Project Objective:
This project aims to develop a new method to integrate depth perception into robots.
Specifically we are tackling the task of navigation and locomotion for our legged robot ANYmal.
Instead of training RL policies from scratch, we would like to understand the potential performance impacts by using self-supervised training, e.g. using DINO, for monocular depth images. The training may consist of leveraging existing datasets and focuses on learning a useful representation that includes not only geometric hints but potentially also semantic information from depth analog to the recent advantages achieved using RGB images.
- Computer Hardware, Computer Perception, Memory and Attention, Computer Software, Computer Vision, Electrical and Electronic Engineering
- Master Thesis, Semester Project
|
This project aims to develop different action recognition models for assembly tasks and compare the effects of depth information and/or hand/object poses. A further investigation could be utilizing synthetic data to train the model, which can significantly improve the adaptation ability. It could be extended to a publication if the progress is good. - Computer Vision, Engineering and Technology
- Master Thesis, Semester Project
|
The scale-up of extrusion processes like high-moisture extrusion from small bench-top extruders to large industrial-scale extruders remains challenging. This is especially true for high-moisture extrusion since the structuring mechanisms in the cooling die connected to the extruder have not been fully understood to date.
We are looking for a candidate who is highly motivated to work in a collaborative project with industry that aims at a better understanding the scale-up of high-moisture extrusion for plant-based meat analogs. The definition of structural parameters to quantify the quality of meat analogues is of particular interest. The project will rely on a close collaboration with the whole ETH team and the industry partners Bühler and ThermoScientific.
Our rheology and scalable extrusion platforms will serve as the fundamental toolbox for the project. - Engineering and Technology
- ETH Zurich (ETHZ), Master Thesis
|
This thesis aims to develop a dexterous robot assembly system. Given components randomly put on the table and the final target, the goal is to generate physics-based motions to grasp the components and put them in the right place with the right order. Specifically, it will utilize reinforcement learning (RL) to train low-level skills (grasping, relocating, dropping) in physics simulation, and use large language models (LLMs) as a high-level planner.
- Computer Vision, Engineering and Technology, Intelligent Robotics
- Master Thesis, Semester Project
|
This project aims to innovate material development by utilizing a round swage forging machine to produce novel alloys and composites. The focus is on producing rods and wires that meet the size specifications for Ultrasonic Plasma Atomizer (UPA) and Directed Energy Deposition (DED) technologies. The project involves designing tool sets for precise forging, producing new aluminum alloys by mixing Al and Ti powders, and potentially integrating carbide powders to enhance material properties. Key objectives include mastering small-scale wire and rod production, understanding aluminum extrusion and alloying processes, and demonstrating the ability to manipulate material hardness. - Alloy Materials, Manufacturing Engineering
- Bachelor Thesis, Semester Project
|
We are working toward robots that transform their shape adapt to new tasks and environments.
This project will entail developing control policies in simulation and deploying them on hardware, with the goal of controlling a quadruped that can change the shape of its legs to accomplish new and useful tasks (see attached image a). - Intelligent Robotics, Robotics and Mechatronics, Simulation and Modelling
- Master Thesis, Semester Project
|
Every day, our skin undergoes deformations that lead to changes in chemical and pressure potentials, resulting in substantial variations in osmotic pressure, and local substrate stiffness. In vivo is not possible to decouple the effect of osmotic pressure and change of stiffness from the deformation of skin, so our idea is to create a model able to control all of them in an independent way. The connections between these two mechanical signals remain unclear. Human dermal fibroblast (HDF) mechanobiology is crucial for understanding tissue homeostasis and repair, as fibroblasts maintain the extracellular matrix (ECM) and tissue integrity. This study explores how osmotic pressure and substrate stiffness affect fibroblast behavior. Using varying stiffness and sorbitol-induced osmotic stress, we observed that substrate stiffness may modulate fibroblast responses to osmotic pressure, with significant metabolic changes at intermediate stiffness levels. Our goal is to create a precise model to tune mechanical signals, reproduce the skin environment, and understand if the combination of stimuli can amplify or attenuate biological responses compared to individual signals alone. - Biomedical Engineering
- Master Thesis
|
Wavemap is a multi-resolution volumetric mapping framework. By integrating its 3D maps with RL pipelines, we want to enable robots to navigate in complex environments. Future semantic support will enable advanced applications like urban navigation and safe traversal of hazardous terrains. - Intelligent Robotics
- Master Thesis
|
The Laboratory of Orthopedic Technology has recently developed a novel joint implant and is undergoing optimization of the manufacturing process. We are looking for a master's student who is passionate about medical devices and mechanical design to join us for a semester project.
Objectives:
• Design different molds for material casting using SolidWorks or Fusion 360.
• Optimize implant design using matlab or Python.
• Mechanical testing of the implant including fatigue test.
Your Profile:
• Strong knowledge in mechanical design and drawing skills.
• Hands-on and detail-oriented.
• Experience with SolidWorks or Fusion 360, as well as Python or Matlab. - Biomechanical Engineering
- ETH Zurich (ETHZ), Semester Project
|
The Laboratory of Orthopedic Technology at ETH Zurich is currently optimizing the manufacturing process for a novel joint implant. We are looking for a master's student who is passionate about medical devices and polymer science to join our team for a semester project or master's thesis.
Project Focus: The selected candidate will work on optimizing the performance of a hydrogel material that is a key component of the cartilage replacement implant. The project will involve:
• Investigating polymer synthesis and formulation techniques to enhance hydrogel performance.
• Developing testing protocols to evaluate the hydrogel’s effectiveness in mimicking natural cartilage behavior.
- Organic Chemical Synthesis
- ETH Zurich (ETHZ), Master Thesis, Semester Project
|
