Prediction of traffic risks

D-TRAS research project completed

The Austrian-German joint project "D-TRAS - Digital Platform for Traffic Safety-Risk Prediction in Rural Areas" was recently concluded with an official closing event and presentation of results at the Historical Observatory in Göttingen. The Smart Mobility Research Group of the Chair of Information Management (Prof Dr Lutz M. Kolbe) and the Research Group for Information Security and Compliance from the University of Göttingen were involved in the project. Project partners from the field were the Austrian companies Virtual Vehicle Research GmbH and motobit GmbH as well as Caruso GmbH and NEXT Data Service AG from Germany. The project was funded by the Federal Ministry for Economic Affairs and Climate Action.

D-TRAS investigated the feasibility of combining vehicle sensor data with safety-relevant data to innovate the prediction of traffic risks. The aim was to provide a traffic risk prediction service for road users running on a digital platform considering the contextual information provided. To this end, sensor data (e.g. from vehicle sensors, smartphones and wearables) and other safety-relevant data sources have been brought together over the past three and a half years in order to recognise traffic risks at an early stage and communicate warnings effectively with the help of a specially developed cloud architecture and the application of machine learning methods. These warnings are now sent to various apps that have integrated the "D-TRAS Kit" and thus provide a direct source of information for road users.

This warning service has also been tested in a field study in two different apps. The tests confirmed the effectiveness of the system, so the final event also discussed possible business models that could be associated with D-TRAS. A live demonstration was also carried out during a taxi journey.

About the project D-TRAS: https://www.uni-goettingen.de/de/648025.html