The AuRoRaS (Automotive Robust Radar Sensing) research project aims to develop new simulation processes and artificial intelligence methods to make radar systems more efficient and autonomous driving safer. As part of KMU-innovativ, an initiative funded by the German Federal Ministry of Education and Research (BMBF), three partners from the world of research and technology - Astyx GmbH, BIT Technology Solutions GmbH and the DFKI - are currently working on improving the measurement quality of high-resolution radar sensors.

Over the next two years, the team plans to develop an automotive radar system for use in highly automated (level 4) and autonomous (level 5) driving, with the aim of significantly improving the quality of the measurement data generated by “continuous-wave radar”. Radar sensors are already widely used in the automotive industry, as their ability to directly measure object speed and withstand weather influences such as fog or snow gives them a clear advantage over camera-based methods and laser sensors (lidar). Among their disadvantages are errors in signal processing that can occur as a result of speed ambiguities or “multipath propagation” – caused by a reflective road surface, for example. However, since a very high level of accuracy and robustness are vital to automated and autonomous driving functions, the project team plans to use innovative AI methods to identify and eliminate the disadvantages of radar sensors, which are rooted in physical circumstances.

German Research Center for Artificial Intelligence (Deutsches Forschungszentrum für Künstliche Intelligenz GmbH) (67663 Kaiserslautern, Germany)
www.dfki.de