📃 Dataset Overview
- Naturalistic trajectory dataset on one recording location
- In total ~ 1380 vehicles and ~ 8600 vulnerable road users (VRUs)
- All road users classes: car, truck/bus, pedestrians, bicyclists
- Shared space next to university
⭐ High Quality and Variety
- High tracking and classification accuracy
- High positioning accuracy
- Highly naturalistic trajectories
- Excellent digital maps (lanelet2 and OpenDRIVE)
🛠️ Supplementary Data
- ASAM OpenDRIVE maps
- Lanelet2 maps
Method
The uniD dataset is an innovative collection of naturalistic road user trajectories, captured within the RWTH Aachen University campus using drone technology to address common challenges such as occlusions found in traditional traffic data collection methods. It meticulously documents the movement and classifies each road user by type. Employing cutting-edge computer vision algorithms, the dataset ensures high positional accuracy. Its utility spans various applications, from predicting road user behavior and modeling driver actions to conducting scenario-based safety checks for automated driving systems and facilitating the data-driven design of Highly Automated Driving (HAD) system components.
What’s included?
- Georeferenced trajectory data (e.g. position, heading, lat./long. velocity/acceleration)
- Recording Meta Information (e.g. frame rate, gps of location or # of objects)
- Track Meta Information (e.g. road user type, size and class)
- One digital map representation for each location in
- OpenDRIVE format including 3D information (fbx & osgb)
- Lanelet2 format
- One aerial photograph of each location without road users
Digital Maps **NEW**
Our dataset includes detailed high-definition maps, enabling the analysis of trajectories in relation to the infrastructure. It supports both ASAM OpenDRIVE and Lanelet2 formats for comprehensive compatibility. Furthermore, these maps facilitate the seamless integration of our trajectory data into prominent simulation tools. To enhance this integration, we provide 3D environments corresponding to the maps in all major formats, including *.osgb and *.fbx, among others.
Applications
This dataset is incredibly versatile, serving a wide range of applications including road user prediction, driver behavior modeling, scenario-based safety validation for automated driving systems, and the development of components for Highly Automated Driving (HAD) systems. Its utility spans from enhancing the understanding of driving dynamics to supporting the refinement and innovation of autonomous vehicle technologies, thereby contributing significantly to advancements in the field of automated driving.
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.
Commercial Use
The uniD 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 uniD dataset, we used the same methodlogy to create more datasets. Specifically, the highD dataset covers trajectories of vehicles on German highways. The interactions of vehicles at entries and exits of German highways are captured in the exiD dataset.
The highly interactive behavior of road users at urban intersections is captured in the inD dataset. Similarly the rounD dataset contains trajectories of road users at German roundabouts. Find out more about these datasets on the individual websites.