Signal processing will play an integral role for enabling all communications in future generation green electric and autonomous vehicles. As the number of communication links and propagation scenarios grows ever faster, the available conventional techniques, often based on simplified assumptions, are failing to meet the demands for high performance and low complexity. On the other hand, the rapidly developing field of machine learning can provide powerful data-driven approaches for the development of new or the enhancement of the available algorithmic signal processing solutions, giving the opportunity to seek reductions in the energy consumption and implementational costs.
The RAISE project will investigate and develop efficient low-complexity machine learning (artificial neural networks and deep learning) techniques for signal processing in automotive radar systems, specifically tailored around the physics-based model of the underlying problem. The novel solutions will be implemented on hardware. This is a €1.6M project, situated on the edge between academia (Eindhoven University of Technology) and industry (NXP Semiconductors), and in total it will involve 3 post-docs, 6 PhD and 2 PDEng students.
