Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

DY: Fachverband Dynamik und Statistische Physik

DY 41: Poster: Nonlinear Dynamics, Granular Matter, and Machine Learning

DY 41.13: Poster

Mittwoch, 11. März 2026, 15:00–18:00, P5

TANGO and Machine Learning Enhanced Experimentation for Real Time Tracking of Actively Steered Magnetic Particles. — •Nikita Popkov^2,3, Nikolai Weidt^1,2, Yahya Shubbak^1,2, Rico Huhnstock^1,2, Kristina Dingel^2,3, Bernhard Sick^2,3, and Arno Ehresmann^1,2 — ¹Institute for Physics and CINSaT, University of Kassel, Heinrich-Plett-Str. 40, 34132 Kassel, Germany — ²AIM-ED, Joint Lab of Helmholtzzentrum für Materialien und Energie, Berlin (HZB) and University of Kassel, Hahn-Meitner-Platz 1, 14109, Berlin, Germany — ³Intelligent Embedded Systems, University of Kassel, Wilhelmshöher Allee 71-73, 34121, Kassel, Germany

This work presents an AI-driven closed-loop framework for automating experimental tasks, demonstrated for the remote-controlled on-chip transport of magnetic particles. The system integrates machine learning models for particle detection, tracking, and classification, enabling dynamic feedback control during experiments. It autonomously adjusts experimental parameters to improve data quality and align outcomes with research objectives. The TANGO controls modular design allows adaptation to different experimental setups and hypotheses. Overall, it emphasizes how autonomous systems could iteratively optimize experiments, advancing the field of next-generation laboratory automation and, specifically for our experiments, the development of novel lab-on-a-chip devices.

Keywords: machine learning; intelligent experimentation; automated science