PhD - Antwerpen | More than two weeks ago
The field of AI has seen great successes in the last years across different application fields such as image processing, robotics, and language. However, a next step is to embed these AI solutions into larger processes and systems. For instance, embed AI algorithms into an industrial production process or a future car. This is far from a trivial task as this raises questions on overall architecture and system design, especially when incorporating constraints like robustness, efficiency, safety, resource consumption, etc. Moreover, this problem grows even more complex when we expected the AI solutions to handle more complex tasks and include more features.
Let’s take a future car as an example [1,2]. This car will contain main different sensors and require AI algorithms to help in perceiving their environment and to offer information to ADAS features (e.g., automatic braking, lane assist, traffic assist, …) and (semi-)autonomous driving. However, many questions are still unsolved: Which (combination of) sensors are required? Where to place the compute (e.g., central versus distributed)? Which communication channels are required? What is the energy and resource consumption of the overall system?
In this PhD topics we would like to explore methods to better answer such questions. The aim is to focus on simulation and modelling of such complex systems, the design of appropriate profiling and analyzing tools, explore the integration of AI accelerators for lower power consumption, and optimizing such systems (e.g., in terms of resource allocation). The end result could be a framework that integrated DL models with sensor systems, enabling real-time data analysis, interpretation and benchmarking. This framework will be accompanied by a suite of efficient AI algorithms and tools.
We offer you a challenging, stimulating and pleasant research environment, where you can contribute to international research on artificial intelligence with a close link to the underlaying hardware. While you will work in the AI&Data department, you will also be working together with imec hardware, sensor development and university teams on jointly coming up with novel solutions.
Our ideal candidate for this position has the following skills:
 Zhu, H., Zhou, W., Li, Z., Li, L., & Huang, T. (2021). Requirements-driven automotive electrical/electronic architecture: A survey and prospective trends. IEEE Access, 9, 100096-100112.
Required background: Master’s degree in Computer Science, Informatics, Physics, Engineering or Electronics, with knowledge about artificial intelligence and machine learning
Type of work: Modelling, algorithmic and system design, experimentation, literature study
Supervisor: Steven Latré
Co-supervisor: Tom De Schepper
Daily advisor: Julie Moeyersoms
The reference code for this position is 2024-090. Mention this reference code on your application form.