Title: Adaptive Control of Magnetic Soft Millirobots
Abstract: Untethered magnetic soft millirobots have the potential to be used in biomedical applications, such as minimally invasive surgery and targeted drug delivery, as they can access hard-to-reach spaces in the human body non-invasively. However, significant variability in the environment and inherent stochastic variance during the fabrication processes affect the robot’s motion and task performance. Therefore, adapting the controller for different robots and task spaces is crucial for medical applications. In this talk, I am going to present how Bayesian optimization (BO) and Gaussian processes (GPs) can address this challenge and tune controller parameters in a data-efficient way.
Bio: Sinan received his bachelor’s degree in Mechanical Engineering and a minor in Mechatronics from
Middle East Technical University (METU) in Ankara, Turkiye. After completing his master’s degree
focusing on road detection algorithms for autonomous ground vehicles at METU, he has started his Ph.D. in Physical Intelligence Department at the Max Planck Institute (MPI) for Intelligent Systems in Stuttgart, Germany. His doctoral research is awarded a Ph.D. scholarship from the Ministry of Education of Turkiye and focuses on the fabrication, localization, and control of small-scale soft robots, statistical machine learning on physical systems, and the design of magnetic actuation systems