A new kind of gas-filled microbubble enables the detection of protease activity by using ultrasound imaging techniques. The main goal of this work is to develop a setup that can reliably be used to measure the stiffness of microbubbles, first in a microbubble solution, and then in a model built to simulate the vasculature of a mouse. - Electrical and Electronic Engineering
- Master Thesis, Semester Project
|
Optoacoustic (OA) imaging is a hybrid imaging method that enables deep tissue imaging with a high spatial resolution by combining optical illumination with ultrasound detection. The goal of this student project is to devise a parallel HW accelerator and explore different HLS code optimizations to achieve the best performance for OA image reconstruction on an FPGA in real-time.
- Biomedical Engineering, Electrical and Electronic Engineering
- Bachelor Thesis, Master Thesis, Semester Project
|
Designing a fishnet harvesting buoy to find and tag ghost nets at the ocean surface in a nature-driven way for ocean cleanup and marine plastic mining - Mechanical and Industrial Engineering
- ETH Zurich (ETHZ), Master Thesis
|
The main goal of this work is to develop a modular system for the characterization and tuning of ultrasonic transducers both in hard- and software
Due to the intended modularity of the system in soft- and hardware, we can guarantee a high flexibility of the setup. This means that the system can be adapted in operation for a wide variety of transducer types and setups. - Electrical Engineering
- Bachelor Thesis, Semester Project
|
This project aims to create a FPGA-based interface capable of streaming live data from a ETH-developed CMOS biosensor and monitor neuroactivity and cell cultures in real time - Biomechanical Engineering, Electrical Engineering
- Master Thesis, Semester Project
|
Vision-based reinforcement learning (RL) is more sample inefficient and more complex to train compared to state-based RL because the policy is learned directly from raw image pixels rather than from the robot state. In comparison to state-based RL, vision-based policies need to learn some form of visual perception or image understanding from scratch, which makes them way more complex to learn and to generalise. Foundation models trained on vast datasets have shown promising potential in outputting feature representations that are useful for a large variety of downstream tasks. In this project, we investigate the capabilities of such models to provide robust feature representations for learning control policies. We plan to study how different feature representations affect the exploration behavior of RL policies, the resulting sample complexity and the generalisation and robustness to out-of-distribution samples. - Intelligent Robotics
- Master Thesis, Semester Project
|
Vision-based reinforcement learning (RL) is often sample-inefficient and computationally very expensive. One way to bootstrap the learning process is to leverage offline interaction data. However, this approach faces significant challenges, including out-of-distribution (OOD) generalization and neural network plasticity. The goal of this project is to explore methods for transferring offline policies to the online regime in a way that alleviates the OOD problem. By initially training the robot's policies system offline, the project seeks to leverage the knowledge of existing robot interaction data to bootstrap the learning of new policies. The focus is on overcoming domain shift problems and exploring innovative ways to fine-tune the model and policy using online interactions, effectively bridging the gap between offline and online learning. This advancement would enable us to efficiently leverage offline data (e.g. from human or expert agent demonstrations or previous experiments) for training vision-based robotic policies. - Intelligent Robotics, Robotics and Mechatronics
- Master Thesis
|
Model-based reinforcement learning (MBRL) methods have greatly improved sample efficiency compared to model-free approaches. Nonetheless, the amount of samples and compute required to train these methods remains too large for real-world training of robot control policies. Ideally, we should be able to leverage expert data (collected by human or artificial agents) to bootstrap MBRL. The exact way to leverage such data is yet unclear and many options are available. For instance, it is possible to only use such data for training high-accuracy dynamics models (world models) that are useful for multiple tasks. Alternatively, expert data can (also) be used for training the policy. Additionally, pretraining MBRL components can itself be very challenging as offline expert data is typically sampled from a very narrow distribution of behaviors, which makes finetuning non-trivial in out-of-distributions areas of the robot’s state-action space. In this thesis, you will look at different ways of incorporating expert data in MBRL and ideally propose new approaches to best do that. You will test these methods in both simulation (simulated drone, wheeled, legged) and in the real world on our quadrotor platform. You will gain insights into MBRL, sim-to-real transfer, robot control. - Intelligent Robotics, Knowledge Representation and Machine Learning, Robotics and Mechatronics
- Master Thesis, Semester Project
|
Driver state detection systems will become mandatory in many countries in this decade. In this thesis, you will use a unique multi-sensor dataset with 55 drivers collected by us in a in a real car on a test track to develop a ML drunk driving detection algorithm. - Engineering and Technology, Information, Computing and Communication Sciences, Mathematical Sciences
- Master Thesis
|
The aim of the project is to generate synthetic LGE CMR images from ground truth segmentation masks using a conditional GAN. - Biomedical Engineering, Computer Vision, Image Processing, Simulation and Modelling
- Bachelor Thesis, Semester Project
|