RepliCar

• Development of a high-precision reference system for environment recognition for automated driving
• Sensor fusion of high-resolution radar, camera and lidar data
• Development of innovative test procedures and methods

Safe perception of the environment is a crucial prerequisite for automated driving. The sensors and processing chains used must fulfil the highest requirements in terms of reliability, precision and fidelity to reality. There are currently no approaches for the effective and efficient validation of sensors and processing chains. The joint project RepliCar closes this gap: the aim of the project is to develop a reference system with integrated high-resolution radar, camera, lidar, GNSS and inertial sensors and to integrate it into a test vehicle.

This reference sensor system will be several years ahead of today’s series sensor technology. The integration of particularly high-resolution sensors and a particularly powerful sensor data fusion for object recognition make it possible to determine a highly accurate representation of reality, a so-called “ground truth”. This forms the basis for validating sensors for automated driving.

The consortium leader is ANavS GmbH, Munich. This company is also developing the sensor data fusion for determining the “ground truth” for self-localisation and environment perception. The Institute for High Frequency Technology and Electronics (IHE) at the Karlsruhe Institute of Technology (KIT), Offenburg University of Applied Sciences (HSO) and Freudenberg FST GmbH, based in Weinheim, are developing a high-precision radar system. This is an essential element in the reference system for environment perception and is described in intervals by the Institute for Regulation and Control Systems (IRS) at KIT. The project partners Akkodis Germany GmbH, Sindelfingen, the FZI Research Centre for Information Technology, Karlsruhe, IAVF Antriebstechnik GmbH, Karlsruhe, IPG Automotive GmbH, Karlsruhe, and GTÜ Gesellschaft für Technische Überwachung mbH, Stuttgart, define and implement all steps from the simulative validation to the release of the sensors and functions. The individual innovations in the validation and testing process for series sensors include artificial intelligence methods for analysing recorded scenarios, a “sensor in the loop” test bench, integration into existing simulation tools and a modular verification and validation process. The other partners HighQSoft GmbH, Idstein, and RA Consulting GmbH, Bruchsal, are building a powerful data platform for managing, processing and providing the reference data. The driving demonstrator is being realised by Dr. Ing. h.c. F. Porsche AG, Stuttgart, is realising the driving demonstrator. It records initial data and uses it for the approval process of an exemplary perception system.