To content
Department of Mechanical Engineering
Academic exchange with ETH Zürich on data-driven control

Exchange with ETH Zürich

Manuel Klädtke giving a talk on explainability in data-driven predictive control at ETH Zürich © RCS​/​MKL
Manuel Klädtke visited the Automatic Control Lab (IfA) at ETH Zürich in Switzerland as part of an academic exchange.

Manuel has recently returned from an insightful visit to the Automatic Control Lab (IfA) at ETH Zürich, a leading group in the field of data-driven control and the birthplace of the popular DeePC scheme. During this visit, he engaged in meaningful discussions that provided valuable insights into current trends and challenges in our field.

As part of this exchange, Manuel gave a talk titled "Exploring the DeePC - Explainability in Data-Driven Predictive Control,” where he offered clear interpretations of the underlying regularization mechanisms and challenged several commonly held heuristics, which was very well received by the attendees. The productive discussions that followed may serve as a foundation for future collaborations aimed at enhancing explainability in data-driven control and leveraging these insights for improved control schemes.

If you are interested in the topic, feel free to contact Manuel or check out our recent (Open Access) papers:

M. Klädtke and M. Schulze Darup, Towards explainable data-driven predictive control with regularizations, in at - Automatisierungstechnik, DOI: 10.1515/auto-2024-0161.

M. Klädtke and M. Schulze Darup, On Data Usage and Predictive Behavior of Data-Driven Predictive Control With 1-Norm Regularization, in IEEE Control Systems Letters, doi: 10.1109/LCSYS.2025.3575436.