Über Kleinanzeigen auf der Jagd nach neuen Minds? NEIN! Das sind nicht wir und bitte reagiert nicht darauf. Das ist fake! Wir suchen euch über die üblichen bekannten Plattformen, oder auch direkt in unseren Social Media Kanälen wie LinkedIn, Facebook, XING und Twitter. Findet uns dort und tretet in Kontakt mit uns. Wir freuen uns auf euch!

QualityMinds is partner of the ATTENTION project

Artificial Intelligence for real-time injury prediction

Urban areas are characterized by limited traffic space. Automation and connecting traffic users offer could potentially enable multiple use of traffic areas. However, multiple use could also pose a great risk to unprotected traffic users, such as cyclists, pedestrians, etc. To make automated traffic as safe as possible, the severity of injuries to particularly vulnerable collision partners in unavoidable accidents in mixed traffic zones must be reduced an the best possible rate.

The aim of the ATTENTION project is to develop a method for real-time injury prediction of unprotected road users (URU), such as pedestrians or cyclists. For this purpose, data-driven AI procedures are used to determine a situation-specific risk of injury, using video data from the vehicle as well as virtual tests carried out on digital test dummies. Injury prediction which minimizes the risks for an automated vehicle could potentially lead to both safe and efficient traffic.

QualityMinds GmbH supports the ATTENTION project in the selection, improvement and generation of test and training data, design, implementation and configuration of machine learning models as well as software solutions for the demonstration of the developed methods and findings.

Our task is the selection of suitable data and features. We are also responsible for iterative findings on requirements for said features and data quality for successful customized trainings. Other area we are helping with is the development of an injury risk visualization which will be based on an open source real-time simulation for road traffic, such as CARLA. Finally, we examine the possibility of using machine learning models to bring the prediction quality of simple 3D engines simulation results closer to the results of finite element simulations.

Project duration: 07/2021 – 06/2024

Development program: Federal Ministry for Economic Affairs and Climate Action (BMWi);

Research program: „Neue Fahrzeug- und Systemtechnologie“ (in German)

Consortium members:

Associated partner:



written by

Iza Wilkosz