We aim to develop a reinforcement learning-based global excavation planner that can plan for the long term and execute a wide range of excavation geometries. The system will be deployed on our legged excavator. - Intelligent Robotics
- Master Thesis, Semester Project
|
Kyoto Institute of Technology in Japan + ETH Zurich. The project will explore the following topics of: 1) design for assembly and disassembly; 2) affordable installation manually and/or digitally with robots, as well as 3) efficient and cost-effective installation, using the case study of the Zero Carbon Building Systems (ZCBS) Lab located on the ETH Hoenggerberg Campus - Architecture, Urban Environment and Building
- Master in Integrated Building Systems (ETHZ), Master Thesis
|
The project aims to implement a semantic label transfer from satellite to aerial imagery in order to enable the training of image-based machine learning algorithms for autonomous aerial vehicle tasks, such as path planning, collision avoidance, and localization. - Computer Vision, Intelligent Robotics
- Semester Project
|
The global increase in temperature and humidity amplifies local impacts on livestock husbandry. Climatic extreme events like heat waves negatively affect milk producers, especially because cows experiencing heat stress may imply lower milk and milk component yields in Switzerland. This thesis uses rich data from swissherdbook and MeteoSwiss and provides causal estimates of temperature humidity shocks on milk production using an econometric analysis. Based on this assessment, the thesis quantifies its economic relevance, considering both quantity and price effects. Knowledge about climate change impacts on milk production provides highly relevant information for farmers and other stakeholders in the agricultural sector. - Agricultural, Veterinary and Environmental Sciences
- Master Thesis
|
The main goal of the project is development of an emulator of resonance cavities for beam acceleration. The emulator should be in a form of a stand-alone electronic box which can be connected to a Low Level Radio Frequency (LLRF) system for laboratory tests. Such platform should allow continuous studies of control algorithms and firmware/software of the LLRF systems without disturbing the real cavity operation. Such a platform would also be used for training of on-call duty staff without risk of damaging real high-power RF system. |
You will be part of the cross-departmental project that aims to develop the system for the activity calculations fulfilling the requirements of the Swiss authorities. One of the requirements of the project is producing the standard report according to the established form combining the multiple types of information about the calculation which are already available in the databases of the project.
You will get familiar with the underlying data structures, participate in the development of the standard report form, develop and implement the programming module for the automatic report generation using existing function libraries for the automatized document creation, and conduct activity calculations demonstrating the functionality of the newly created programming component.
- Engineering and Technology, Information, Computing and Communication Sciences
- Internship
|
The integration of renewable energy sources, such as photovoltaics, introduces stability issues to the power grid. Consequently, microgrids are becoming increasingly compelling as they are able to stay in operation during a power outage. The Battery Energy Storage System (BESS) ensures voltage and frequency stability of the microgrid in regular island grid operation. However, during transients, the BESS may reach its current limits and typically is then switched off as a safety precaution. The objective of this project is to devise a control strategy that guarantees voltage and frequency stability, while preventing the system from exceeding its current limits. - Engineering and Technology
- Master Thesis, Semester Project
|
The Abstraction and Reasoning Corpus (ARC) is like an IQ test for machine intelligence, allowing us to quantify progress towards human-level AI. It was introduced in 2019
by François Chollet as a Kaggle competition. Rather than focusing on a single specific challenge, the aim of ARC is to provide an ensemble of challenges to measure the ability
to handle and adapt to new unseen environments. One task of the ARC usually consists of three given samples with input and output pairs. For a fourth sample, only the input is given and the output must be produced. These challenges seem easy for humans to solve, however machines, at least for now, struggle with them a lot. The implicit assumption is that we humans can rely on existing ”priors” and knowledge that help us tackle these tasks.
We are interested in following up an approach which shows potential by combining both vision and language to build a learned end-to-end pipeline to solve ARC. - Artificial Intelligence and Signal and Image Processing
- Master Thesis
|
To advance the field of legged robots in low-gravity space applications, team SpaceHopper (https://spacehopper.ethz.ch/) plans to conduct a testing campaign on a parabolic flight in late 2023. For this test campaign, the robot needs to be equipped with a new battery concept that complies with the safety requirements on a ZeroG flight. - Aerospace Electrical Systems, Electrical Engineering, Mechanical Engineering
- Bachelor Thesis, Internship, Lab Practice, Semester Project
|
Digital capture of human bodies is a rapidly growing research area in computer vision and computer graphics that puts scenarios such as life-like mixed-reality (MR) virtual-social interactions into reach. Therefore, we offer projects for modeling and capturing humans at the intersection of computer vision, computer graphics, and machine learning. - Computer Graphics, Computer Vision, Virtual Reality and Related Simulation
- CLS Student Project (MPG ETH CLS), ETH Zurich (ETHZ), Master Thesis, Semester Project
|
