Research Projects

Recent advancements in machine learning offer new opportunities for the design of high performance controllers for many safety critical applications, for example in power systems, robotics, biomedical applications, or manufacturing. At the same time, the use of learning in closed-loop control systems raises a number of challenges related to their safety and reliability, but also real-time computation requirements and data-efficiency. We develop the theory, methods and tools for advanced control and state estimation with guaranteed satisfaction of critical safety constraints, and demonstrate their benefits in a range of applications together with our industry and research partners. The following pages provide on overview of our research activities.

An overview of previous research projects can be found here.

Predictive Control Methods

Predictive control methods use finite-​horizon model-​based predictions and compute an optimal control input based on an optimization problem. This offers a flexible framework to address a range of challenging control problems, including safe learning-based control. more...

Learning and Estimation

One of the key problems in science and engineering is to provide a quantitative description of the systems under investigation leveraging collected noisy data. Our research in learning targets both static and dynamic systems, aiming for strategies that trade off accuracy and computational speed to be used, e.g., in the context of (adaptive) control. In this context, we are also interested in providing algorithms to perform state estimation of dynamical systems from noisy data. more...

Emborocket

Demonstrators

We validate the developed control, estimation, and learning methods on challenging robotics hardware platforms in order to highlight the advantages of novel techniques, but also to determine the limitations. The various applications include autonomous racing, autonomous flying vehicles, and multi-​agent robotics. more...

Biomedical Applications

In our research projects, we aim to model the nonlinear behavior of the human body, estimate appropriate parameters for the attending physician and by means of adaptive, safe controllers to ultimately improve the health of the patient. more...

JavaScript has been disabled in your browser