Minimal is a mostly 3D-printed, highly reconfigurable robot. Using state-of-the-art reinforcement learning, we will explore novel and highly advanced hardware design possibilities that will be coupled with design optimization through learning. This will enable the next generation of robots to be a lot faster, stronger and agile. - Engineering and Technology
- Master Thesis, Semester Project
|
The aim of this project is to implement and test different T1ρ measurement approaches using MR simulations and measurements. - Biomedical Engineering, Medical Physics
- Bachelor Thesis, Semester Project
|
We want to develop a generalist digging agent that is able to do multiple tasks, such as digging and moving loose soil, and/or control multiple excavators. We plan to use decision transformers, trained on offline data, to accomplish these tasks. - Intelligent Robotics
- Master Thesis, Semester Project
|
The accumulation of metals in tissues can either contribute to or arise from metabolic disorders, resulting in supraphysiological concentrations of deleterious species within organs and tissues. Chronic metal overload can lead to organ failure and arthritis, while in the short term is proinflammatory and complicates wound healing. - Biomaterials, Chemical Engineering, Chemistry
- Bachelor Thesis
|
The traveling velocity of Swiss pendolino reaching 250 km/h creates both aerodynamic noise
as well as noise from the train wheel – track interaction. Corrundum grinding wheels are
widely used in industry for maintaining rail tracks and acoustic grinding. Rolling noise
contributes significantly to the overall acoustic pollution, whereby correlation between track
surface quality and noise emission could be detected and needs to be improved.
It is a challenge to measure the rail roughness from the train, to monitor the condition of the
rail network at a high speed. For this purpose, an optical measurement system is to be developed which can measure the
rail roughness contact-free. A possible additional topic is the detection of rail defects using
machine learning. From design to performing experiments to data processing or data storage
strategies, a variety of thesis topics are possible. - Mechanical Engineering
- Bachelor Thesis, Semester Project
|
The project focuses on optimizing the compact Marx generator, which charges capacitors in parallel and discharges in series to produce high-voltage pulses. Through FEM simulations, the objective is to design capacitor arrangements that limit the electrical field, mitigating equipment failures, and extracting parasitic elements. - Electrical Engineering
- Semester Project
|
In this project, you will investigate how to design appropriate geometries for spark gaps and extract the electrical parasitic elements. You will create a parametrized simulation linking Matlab and COMSOL to optimize the parasitic elements. - Electrical Engineering
- Master Thesis, Semester Project
|
Searching for specific objects within a confined space requires advanced spatial and perceptual reasoning. In this project, we want to develop a learning-based system that finds a desired object in a cluttered scene efficiently and safely. - Computer Vision, Knowledge Representation and Machine Learning, Learning, Memory, Cognition and Language
- Master Thesis
|
In this project, you will design a DC-DC converter, including soft start control, losses estimation, and external interfaces. You will use Matlab for calculations, PLECS for simulations, and Altium create the design of the PCB device. Then you will analyze the practical results. - Electrical Engineering
- Master Thesis, Semester Project
|
Model-based state estimation for locomotion has shown some significant drawbacks, especially in the case of complex contact scenarios. At the same time, locomotion controllers are evolving, now purposely using knee contacts or wheel slippage for advanced motions. The current model-based state estimation techniques often cannot supply sufficiently accurate observations for these controllers, leading to major estimation drifts and thus potential failures. In this project, we aim to leverage learning-based methods not only for locomotion control, but also for state estimation. Preliminary work shows that creating a state estimation through supervised learning from recorded simulation data can produce a viable solution. Furthermore, fusing these approaches with classical filtering theory opens a promising realm of research. The project should also compare the developed methods with existing approaches on real hardware. If time permits, we are interested in learning state estimation and locomotion jointly. - Intelligent Robotics, Robotics and Mechatronics
- Master Thesis, Semester Project
|