The evaluation of autonomous driving functionality is a big challenge for developers: Simulations reflect reality only to a certain degree und real-world-testing is expensive, complex and legally problematic. Model vehicles provide a compromise solution. This allows software components to be tested without having to overcome the major hurdles of actual passenger cars.
The aim of these scale vehicles is to carry the necessary hardware in the form of sensors, computers and actuators in order to cover all areas of autonomous driving. This enables an application in research and development of new algorithms as well as an application for teaching purposes.
Modern components such as stereo cameras and LiDARs are used to get as close as possible to real-world-vehicles. The software platform is designed in such a way that individual functions can be developed isolated from each other as far as possible. For this purpose the open source middleware ROS (Robot Operating System) is being used. In order to be able to test the interaction between vehicles, several scale vehicles are to be built that can communicate with each other.