leveLXData – Real-World Scenario Data
The Highway Drone Dataset
Naturalistic Trajectories of 110 500 Vehicles Recorded at German Highways

About the Dataset

The highD dataset is a new dataset of naturalistic vehicle trajectories recorded on German highways. Using a drone, typical limitations of established traffic data collection methods such as occlusions are overcome by the aerial perspective. Traffic was recorded at six different locations and includes more than 110 500 vehicles. Each vehicle’s trajectory, including vehicle type, size and manoeuvres, is automatically extracted. Using state-of-the-art computer vision algorithms, the positioning error is typically less than ten centimeters. Although the dataset was created for the safety validation of highly automated vehicles, it is also suitable for many other tasks such as the analysis of traffic patterns or the parameterization of driver models.

The highD dataset was created and published by a team from the Institute for Automotive Engineering (ika) of RWTH Aachen University to promote research in many different domains of mobility. The dataset can therefore be downloaded and used free of charge for academic and research purposes.

🔍 Large-scale Dataset

The dataset includes:

  • 110 500 vehicles
  • 44 500 driven kilometers
  • 147 driven hours

⭐ High Quality and Variety

The dataset features:

  • Six different recording locations
  • Different traffic states (e.g. traffic jams)
  • Low typical positioning error

✨ Enriched Data

Pre-extracted information include:

  • Surrounding vehicles
  • Metrics like THW or TTC
  • Driven maneuvers (e.g. lane changes)

🚀 Easy Start

Provided scripts for Python here:

  • Parsing of provided files
  • Visualization of recorded trajectories

Download the format description here.

Citation

Our paper introducing the dataset and the used methods is published at the IEEE ITSC 2018 and available here. A preprint on arXiv.org is available here. To reference the dataset, please use:

@inproceedings{highDdataset,
               title={The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems},
               author={Krajewski, Robert and Bock, Julian and Kloeker, Laurent and Eckstein, Lutz},
               booktitle={2018 21st International Conference on Intelligent Transportation Systems (ITSC)},
               pages={2118-2125},
               year={2018},
               doi={10.1109/ITSC.2018.8569552}
}

Application for Access for Non-Commercial Use

To apply for access to the dataset, please send us a request using this form. Please note that each request is checked manually. Therefore, make sure that that your answers are complete, detailed and correct. If any ambiguities arise, we may contact you for clarification purposes.

    Full name (*) Official university/company address (*) Company/Insitut/University/Authority/Association (*)
    Project - please check all the options that apply to you (*)
    Please tell us about yourself, your position, your current (research) project and what exactly you would like to use the highD dataset for. Access will only be granted if all details are provided. (*)

    Commercial Use

    The highD dataset is free for non-commercial use only. If you are interested in commercial use, please visit https://levelxdata.com. Under levelXdata, fka GmbH combines its expertise in the field of data acquisition and processing for all stages of automated driving.

    Full Usage Rights

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

    Analysis

    The leveLXData team can provide or support your analyses, evaluations and also parameterization of models on the basis of the data.

    Individual Solutions

    leveLXData can tailor a dataset for your requirement, either from an extensive database or based on new traffic recordings along your needs.

    More Datasets

    In addition to the highD dataset, we used the same methodology to create more datasets. Specifically, the inD dataset covers trajectories of road users including pedestrians at urban intersections. The highly interactive behavior of road users at roundabouts is captured in the rounD dataset.

    Furthermore the exiD dataset contains trajectories of vehicles at exits and entries of highways in Germany. The trajectories of road users at the RWTH Aachen University Campus are covered in the uniD dataset. Find out more about these datasets on the individual websites.

    Contact

    Institute for Automotive Engineering, RWTH Aachen University
    Vehicle Intelligence and Automated Driving
    Steinbachstraße 7
    52074 Aachen
    Germany

    leveLXData by fka GmbH
    Steinbachstraße 7
    52074 Aachen
    Germany

    home