The goal of the project PARIS is the development of a new highly parallel processing unit with optimized cores for the calculation of complex and computationally intensive fusion algorithms. A major field of these algorithms is machine learning, e.g. for computer vision, but also for behavior generation in the context of automated driving.
For the development of these algorithms, it is essential to create programming guidelines and verification methods already during the development process, e.g. by using virtual prototyping methods. At the end of the project, all algorithms will be integrated in a test vehicle and demonstrated in a real driving scene.
In this project, a novel parallel processor platform with optimized processor cores will be developed. Complex and computationally intensive sensor fusion algorithms shall be mapped on this platform. In particular, innovative algorithms from the field of machine learning shall be developed and applied. In order to efficiently model such algorithms, programming and verification methods based on virtual prototyping, among others, shall be developed. At the end of the project, the developed and implemented algorithms will be presented in a demonstrator vehicle in a real driving situation.