This email address is being protected from spambots. You need JavaScript enabled to view it.
Telefon: +49 241 80 26533

This email address is being protected from spambots. You need JavaScript enabled to view it.
Phone: +49 241 80 26533