As Austria's largest research and technology organisation for applied research, we are dedicated to make substantial contributions to solving the major challenges of our time, climate change and digitalisation. To achieve our goals, we rely on our specific research, development and technology competencies, which are the basis of our commitment to excellence in all areas. With our open culture of innovation and our motivated, international teams, we are working to position AIT as Austria's leading research institution at the highest international level and to make a positive contribution to the economy and society.

Our Center for Vision, Automation & Control located in Vienna invites applications for a Master Thesis. The Center for Vision, Automation & Control exploits the opportunities provided by automation and digitalisation to initiate and advance innovation for industry, primarily in Austria and Europe. Our main goal is to take away the monotonous, heavy, difficult and dangerous aspects of people’s work through innovation. We help our partners by making technical systems more robust, reliable, flexible and easy to use. At the same time, we increase the resource efficiency of industrial processes by reducing waste, product failures and emissions.

Our Competence Unit Complex Dynamical Systems located in Vienna invites applications for a master thesis. Our unit focuses on the development and deployment of algorithms to control various types of systems. Starting from low energy applications like electronics and drive systems, via (large-scale) robotics to heavy industrial applications. We are working in projects in cooperation with national and international research organisations and companies leading their market sector.

• This master’s thesis will explore the application of Clustered Federated Learning (Clustered FL) in the context of nonlinear control systems, with a particular focus on vehicle dynamics.
• Clustered FL extends traditional Federated Learning by enabling collaboration among clients with heterogeneous data distributions - accounting for feature, target, and concept shift - as well as temporal variations. Despite recent advances in Clustered FL, its integration with real-world control systems remains largely unexplored.
• The goal of this thesis is to analyse existing Clustered FL techniques, adapt them to the challenges of nonlinear control, and evaluate their performance in practical control scenarios, paving the way for robust and privacy-preserving learning in distributed control settings.

• You will start with a comprehensive literature review to understand the current state of Clustered FL and its potential for handling data heterogeneity and distribution shifts.
• Based on this review, suitable algorithms will be selected and implemented, with a focus on adapting them to the specific challenges of nonlinear control systems.
• Together with our team, you will strive to publish the code basis in an Open Science publication of the source code.
• You will be trained in scientific work, and you will have the opportunity to discuss your experiences with scientific interdisciplinary experts from the fields of mathematics, electronics, informatics, physics and control and mechanical engineering.
• You may publish your results at a conference or a journal.