Decoding Decay - Real-Time Particle Detection from Point Clouds

Context

Dive into the heart of particle physics with Belle II located in Tsukuba, Japan. In our quest for indirect proof of dark matter and other rare decays, we are thriving to improve the efficiency of the detector through point cloud neural networks. Recently, these algorithms have shown promising performance in classic computer vision applications.

In this seminar thesis, you will research what it takes to adapt point cloud algorithms for high-performance embedded systems such as particle detectors. On top of that, you will have the opportunity to get in touch with FPGA firmware development for cutting-edge particle detectors.

Targets

You are going to develop a point cloud network prototype on top-of-the-line FPGAs which allows for online event processing in sub-microsecond latency.

Requirements

• Ideally you have previous experience with FPGAs or completed one of the following pertinent lectures: Laboratory System-on-Chip (PSoC),Design Hardware Laboratory (DHL),Hardware Synthesis and Optimization (HSO),Hardware Software Co-Design (HSC), Digital Circuit Design (DDS), ...
• Ability to work in an international, interdisciplinary team
• Fluent in English or German with strong communication skills
• Previous programming experience in Python, C++, Scala is a plus