DFG funds research at the interface of machine learning and control theory

The German Research Foundation (DFG) has approved funding for a new Research Training Group (RTG) named METEOR (Machine Learning and Control Theory: Exploring Synergies, Complementarities and Mutual Benefits). The initiative is a joint project between Ludwig-Maximilians-Universität München (LMU) and the Technical University of Munich (TUM), set to commence in spring 2026 for an initial five-year period.

The RTG aims to bridge the gap between machine learning (ML) and control theory (CT), two core disciplines within computer science and engineering. Despite shared interests and methodologies, these fields have largely developed independently, fostering distinct languages and cultures. METEOR seeks to foster synergy by integrating ML's data-driven, learning-centric approach with CT's model-based perspective.

The program is designed to cultivate a new generation of researchers proficient in both areas. This will be achieved through tailored lectures, seminars, interdisciplinary workshops, and annual hackathons, intended to establish a common lexicon and foundational understanding between the disciplines, alongside practical experience.

METEOR's research will focus on two primary directions. The first will investigate how ML can support the data-driven design of robust control for complex, safety-critical applications. The second will explore how CT concepts and methods can enhance ML algorithms. Both directions will be approached from the perspective of complex dynamical systems, which provide a shared mathematical framework.