Focus Projects
In a focus project, students develop and build a product from A-Z! They will be working in teams, where they learn how to structure problems and identify solutions to them, system analysis and simulation, as well as presentation and documentation techniques.
Furthermore, the students will build the product with access to rapid prototyping facilities, a machine shop, and state of the art engineering tools (Matlab, Simulink, CAD, CAE, PDM). Below, you can find a description of the currently offered focus projects.
'22-'23: Project SURF-eDNA
The rapidly changing climate and overfishing has caused harm to marine habitats and their biodiversity. To understand these changes marine scientists - like Prof. Loïc Pellissier at ETH - survey populations and build environmental models on collected data. Data collection is primarily done by humans and camera traps, limiting data density. Sparse data makes establishing population models harder and the outcome less precise, so an autonomous collection method that does not interfere with the wildlife would be sought after. Our project aims to solve automatic marine data collection by applying recent advances in underwater soft robots. We would construct a modified version of Prof. Dr. Robert Katzschmann’s robotic fish, SoFi, that can autonomously collect data, namely, HD video and eDNA traces - without disturbing wildlife. Prof. Pellisier’s lab would provide us with filters and the means of evaluating the eDNA. Thus, our robot would carry a filtering device and a camera around a given trajectory. It would then periodically resurface, so that the data can be retrieved, and the batteries are recharged.
'22-'23: Project MetaSuit
Augmented reality (AR) and virtual reality (VR) experiences will play an important role in the coming decade. Technology companies such as Meta, Alphabet, and Microsoft are investing heavily in virtual-reality spaces in which users can interact with a computer-generated environment (e.g., Metaverse). These developments depend on AR and VR hardware, which have recently entered the mass market and are becoming affordable to a wider audience. Pose estimation of the user and therefore the ability to naturally interact with the virtual world is still a challenge. Current systems are based on handheld devices or vision based pose sensors. This hinders adoption and usage outside of predefined AR/VR spaces. This project will investigate new sensor designs based on capacitive electrostatic actuators. These will be inexpensive and fast to manufacture as well as safe to interact with. In addition, the project will investigate and miniaturize the readout electronics for the sensor. This sensor should result in a modular, easily adaptable sensor system that can be embedded in clothing. The
result of this project will be a sensorized piece of clothing that allows for pose estimation. It should be comfortable to wear for a long time, not hinder natural motion, and cheap and fast to manufacture. We imagine that as a final result the students will present a wearable piece of clothing that can be used in an AR and VR setting.
'21-'22: Project RAPTOR
In this focus project, you will develop the platform RAPTOR. The acronym stands for "Rapid Aerial Pick and Transfer of Objects by a Robot". Together with your team, you design, build and test a flying platform that swoops down towards an object to dynamically pick it up, just like an eagle swoops down to pick up its prey.
The flying system will consist of a soft robot gripper attached to a quadcopter or vertical take-off and landing (VTOL) aircraft. The team's design will first be tested in simulation using tools including Matlab, Gazebo, Drake, and the soft robotics simulator SOFA. A testbed made out of a five bar linkage will facilitate the testing of the design and control of the soft gripper. The testbed emulates quadcopter trajectories on a plane. The testbed will validate the robustness of our gripping experiments in simulation. Successful designs and control algorithms will eventually be tested on a dynamically maneuverable aerial vehicle with self-built gripper.
If you like to see the project slides or learn more about this project, please email .
