ETH Zurich

Open Opportunities

Probabilistic System Identification of a Quadrotor Platform University of Zurich Robotics and Perception This work investigates the usage of Gaussian Processes for uncertainty-aware system identification of a quadrotor platform. Automotive Engineering Master Thesis, Semester Project

Why so complicated? Global localization without fuss University of Zurich Robotics and Perception Achieve comparable or better place recognition performance than NetVLAD, with a simpler network architecture. Computer Vision Master Thesis

One net to rule them all (global localization and pose estimation) University of Zurich Robotics and Perception Combine state-of-the-art place embedding and feature extraction networks into a single network and train them jointly. Computer Vision Master Thesis

Learning to paint with an autonomous spray painting UAV ETH Zurich Autonomous Systems Lab PaintCopter [1] is an autonomous UAV capable of spray painting on complex 3D surfaces. Currently the system is capable of painting basic elements such as lines, gradients and area-fill with a color of choice (see Fig.b). The motivation for this project is to find a way to decompose a provided textur Knowledge Representation and Machine Learning, Robotics and Mechatronics Master Thesis

Data-Driven Visual Inertial Odometry for Quadrotor Flight University of Zurich Robotics and Perception Investigate the usability of data-driven methods to improve the performance of a VIO pipeline on a resource-constrained platform. Automotive Engineering Master Thesis, Semester Project

Data-efficient Optimization of the Thermal Spray Coating Process ETH Zurich Institute of Machine Tools and Manufacturing Thermal spray technology is used to coat critical parts in industrial machines and products, from turbine blades in jet engines to brake disks in automobiles to hard-chrome replacement, which require the highest achievable quality of the coating. Optimization of the thermal spray process to consistently achieve this high quality is challenging due to its stochastic, non-linear and transient behavior. Physical modelling is therefore at its limits, and data-driven techniques could be used to identify the process. The overall system can be divided into several sub-systems, and the input-output relationship in each subsystem can be estimated from data acquired at each stage with a data-driven approach using learning techniques in combination with empirical modeling. Control Engineering, Mechanical Engineering Bachelor Thesis, Master Thesis, Semester Project

Sleep Traits and Age: does our ‘Brain Fingerprint’ Remain? ETH Zurich Sensory-Motor Systems Lab From studies conducted with young adults and teenagers, we know that brain activity during sleep varies from person to person, but is very repeatable from night to night within one person. We want to know whether this “brain fingerprint” is also visible later in life. Biomedical Engineering, Developmental Psychology and Ageing, Medical and Health Sciences Master Thesis, Semester Project

Replicability in Agricultural Economics ETH Zurich Chair of Agricultural Economics and Policy D-MTEC The aim of this thesis is to understand and compare recent trends in replicability in agricultural economics journals. Agricultural, Veterinary and Environmental Sciences, Economics, Information, Computing and Communication Sciences ETH Organization's Labels (ETHZ), Master Thesis

Learning to Deblur Images with Events University of Zurich Robotics and Perception Explore machine learning based approaches for deblurring of images with events Computer Vision, Image Processing, Pattern Recognition Master Thesis, Semester Project

Simulation to Real World Transfer University of Zurich Robotics and Perception The project aims to develop techniques based on machine learning to have maximal knowledge transfer between simulated and real world on a navigation task. Intelligent Robotics Bachelor Thesis, Master Thesis, Semester Project