ABOUT THIS POSITION

Interested in deep learning for radar? Explore with us how deep learning can optimize radar waveforms under real-world constraints and interference of other emitters. The internship challenges you to embed these into networks and validate with actual radar measurements!

Next generation radar systems have the flexibility to transmit complex signals to improve on the robustness of detecting targets with interference of other emitters. Optimizing waveforms for radar operation result in non-smooth and non-convex and, therefore, are computationally challenging.
The goal is to define a deep learning optimization problem for waveform design. Deep learning frameworks provide powerful solvers, but their main utilization is in other applications. Therefore, research questions arising are: how to embed hardware constraints, e.g., quantization, into the network? And how to optimize the waveform for specific interference of other emitters? The waveform of the trained network should be validated using real-life measurements. Potential research directions could be into soft quantization networks and/or ResNet autoencoders.
You will perform this assignment in the Department of Radar Technology. We are a passionate and creative group of professionals (60 people) dedicated to the specification, development and evaluation of innovative, high-performance MMICs, miniaturised and integrated RF subsystems, antennas and front-ends. The department is at the heart of novel, game-changing radar system and signal processing concepts for the military, space and civil domains.