Automatic Control Laboratory

Open Opportunities

Integration of robust control design and flexible optimal guidance for reusable launch vehicles ETH Zurich Automatic Control Laboratory Autonomy is a key enabler for successful and reliable space missions carried out with reusable rockets. This project will investigate the integration of optimal guidance strategies with the design of robust controllers for these challenging missions, which are in the forefront of space endeavours. Flight Control Systems, Flight Dynamics, Systems Theory and Control Master Thesis

Implementation and Analysis of the Stochastic Generalized Gauss-Newton Method for Training Deep Neural Networks ETH Zurich Automatic Control Laboratory Deep neural networks (DNNs) are powerful mathematical models capable of learning arbitrarily complex functions given a sufficiently representative set of data points. In the recent decade, DNNs have been successfully deployed in many different applications, ranging from computer vision to finance. Engineering and Technology, Information, Computing and Communication Sciences, Mathematical Sciences Master Thesis

Control of Dynamic Virtual Power Plants with Distributed Energy Sources ETH Zurich Automatic Control Laboratory The goal of this project is to develop and test control strategies for a heterogenous group of geographically distributed energy resources (e.g. wind, PV, energy storage systems, etc.) to collectively provide dynamic ancillary services to the power grid. Engineering and Technology Bachelor Thesis, Master Thesis, Semester Project

Predictive-sensitivity for optimization ETH Zurich Automatic Control Laboratory The objective is to explore the applications of the predictive-sensitivity approach in the field of optimization, in particular, for algorithm that have nested loops on different time-scales. Engineering and Technology, Mathematical Sciences Master Thesis

Stochastic Online Feedback Optimization for Power Systems ETH Zurich Automatic Control Laboratory The objective of the Thesis is to build a stochastic online feedback optimization algorithm taking into account the uncertainty from a dynamic state estimation, and use to solve a power grid optimal power flow. Engineering and Technology Bachelor Thesis, Master Thesis, Semester Project

SwissFEL photocathode laser optimization and stabilization using data-driven optimization ETH Zurich Automatic Control Laboratory To achieve continuous stability, we propose to optimize the swiss-FEL UV seed laser beam, using images of the beam from two cameras and measurements of the laser power. In this project, we will use sequential data-driven optimization to achieve efficiently the correct alignment via motorized mirrors Engineering and Technology Master Thesis

Robust optimal control of power hardware in the loop systems ETH Zurich Automatic Control Laboratory Power-Hardware-In-the-Loop is an advanced simulation infrastructure that allows connecting power producing devices to real-time grid simulators. The project aims at designing an interface which ensures robust stability and performance and testing it at the Hydro Quebec Research Institute. Control Engineering, Electrical Engineering, Systems Theory and Control Master Thesis

Machine learning-based forecast of CO2 intensity to support electrical load shifting ETH Zurich Automatic Control Laboratory In this project, we aim at combining decomposition-based approaches with various machine learning techniques to forecast the short-term CO2 intensity time series (for SA). Furthermore, we aim at using this forecast in the implementation of an emission-aware Model Predictive Controller (for MA). Engineering and Technology, Information, Computing and Communication Sciences Master Thesis, Semester Project

Karma mechanisms for many players and resources ETH Zurich Automatic Control Laboratory Karma mechanisms allow for players to self-coordinate the use of resources in a fair and efficient manner. We recently demonstrated that for the case of two players competing over one resource. The main scope of this project is to extend the mechanism to an arbitrary number of players and resources. Intelligent Robotics Master Thesis

Design of a PAT-controlled pharmaceutical drug product dilution process ETH Zurich Automatic Control Laboratory We aim to design and complete a proof-of-concept study for a pharmaceutical drug product dilution process, utilizing advanced model-predictive process control. The advantage of this setup is to decrease manufacturing lead time and reduce operational execution failure rates. Engineering and Technology Master Thesis