Physical intelligent agents act that want act in the world need to control their bodies autonomously while learning new behaviors and adapt new goals or react to changes in their environment. I am interested in understanding how an agent can explore it's capacity to act in a safe and robust manner. I am currently working on controllers for systems with complex dynamics and I am especially interested in learning interpretable models and robust controllers, combining machine learning methods with optimal control theory.
As part of the Intelligent Control Systems Group at the Max Planck Institute for Intelligent Systems I am currently doing my Ph.D. under the supervision of Dr. Sebastian Trimpe and in close collaboration with the IAV GmbH.
Before joining the Intelligent Control Systems group for my master thesis in 2018 I studied Computer Science at the University of Lübeck and obtained my Bachelor's degree in Electrical Engineering at the Beuth University of Applied Sciences Berlin in 2013.
In International Conference on Intelligent Robots and Systems (IROS) 2018, pages: 6199-6206, International Conference on Intelligent Robots and Systems 2018, October 2018 (inproceedings)
Soft microrobots based on photoresponsive materials and controlled by light fields can generate a variety of different gaits. This inherent flexibility can be exploited to maximize their locomotion performance in a given environment and used to adapt them to changing environments. However, because of the lack of accurate locomotion models, and given the intrinsic variability among microrobots, analytical control design is not possible. Common data-driven approaches, on the other hand, require running prohibitive numbers of experiments and lead to very sample-specific results. Here we propose a probabilistic learning approach for light-controlled soft microrobots based on Bayesian Optimization (BO) and Gaussian Processes (GPs). The proposed approach results in a learning scheme that is highly data-efficient, enabling gait optimization with a limited experimental budget, and robust against differences among microrobot samples. These features are obtained by designing the learning scheme through the comparison of different GP priors and BO settings on a semisynthetic data set. The developed learning scheme is validated in microrobot experiments, resulting in a 115% improvement in a microrobot’s locomotion performance with an experimental budget of only 20 tests. These encouraging results lead the way toward self-adaptive microrobotic systems based on lightcontrolled soft microrobots and probabilistic learning control.
Our goal is to understand the principles of Perception, Action and Learning in autonomous systems that successfully interact with complex environments and to use this understanding to design future systems