2026 Intelligent Systems Summer Event

Abstract

Seamless integration of medical robotic devices in biological environments remains a challenge. When interfacing with biology, these devices are prone to the accumulation of fouling proteins, microorganisms, and biofilms that lead to inflammation, infections, and failure or rejection of the device. Addressing these complex problems requires an interdisciplinary approach in the co-design and control of robotic devices, considering mechanical, chemical, and biological effects. This was an exciting challenge that I started as a postdoc at MPI-IS in 2018, where we developed 3D-printed microrobots that avoided recognition and clearance by the immune system (significantly prolonging the functional lifetime of microrobots). More importantly, the findings and knowledge we developed opened many new research questions and opportunities, and served as the foundation of my own independent career after MPI.

In this talk, I will present how some early-stage ideas from my postdoc times at MPI-IS have evolved into a full research program at the University of Michigan, and will provide a brief perspective on exciting opportunities at the interface of robotics, surface science, and materials chemistry. Particularly, I will discuss two examples on how polymer chemistry can help provide new capabilities and functions in small-scale robotics and medical devices, and on how robotics can accelerate the discovery of new biomolecules for applications in aviation, transportation, and industrial engineering.

Biography

Abdon Pena-Francesch is an assistant professor in the Department of Materials Science & Engineering at the University of Michigan. He leads the BioInspired Materials Lab, an interdisciplinary research group working on materials science, polymer chemistry, and soft matter engineering to develop solutions for healthcare, robotics, and the environment. He obtained his PhD from Penn State University and was a Humboldt Postdoctoral Fellow at the Max Planck Institute for Intelligent Systems in Germany. His work has been recognized by multiple awards including the AFOSR Young Investigator Program Award, ACS PMSE Early Investigator Award, ACS PRF New Investigator Award, Materials Today Rising Star Award, MRS Sustainability in Action Award, and the Alexander von Humboldt Fellowship for Postdoctoral Researchers.

Abstract

In our digital age, intelligent technical systems have become an integral part of everyday life: on an almost daily basis, they guide and support our decisions when it comes to online shopping and entertainment. They can further help us acquire new knowledge and skills in a personalized way. Embedded in wearable devices, they can help us maintain a healthy lifestyle. With their constantly evolving capabilities, they can also support us in safety-critical work environments. To adequately support human users, such systems must not only be technically reliable and secure, but also meet their needs and expectations, particularly regarding trustworthiness, cognitive resource demands, or task-related performance. In this talk, I will present some examples from my ongoing research on factors that influence human trust, workload, and team performance when interacting with intelligent technical systems. Building on existing use cases such as a chatbot or a cockpit assistant, I will also outline future directions that involve robotic embodiments.

Biography

Prof. Maria Wirzberger is a full professor at the University of Stuttgart heading the Department of Applied Cognition and Informatics Education at the Institute of Visualization and Interactive Systems. By investigating individual human factors contributing to performance, workload, trust or technology acceptance, her research contributes to a responsible, human-centered design of intelligent technical systems. Aligned with this vision, she has been serving as spokesperson for the Interchange Forum for Reflecting on Intelligent Systems (IRIS) at the University of Stuttgart since its founding in 2021, an interdisciplinary network that is dedicated to critically reflecting on the ethical and social implications of intelligent systems in research, teaching, and public engagement. In addition, Prof. Wirzberger is a founding member and co-director of the Artificial Intelligence Software Academy (AISA) and, in this role, helps to make technical skills accessible to educators and students.

Abstract

Fast dynamics, nonlinearities, and variability are just a few reasons to leverage learning for control—challenges central to modern robotics. In this talk, I will explore three paradigms for developing agile robot controllers, organized from general to structured problems: deep reinforcement learning, automatic imitation learning from optimal control, and auto-tuning via Bayesian optimization. I will present recent results addressing key practical challenges, including uncertainty quantification that enables model-based reinforcement learning on hardware without relying on simulators, parameter-adaptive imitation learning without retraining, and learning from user preferences. These advancements will be illustrated through hardware experiments on unicycle robots, quadcopters, and cars, highlighting the potential of learning-based control in both research and real-world applications.

Biography

Sebastian Trimpe is a Full Professor at RWTH Aachen University, where he heads the Institute for Data Science in Mechanical Engineering (DSME) since May 2020. He is also an Executive Director of the RWTH AI Center, and the local coordinator for RWTH within the Robotics Institute Germany. His research focuses on fundamental questions at the crossroads of machine learning, control, and robotics, with innovative applications. Before joining RWTH, Sebastian was a Max Planck Research Group Leader at the Max Planck Institute for Intelligent Systems in Tübingen/Stuttgart. He earned his Ph.D. degree in 2013 from ETH Zurich, working with Raffaello D'Andrea at the Institute for Dynamic Systems and Control. Earlier, he earned degrees in engineering and technology management at Hamburg University of Technology and was a visiting research scholar at UC Berkeley. Sebastian is the recipient of several awards, including best paper awards at the IFAC World Congress and International Conference on Cyber-Physical Systems, the Klaus Tschira Award for achievements in public understanding of science, and the Future Prize by the Ewald Marquardt Stiftung for innovations in control engineering.