Job description
We are looking for motivated doctoral students to contribute to this effort. The envisioned research will address:
1. Online learning-based control and control-oriented machine learning with application to advanced manufacturing systems, using methods such as Reinforcement Learning, Online Convex Optimization, and Iterative Learning Control.
2. System-level hierarchical controller optimization for industrial systems and decision-making using methods from bilevel, on-line, and differentiable optimization.
3. Control and task planning for advanced manufacturing using domain knowledge and expert feedback using methods from domain adaptation, transfer learning, and large-language models and expert feedback in process planning.
4. Digital twin-based learning and optimization for manufacturing processes such as 3D Printing, laser cutting, precision motion, robotic manipulation, using methods in machine learning, federated learning, and optimization.
In all cases, the results will be demonstrated on real-world advanced manufacturing and robotic systems in collaboration with industrial partners, helping to improve the efficiency and sustainability of their products.
Your goal will be to translate your own research ideas to tackle these challenges, in close collaboration with our interdisciplinary team. As part of this process, you will support our master students, publish in scientific journals, and participate in conferences. The positions are supported by the NCCR Automation and the European Project DMaaST that offer excellent opportunities for national and international collaboration with academic and industrial partners.
Your profile
You are highly motivated and dedicated with a master’s degree in electrical, mechanical, or industrial engineering. Programming, modelling, and data analysis skills in python and machine learning/optimization libraries support you in contributing to our ongoing software development efforts. Your spoken and written English skills help you navigate our international environment.