Campus Event Calendar

Event Entry

What and Who

Machine learning for machines: Challenges and recent results in learning-based control

Prof. Sebastian Trimpe
RWTH Aachen

Sebastian Trimpe is a Full Professor at RWTH Aachen University, where he heads the newly founded Institute for Data Science in Mechanical Engineering (DSME) since May 2020. Research at DSME focuses on fundamental questions at the intersection of machine learning, control, networked systems, and robotics. Sebastian is also a Co-Director of the RWTH Center for Artificial Intelligence. Before moving to RWTH, he was a Max Planck Research Group Leader (W2) at the Max Planck Institute for Intelligent Systems in Tübingen/Stuttgart. He obtained his Ph.D. degree in 2013 from ETH Zurich with Raffaello D'Andrea at the Institute for Dynamic Systems and Control. Before, he received a B.Sc. degree in General Engineering Science in 2005, a M.Sc. degree (Dipl.-Ing.) in Electrical Engineering in 2007, and an MBA degree in Technology Management in 2007, all from Hamburg University of Technology. Sebastian is recipient of the triennial IFAC World Congress Interactive Paper Prize (2011), the Klaus Tschira Award for achievements in public understanding of science (2014), the Best Paper Award of the International Conference on Cyber-Physical Systems (2019), and the Future Prize by the Ewald Marquardt Stiftung for innovations in control engineering (2020).
More info at
AG 1, INET, AG 5, RG1, SWS, AG 2, AG 4, D6, AG 3  
AG Audience

Date, Time and Location

Thursday, 22 June 2023
60 Minutes
E1 4


In recent years, machine learning (ML) has revolutionized domains like computer vision, natural language processing, and web services. While ML holds great promise also for engineering, some core challenges have to be overcome requiring new developments at the intersection of the fields. In this talk, I will discuss new approaches integrating ML with control theory and some of our recent results in learning-based control: (i) probabilistic model learning incorporating also physical knowledge, (ii) controller optimization combining simulation and real experiments, and (iii) deep learning of approximate model predictive controllers with guarantees. The developed theory will be illustrated through experimental results on robotic hardware.


Vahid Babaei
+49 681 302 70761
--email hidden
passcode not visible

Vahid Babaei, 06/07/2023 12:40
Vahid Babaei, 06/07/2023 12:36 -- Created document.