**SiROP is an exclusive network of leading universities in science and technology**
Why join SiROP?
- Hundreds of open positions readily available online
- Direct contact and easy application procedure without any bureaucracy
- PhD positions, MSc, BSc, and internships in Computing Sciences. **SiROP is an exclusive network of leading universities in science and technology**
Why join SiROP?
- Hundreds of open positions readily available online
- Direct contact and easy application procedure without any bureaucracy
- PhD positions, MSc, BSc, and internships in Computing Sciences. Profit from a great search interface and directly apply to the position of your choice. SiROP - Excellence in Science! Profit from a great search interface and directly apply to the position of your choice. SiROP - Excellence in Science! Selection of open positions in **Computing Sciences** Selection of open positions in **Computing Sciences** Three-dimensional (3D) reconstruction of dynamic scenes, particularly those involving humans interacting with their environment, remains a challenging problem in computer vision and graphics. Traditional volumetric and mesh-based methods can struggle with occlusions, complex geometries, and real-time performance. Recent advances in neural rendering—especially Gaussian splatting—offer promising alternatives by representing scenes as clouds of oriented 3D Gaussians (“splats”) that can be rendered extremely efficiently. The goal of this project is to develop a novel pipeline that leverages Gaussian splatting to reconstruct, analyze, and interpret human–scene interactions in 3D. - Computer Vision
- Master Thesis, Semester Project
| Noisy signals, scarce labels, and black-box models hinder EEG-based BCIs for imagined speech and limb movement. We will tackle these issues with hybrid convolution-transformer networks—CTNet (github.com/snailpt/CTNet) and MSCFormer (github.com/snailpt/MSCFormer)—augmented by transfer learning and few-shot adaptation. Attention heat-maps and SHAP explanations (github.com/slundberg/shap) will expose which channels and time windows drive each decision. The work aligns with ViTFOX’s goal of low-power, explainable neuro-AI (vitfox.eu). - Engineering and Technology, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition, Signal Processing, Speech Recognition
- Collaboration, ETH Zurich (ETHZ), Master Thesis, Semester Project
| Silent-speech interfaces decode spoken content from muscle activity when no sound is produced. Surface electromyography (sEMG) offers a non-intrusive signal source but suffers from low SNR and large user variability. We propose a transformer-based pipeline that classifies silently mouthed words from multi-channel sEMG. We propose a rigorously benchmarked, transformer-based decoding pipeline that treats multi-channel sEMG as a structured time series and learns rich, long-range dependencies inaccessible to conventional CNN- or RNN-based systems. - Behavioural and Cognitive Sciences, Engineering and Technology, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition, Signal Processing
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| Emerging ferroelectric resistive / capacitive devices can store analog synaptic weights and update them in situ, eliminating the memory-processor traffic that dominates AI energy budgets. We will build the first hardware-in-the-loop prototype that learns online with such devices, combining a mixed-precision supervised rule (Tiki-Taka) and a bio-inspired Hebbian rule. The demonstrator will show that continual learning on ferroelectric IMC arrays achieves software-class accuracy while slashing update energy, opening a path toward self-adapting edge hardware. - Artificial Intelligence and Signal and Image Processing, Electrical and Electronic Engineering, Memory Structures, Nanotechnology
- Bachelor Thesis, Collaboration, ETH Zurich (ETHZ), Master Thesis, Semester Project
| This master's thesis aims to develop a model-based optimal control strategy to accelerate the measurement process on a turbocharger gas-flow testbench. By modeling the temperature dynamics of the testbench and turbocharger housing, and identifying parameters from existing data, the project will enable faster transitions between operating points. The optimized control strategy will be compared to current methods, and additional focus will be placed on minimizing overall measurement time by optimizing the sequence of test points. The work supports Accelleron's efforts in efficient turbocharger characterization. - Mechanical and Industrial Engineering, Simulation and Modelling
- Master Thesis
| This internship offers practical research experience in speech and audio-based AI at the University of Zurich’s KrauthammerLab. The focus is on building systems that can understand and generate spoken language in natural and expressive ways. - Computer-Human Interaction, Speech Recognition
- Internship
| TLDR: Improving navigation capabilities of ANYmal - RL is simulation - optimizing learning progress. - Computer Hardware, Computer Perception, Memory and Attention, Computer Vision, Electrical Engineering, Intelligent Robotics, Robotics and Mechatronics
- Master Thesis, Semester Project
| We are looking for a highly motivated MSc student in computer science to help us developing a fully functional research prototype for Mueller polarimetric imaging (MPI) system to be employed on human tissues for surgical analyses, feedback and visualisations. The development will be supervised by PD Dr. Richard McKinley, in strong collaboration with the NVIDIA Holoscan Team.
This is a unique internship opportunity to bridge the gap between academia and industry within a fully translational research project in collaboration with Inselspital and University of Bern. - Information, Computing and Communication Sciences
- Internship, Semester Project
| Explore online fine-tuning in the real world of sub-optimal policies. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| As autonomous vehicles become more prevalent, the role of roadside infrastructure sensors—such as cameras and LiDARs mounted on traffic lights, intersections, or poles—grows increasingly important. Unlike onboard sensors, infrastructure sensors offer a bird’s-eye view and can provide critical perception support for traffic participants. However, standard evaluation metrics like mean Average Precision (mAP) fail to capture how well these systems work under real-world variability in road types, weather conditions, sensor placement, and object orientation. In this project, we aim to develop probabilistic models that predict the object detection performance of sensors mounted on roadside infrastructure. - Automotive Engineering, Information, Computing and Communication Sciences, Mathematical Sciences, Mechanical and Industrial Engineering
- Bachelor Thesis, Master Thesis
| Use Inverse Reinforcement Learning (IRL) to learn reward functions from previous expert drone demonstrations. - Engineering and Technology, Intelligent Robotics
- Master Thesis, Semester Project
| Design and implement efficient event-based networks to achieve low latency inference. - Computer Vision
- Master Thesis, Semester Project
| Recent advances in neural scene reconstruction, such as Neural Radiance Fields (NeRF) and Gaussian Splatting, have significantly improved the performance of downstream tasks, including novel view synthesis and geometric reconstruction. Building on these innovations, multi-modal approaches have been explored to incorporate additional scene attributes such as depth, surface normals, thermal data, and semantic information to enrich existing scene representations. However, current multi-modal methods often rely on a tightly coupled correspondence between RGB data and other modalities, which limits their applicability in uncontrolled, real-world scenarios. - Computer Graphics, Computer Vision, Virtual Reality and Related Simulation
- Master Thesis, Semester Project
| This project aims to collect diverse forehead PPG datasets using a newly developed device, to evaluate variability across populations and sensor placements and, to explore their impact on signal quality. You will apply classical signal processing and machine learning methods to extract reliable MRI triggers from the PPG signal to statistically quantify the pulse arrival time (PAT) and its variability. If time permits, you may further investigate the extraction of respiratory-modulated components from the PPG waveform. - Artificial Intelligence and Signal and Image Processing, Biomechanical Engineering, Electrical Engineering, Optometry
- Bachelor Thesis, Semester Project
| Diffusion models (DDPMs) have revolutionised generative modelling, surpassing GANs in images, advancing audio synthesis, and enabling de-novo protein design. Yet progress on time series lags behind early adversarial work. Recent studies highlight the benefits of spectral biases - FourierFlow and frequency-domain DDPMs.
In parallel, diffusion in the wavelet domain has emerged for images, offering a multi-resolution view well-suited to non-stationary signals. Wavelets capture localised, scale-dependent features, making them attractive for domains from finance to climate and biomedical data such as ECGs.
This project proposes the first DDPM framework operating directly in the wavelet domain for time series, aiming to improve generalisation, interpretability, and robustness across diverse sequential tasks. - Artificial Intelligence and Signal and Image Processing, Statistics
- ETH Zurich (ETHZ), Master Thesis
| Develop a plugin for the Jupyter-based AiiDAlab Quantum ESPRESSO app focused on calculating the work function of material surfaces. Ideal for students aiming to apply their coding skills and scientific knowledge to contribute to scientific software in material science research. - Software Engineering, Theoretical and Condensed Matter Physics
- Master Thesis, Semester Project
| This project uses Visual Language Models (VLMs) for high-level planning and supervision in construction tasks, enabling task prioritization, dynamic adaptation, and multi-robot collaboration for excavation and site management.
prioritization, dynamic adaptation, and multi-robot collaboration for excavation and site management - Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| Reconstructing time-varying graph signals is a critical challenge in graph machine learning and graph signal processing, with various applications such as missing data imputation in sensor networks and time-series forecasting. Effectively addressing these tasks requires accurately capturing the spatio-temporal information inherent in these graph signals. Current methods, however, often rely exclusively on either graph signal processing methods or graph neural networks, limiting their ability to fully leverage the strengths of both approaches. This project aims to develop a new model for time-varying graph signal reconstruction, integrating the inductive bias from graph signal processing to graph neural networks. - Artificial Intelligence and Signal and Image Processing
- Semester Project
| We will explore the design space of avatars in Virtual Reality to support learning and creativity. The project will leverage the concept of "embodied cognition", a set of theories that imply that our bodies and their interaction with the environment can impact how we learn. We will develop a Unity3D-based VR environment for embodied learning that can be deployed on everyday VR headsets. - Computer Graphics, Computer-Human Interaction
- Master Thesis, Semester Project
| Our project aims to enhance the ultrasound-assisted bioprinting process using real-time feedback and image processing. We have developed a transparent nozzle equipped with multiple cameras for real-time monitoring. The next steps involve integrating advanced image processing techniques, such as template matching, and implementing a feedback system to optimize the printing process. The system will be fully automated, featuring a function generator for wave creation and cooling elements. By analyzing the printing process and acoustic cell patterning with computer vision and leveraging real-time sensor feedback, we aim to dynamically optimize parameters such as frequency and amplitude for accurate and consistent pattern formation, crucial for bio applications. - Artificial Intelligence and Signal and Image Processing, Behavioural and Cognitive Sciences, Computation Theory and Mathematics, Computer Software, Engineering and Technology, Information Systems, Medical and Health Sciences
- Bachelor Thesis, Master Thesis
| Enable Birds-Eye-View perception on autonomous mobile robots for human-like navigation. - Computer Vision, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition, Photogrammetry and Remote Sensing
- ETH Zurich (ETHZ), Master Thesis
| Elevate semantic scene graphs to a new level and perform semantically-guided navigation and interaction with real robots at The AI Institute. - Computer Vision, Engineering and Technology, Intelligent Robotics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition
- ETH Zurich (ETHZ), Master Thesis
| Functional traits describe biophysically relevant properties of plants and form an important basis for understanding ecosystem dynamics and the Earth system. Planttraits.earth has recently produced global high-resolution maps of many plant traits (some of which have never before been mapped globally), by combining field data from plant scientists, crowd-sourced data from citizen scientists, and remote sensing imagery. The present project will develop methods to improve those maps and bring plant trait mapping to the next level. - Ecology and Evolution, Information, Computing and Communication Sciences, Photogrammetry and Remote Sensing
- Master Thesis, Semester Project
| Are you interested in uncovering how Alzheimer’s disease disrupts communication in the brain — and exploring new ways to study and possibly intervene in this process?
In this project, you will use cutting-edge microfluidic platforms to construct bioengineered neural networks that better mimic the structure and function of brain microcircuits. These networks, established from human iPSC-derived neurons, will be studied throughout their development using high-density microelectrode arrays (HD-MEAs), enabling detailed tracking of their electrical activity at high spatiotemporal resolution.
You will introduce Alzheimer’s disease-related pathology into the networks and investigate how it alters connectivity, signaling patterns, and neural responses to stimulation over time.
The project offers a unique opportunity to combine experimental work in cellular neuroscience with computational analysis of neural network function. Depending on your background and interests, your work can be directed more toward wet-lab techniques (e.g., cell culturing, immunostaining, confocal imaging, electrophysiology) or toward data analysis and modeling (e.g., signal processing, graph theory, information theory).
- Analysis of Algorithms and Complexity, Biomedical Engineering, Biophysics, Biosensor Technologies, Biotechnology, Electrical and Electronic Engineering, Medical Biotechnology, Nanotechnology, Neurosciences, Systems Biology and Networks
- Bachelor Thesis, ETH Zurich (ETHZ), Master Thesis, Semester Project
| This thesis investigates the use of generative diffusion models for estimating Digital Surface Models (DSMs) with at least relative surface height from a single RGB image. While DSMs are traditionally derived from stereo imagery, monocular estimation offers a lightweight alternative for applications where only single-view input is available. Building on recent advances in monocular depth estimation, such as DepthAnythingV2 and Marigold, this work explores whether diffusion-based approaches can effectively bridge the gap between relative depth predictions and real-world surface structure. - Information, Computing and Communication Sciences, Photogrammetry and Remote Sensing
- Bachelor Thesis, Master Thesis, Semester Project
| Predicting the failure mechanisms of low-density cellular solids, from random fiber networks to periodic
architected materials (or metamaterials), remains a challenge for computational mechanics. One fundamental
distinction between beam-based architected materials and classical homogeneous solids lies in
the nature of their failure. Unlike classical materials, beam-based architected materials fail through the
discrete breaking of individual beams. This results in complex patterns of crack initiation and propagation,
that are significantly different from those observed in classical materials.
As computational models for large-scale, manufacturable metamaterials often involve millions or even
billions of unknowns, we are developing an open-source C++ library for scalable finite element simulations.
Currently, this library leverages distributed computing on CPUs via Open MPI, utilizing ETH
Zurich’s Euler cluster. The goal of this project is to improve simulation performance for predicting failure
in large-scale beam networks. A key focus will be integrating Nvidia’s GPU accelerators to achieve
significantly enhanced computational efficiency beyond what distributed CPU computing alone can provide.
Throughout this project, the student will contribute to an open-source project, conduct in-depth
performance studies, and utilize the developed software to predict fracture behavior in novel materials
with different (multi-)material properties, including both linear elastic and plastic regimes. - Mechanical Engineering, Numerical Analysis
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| This project focuses on developing autonomous robots for synchronized performances on water. Equipped with kinetic water fountains, RGB lighting, and ultrasonic mist generators, the robots are designed to execute planned choreographies. The system utilizes robotics control, wireless communication, and positioning technologies to coordinate movements, and payload activation, facilitating complex pattern generation and synchronization. The objective is to advance the application of distributed robotic systems in creating structured and cohesive visual displays on water. - Arts, Engineering and Technology, Information, Computing and Communication Sciences
- Bachelor Thesis, Master Thesis, Semester Project
| This thesis aims to bridge the gap between human decision-making under uncertainty and artificial intelligence. Building upon recent neuroimaging research from our group on how the human brain processes probability and uncertainty of motivational events, this project will investigate whether meta-reinforcement learning (meta-RL) models can accurately replicate these complex neural computations and match human performance on a specific Pavlovian task. Ultimately, the goal is to understand the similarities and differences in how AI and biological intelligence handle learning and decision-making in uncertain environments. - Computer Perception, Memory and Attention, Neurocognitive Patterns and Neural Networks, Neurosciences, Simulation and Modelling
- Master Thesis
| In this project, you are going to work with a state-of-the-art deep learning approach and generative models for building an efficient system to directly reconstruct a 3D animatable avatar from a single image.
Feel free to contact me for more details.
- Information, Computing and Communication Sciences
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| Household energy consumption patterns, accounting for ~25% of European electricity demand, play a pivotal role in demand flexibility to support the grids under increasing intermittent renewable generations. The specific patterns of household appliance usage and time preferences can be the complex consequence of asset and facility conditions, household economic status, resident occupational and recreational lifestyles, and local social-organizational context. We have also been working towards integrating household energy models with socio-economic survey data to emulate these complex and heterogeneous patterns. Agent-based modeling (ABM) via large language models (LLMs) is a promising approach to reflect individual household properties and simulate complex human-like reasoning, behavioral adaption, and interactions in this process via LLM. In this project, we will leverage existing LLM-agent frameworks to simulate Swiss households’ energy behavior using our collected demographic and time-use survey data, and gain understanding of populational behavioural shifts & individual reactions to different demand response policy and extreme weather scenarios. - Civil Engineering, Simulation and Modelling
- Master Thesis, Semester Project
| Tree species maps are crucial for effective forest management, biomass assessment, and biodiversity monitoring. Remote sensing products offer flexible and cost-effective ways to assess forest characteristics, while deep learning methods promise high predictive accuracy and transformative applications in forestry. This study aims to apply novel deep learning approaches to detect and identify individual trees and tree species in mixed forests. By addressing the challenges of tree species identification, this research will enhance biodiversity assessment, forest resilience understanding, and management strategies. - Artificial Intelligence and Signal and Image Processing, Forestry Sciences, Geomatic Engineering
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| The project aims to create a controller for an interesting and challenging type of quadrotor, where the rotors are connected via flexible joints. - Control Engineering, Flight Control Systems, Intelligent Robotics, Systems Theory and Control
- Master Thesis, Semester Project
| Fracture surfaces in rock cores contain valuable structural information crucial for geological interpretation, engineering design, and are commonly mapped and analyzed by geologists. With advancements in camera technologies and computational techniques, it is now possible to digitize these surfaces in high resolution and apply automated methods for fracture analysis. - Computer Vision, Geology, Image Processing, Photogrammetry and Remote Sensing
- Bachelor Thesis, Master Thesis, Semester Project
| This project aims to use vision-based world models as a basis for model-based reinforcement learning, aiming to achieve a generalizable approach for drone navigation. - Computer Vision, Intelligent Robotics, Simulation and Modelling
- Master Thesis, Semester Project
| We aim to learn vision-based policies in the real world using state-of-the-art model-based reinforcement learning. - Computer Vision, Flight Control Systems, Intelligent Robotics
- Master Thesis, Semester Project
| The Dynamic and Distributed Information Systems Group at the University of Zurich is looking for motivated applicants who are interested in investigating how news recommender systems can have a more diverse coverage of recommended items from a societal perspective, be fair and transparent, and provide more control to users using modern technologies such as generative AI. - Computer-Human Interaction
- PhD Placement
| The Dynamic and Distributed Information Systems Group at the University of Zurich is looking for motivated applicants who are interested in developing personalized news recommender systems using generative AI technology. - Computer-Human Interaction
- PhD Placement
| The student will be involved in the development of software applications for in-vitro neural interfaces. The ultimate goal is controlling a complex embedded system, comprising a custom-made CMOS neural interface and two system on a chip. - Electrical Engineering, Engineering/Technology Instrumentation, Mathematical Software, Programming Languages, Programming Techniques, Software Engineering
- Bachelor Thesis, Internship, Master Thesis, Semester Project
| Improving volume control precision and robustness in automated pipetting remains a challenge, often limited by traditional indirect methods. This project explores direct volume control by leveraging internal air pressure measurements and the ideal gas law. Key obstacles include friction, pressure oscillations, varying liquid viscosities, evaporation, and liquid retention. Collaborating with Hamilton Robotics, the goal is to develop a robust control architecture for their precision pipette (MagPip) suitable for diverse liquids. The approach involves mathematical modeling based on sensor data, designing robust control strategies to handle nonlinearities and disturbances, and validating through simulation and real-world experiments. - Control Engineering, Systems Theory and Control, Systems Theory and Control
- Semester Project
| In this project, you will explore how cells generate mechanical forces using confocal traction force microscopy (cTFM). The project combines experimental techniques, such as cell culturing, quantum dot array printing, and live-cell confocal imaging, together with computational data analysis using the open-source tool Cellogram. By growing cells on deformable substrates and tracking the displacement of fluorescent quantum dots, students will quantify the traction forces that individual cells exert on their environment. - Biology, Engineering and Technology, Information, Computing and Communication Sciences
- Bachelor Thesis, Master Thesis, Semester Project
| We are looking for a research assistant who is skilled at data collection, cleaning, matching and programming. Please see details in the attachment. - Programming Languages
- Student Assistant / HiWi
| This research project aims to develop and evaluate a meta model-based reinforcement learning (RL) framework for addressing variable dynamics in flight control. - Artificial Intelligence and Signal and Image Processing, Engineering and Technology
- Master Thesis
| Object search is the problem of letting a robot find an object of interest. For this, the robot has to explore the environment it is placed into until the object is found. To explore an environment, current robotic methods use geometrical sensing, i.e. stereo cameras, LiDAR sensors or similar, such that they can create a 3D reconstruction of the environment which also has a clear distinction of 'known & occupied', 'known & unoccupied' and 'unknown' regions of space.
The problem of the classic geometric sensing approach is that it has no knowledge of e.g. doors, drawers, or other functional and dynamic elements. These however are easy to detect from images. We therefore want to extend prior object search methods such as https://naoki.io/portfolio/vlfm with an algorithm that can also search through drawers and cabinets. The project will require you to train your own detector network to detect possible locations of an object, and then implement a robot planning algorithm that explores all the detected locations. - Intelligent Robotics, Robotics and Mechatronics
- Master Thesis
| Explore the use of large vision language models to control a drone. - Engineering and Technology, Intelligent Robotics
- Master Thesis, Semester Project
| Join us in revolutionizing brain imaging technologies and make it accessible for everyday use. Functional near-infrared spectroscopy (fNIRS) is an emerging technology that enables cost-effective and precise brain measurements, helping to improve neurotherapies and brain health. - Electrical Engineering, Mechanical and Industrial Engineering, Neurology and Neuromuscular Diseases, Neurosciences, Signal Processing
- Internship
| We are currently looking for Master’s students with background in machine learning (or related computational field) for a project on Protein Fitness Optimization. - Artificial Intelligence and Signal and Image Processing, Computational Structural Biology
- Master Thesis, Semester Project
| This project aims to develop a deep learning model to automate the identification of DNA replication intermediates (RIs) in high-resolution Transmission Electron Microscopy (TEM) images—a process currently reliant on manual review. Leveraging a rich dataset from the Lopes lab at the University of Zurich, the model will classify image tiles containing RIs and rank them by prediction confidence to streamline analysis. The project also includes implementing interpretability tools to uncover features associated with RIs. It is ideal for candidates with strong computational skills, experience in deep learning (e.g., PyTorch or TensorFlow), and an interest in interdisciplinary research at the interface of biology and AI. - Electronmicroscopy, Genome Structure, Image Processing, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Protein Targeting and Signal Transduction, Systems Biology and Networks
- Internship, Master Thesis
| Are you interested in what a cell look like in nanometer scale? Do you want to see how the cell behaves in real time?
Scanning ion conductance microscopy (SICM) is the non-contact SPM technology to image live cells based on glass capillaries with a nanometric aperture. It applies a voltage and measures the ionic current flowing through the pipette above the sample in the buffer solution: the recorded current represents the feedback signal to measure the topography of the sample. This project aims to characterize a state of the art high-speed SICM to enable time-resolved live cell imaging, and do the live cell imaging on human primary keratinocytes to study the related disease. - Biomedical Engineering, Electrical and Electronic Engineering, Information, Computing and Communication Sciences, Manufacturing Engineering, Mechanical Engineering, Nanotechnology
- Master Thesis
| The goal of this project is to develop an image-based analysis method that enables timely evaluations. - Chemical Engineering, Computer Software, Image Processing, Interdisciplinary Engineering, Manufacturing Engineering, Materials Engineering, Mechanical and Industrial Engineering
- Bachelor Thesis, Master Thesis, Semester Project
| diaxxo, a start-up from ETH Zürich, is transforming molecular diagnostics with an innovative Point-of-Care Polymerase Chain Reaction (PCR) device. Designed to accelerate and democratize access to diagnostic testing, our cutting-edge technology can be used across various fields, from human diagnostics to vet and food testing.
Our products are also tailored for use in developing countries and resource-limited settings, aiming to bring reliable diagnostics to every corner of the globe.
The company offers several projects and thesis opportunities focusing on interfacing computer and camera systems (e.g. controlling Camera Pi from ESP microcontrollers, and integrating hardware and software components to address design and automation challenges. - Chemical Engineering, Computer Hardware, Electrical Engineering, Manufacturing Engineering, Mechanical Engineering, Software Engineering
- Bachelor Thesis, Internship, Master Thesis, Semester Project
| In this project, we focus on continuous and quantitative monitoring of activities of daily living (ADL) in SCI individuals with the goal of identifying cardiovascular events and PI-related risk behaviors.
ADLs specific to SCI patients and their lifestyles shall be discussed and narrowed down in the scope of this work, therefore an autonomous camera-based system is proposed to classify ADLs.
The Current work builds on a previous project where a SlowFast network [1] was trained to identify SCI-specific classes and we aim to further improve the classification and temporal resolution for transferring to wearables' time-series data. - Computer Vision, Health Information Systems (incl. Surveillance), Intelligent Robotics, Knowledge Representation and Machine Learning, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Pattern Recognition
- Bachelor Thesis, Course Project, ETH for Development (ETH4D) (ETHZ), ETH Zurich (ETHZ), Internship, Master Thesis, Semester Project
| The repetitive and high-impact nature of the golf swing may contribute to lower spine degeneration and chronic low back pain. This project aims to analyze the biomechanical loading of the lumbar spine during the golf swings through advanced motion capture and modeling techniques. A high-fidelity golf simulator combined with a mobile phone-based motion capture system will be used to evaluate swing mechanics. In Part A, state-of-the-art pose estimation models will be tested for their accuracy in extracting 3D motion data from monocular videos. In part B, biomechanical analysis will integrate pose data into an individualized OpenSim model to estimate spinal joint reaction forces and muscle activity. The ultimate goal is to develop a smartphone-based tool capable of real-time swing analysis to provide insight into injury prevention and technique optimization for golfers. - Artificial Intelligence and Signal and Image Processing, Biomechanical Engineering
- Master Thesis
| Our lives on Earth are greatly influenced by the geopotential and its variation based on location, yet understanding it is often challenging. Therefore, a visualization tool is needed to show how changes in the Earth's shape and density affect the geopotential and its derivatives. - Cartography, Computer Software, Earth Sciences, Geodesy
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| Climate change is increasing tree mortality due to drought and biotic infestations, but current detection methods are limited by data availability and low transferability. This study aims to use deep learning with true color near-infrared RGBI aerial imagery to detect spruce mortality in mixed forests. By integrating field inventories and RGB imagery, the method will be analyzed using R or ArcGIS Pro to accurately assess vegetation conditions. - Environmental Sciences, Geomatic Engineering, Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| This project explores and extends the novel "deep state-space models" framework by leveraging their transfer function representations. - Engineering and Technology, Information, Computing and Communication Sciences, Mathematical Sciences
- Master Thesis, Semester Project
| Integrating wind energy into Switzerland’s future energy system remains a complex challenge, with optimal use of available potential in an integrated system still underexplored. This project aims to enhance wind energy assessments by incorporating spatial-temporal wind potential into energy system modeling and analyzing its role in Switzerland’s energy transition, including social aspects. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Quality requirements or non-functional requirements (NFR) are frequently described from the perspective of an organization that requires a software system to address a specific problem and achieve organizational goals. This approach is business-oriented and primarily reflects business goals. However, to design a user-centric system, the goals should be considered beyond the interests of a single organization and accurately reflect the perspective of users instead.
- Software Engineering
- Master Thesis
| We are offering a paid internship opportunity at the EPFL IMOS lab to explore innovative data generation techniques that enhance the capabilities of Foundation Models. In this role, you will investigate synthetic data creation for Prognostics and Health management (PHM) scenarios, working towards pretraining a foundation model for PHM and scaling synthetic data generation to millions of datasets. You’ll gain hands-on experience with cutting-edge Machine Learning tools, collaborate with researchers, and help shape the future of data-driven PHM. If you're eager to take on the challenge of scaling data generation for Foundation Models, we’d love to hear from you! - Data Storage Representations, Data Structures, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Simulation and Modelling, Software Engineering
- Internship, Master Thesis
| Join the Sensors Group (https://sensors.ini.ch/) at the Institute of Neuroinformatics (INI), UZH-ETH Zurich to develop next generation audio systems for augmented auditory perception! This project explores advanced audio processing techniques to enhance human hearing beyond natural capabilities. You will develop and optimize algorithms that amplify, filter, and selectively enhance sounds in complex auditory environments. Applications include assistive listening devices, augmented reality audio, and situational awareness systems. The work involves designing deep learning models, improving real-time processing efficiency, and optimizing hardware cost on embedded platforms. - Computer Software, Electrical and Electronic Engineering, Signal Processing
- ETH Zurich (ETHZ), Master Thesis, Semester Project
| Project Title: Designing a Human-in-the-Loop Model for Behavior Classification in Videos
Description:
We are looking for a motivated student to join an exciting interdisciplinary project that combines neuroscience, machine learning, and human-computer interaction. The project involves building a robust model for behavior classification in videos with a human-in-the-loop approach. The data for this project has already been recorded, and the next steps involve integrating new data, improving the model, and implementing machine learning solutions using Python and popular ML libraries. - Biology, Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Robotics is dominated by on-policy reinforcement learning: the paradigm of training a robot controller by iteratively interacting with the environment and maximizing some objective. A crucial idea to make this work is the Advantage Function. On each policy update, algorithms typically sum up the gradient log probabilities of all actions taken in the robot simulation. The advantage function increases or decreases the probabilities of these taken actions by comparing their “goodness” versus a baseline. Current advantage estimation methods use a value function to aggregate robot experience and hence decrease variance. This improves sample efficiency at the cost of introducing some bias.
Stably training large language models via reinforcement learning is well-known to be a challenging task. A line of recent work [1, 2] has used Group-Relative Policy Optimization (GRPO) to achieve this feat. In GRPO, a series of answers are generated for each query-answer pair. The advantage is calculated based on a given answer being better than the average answer to the query. In this formulation, no value function is required.
Can we adapt GRPO towards robot learning? Value Functions are known to cause issues in training stability [3] and a result in biased advantage estimates [4]. We are in the age of GPU-accelerated RL [5], training policies by simulating thousands of robot instances simultaneously. This makes a new monte-carlo (MC) approach towards RL timely, feasible and appealing. In this project, the student will be tasked to investigate the limitations of value-function based advantage estimation. Using GRPO as a starting point, the student will then develop MC-based algorithms that use the GPU’s parallel simulation capabilities for stable RL training for unbiased variance reduction while maintaining a competitive wall-clock time.
- Intelligent Robotics, Knowledge Representation and Machine Learning, Robotics and Mechatronics
- Bachelor Thesis, Master Thesis, Semester Project
| This project explores a novel approach to graph embeddings using electrical flow computations. - Artificial Intelligence and Signal and Image Processing, Knowledge Representation and Machine Learning, Mathematics
- Master Thesis
| Study the application of Long Sequence Modeling techniques within Reinforcement Learning (RL) to improve autonomous drone racing capabilities. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Perform knowledge distillation from Transformers to more energy-efficient neural network architectures for Event-based Vision. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Tree species identification is crucial for biodiversity monitoring, forest management, and understanding ecological processes. Advances in computer vision and deep learning have enabled the use of multi-view convolutional neural networks (CNNs) to classify species by integrating complementary information from different views. This thesis explores the integration of multi-view data and citizen science images to develop a scalable, high-accuracy tree species identification framework. By addressing challenges related to data variability and leveraging diverse georeferenced plant images, the study aims to enhance the training and generalization of multi-view CNN models. - Computer Vision, Forestry Sciences, Photogrammetry and Remote Sensing
- Master Thesis
| This thesis explores the integration of Personal Datastores (Solid Pods) and Mixed Reality using an HL2. Concretely, this thesis implements an application for the HL2 that provides an MR UI for interacting with a Solid Pod. The implemented app furthermore provides an intuitive way to share (personal) data from the HL2 in real-time with others via Solid. This may include, e.g, one's current gaze data, current activity or detected objects in the user's environment. - Computer-Human Interaction
- Bachelor Thesis, Master Thesis
| We are using retrieval augmented generation (RAG) to support a large language model (LLM) answering questions related to our accelerators. Source documents include scientific publications, as well as internal documents. Many of these documents include images, tables, and equations, which are not directly accessible to be indexed in a language-based embedding.
You will help address these issues by:
• Support the interpretation of scientific publications and internal notes by large language models
• Assess possibilities to index images, tables, and equations
• Store embeddings in a vector data base
• Use a large language model to search this data base, and answer user questions
• Build a user interface for this model
The vector data base and the large language model run locally on hardware located at PSI. - Computer Software, Data Format
- Internship
| Humanoid robots, designed to mimic the structure and behavior of humans, have seen significant advancements in kinematics, dynamics, and control systems. Teleoperation of humanoid robots involves complex control strategies to manage bipedal locomotion, balance, and interaction with environments. Research in this area has focused on developing robots that can perform tasks in environments designed for humans, from simple object manipulation to navigating complex terrains. Reinforcement learning has emerged as a powerful method for enabling robots to learn from interactions with their environment, improving their performance over time without explicit programming for every possible scenario. In the context of humanoid robotics and teleoperation, RL can be used to optimize control policies, adapt to new tasks, and improve the efficiency and safety of human-robot interactions. Key challenges include the high dimensionality of the action space, the need for safe exploration, and the transfer of learned skills across different tasks and environments. Integrating human motion tracking with reinforcement learning on humanoid robots represents a cutting-edge area of research. This approach involves using human motion data as input to train RL models, enabling the robot to learn more natural and human-like movements. The goal is to develop systems that can not only replicate human actions in real-time but also adapt and improve their responses over time through learning. Challenges in this area include ensuring real-time performance, dealing with the variability of human motion, and maintaining stability and safety of the humanoid robot.
- Information, Computing and Communication Sciences
- Master Thesis
| Humanoid robots hold the promise of navigating complex, human-centric environments with agility and adaptability. However, training these robots to perform dynamic behaviors such as parkour—jumping, climbing, and traversing obstacles—remains a significant challenge due to the high-dimensional state and action spaces involved. Traditional Reinforcement Learning (RL) struggles in such settings, primarily due to sparse rewards and the extensive exploration needed for complex tasks.
This project proposes a novel approach to address these challenges by incorporating loosely guided references into the RL process. Instead of relying solely on task-specific rewards or complex reward shaping, we introduce a simplified reference trajectory that serves as a guide during training. This trajectory, often limited to the robot's base movement, reduces the exploration burden without constraining the policy to strict tracking, allowing the emergence of diverse and adaptable behaviors.
Reinforcement Learning has demonstrated remarkable success in training agents for tasks ranging from game playing to robotic manipulation. However, its application to high-dimensional, dynamic tasks like humanoid parkour is hindered by two primary challenges:
Exploration Complexity: The vast state-action space of humanoids leads to slow convergence, often requiring millions of training steps.
Reward Design: Sparse rewards make it difficult for the agent to discover meaningful behaviors, while dense rewards demand intricate and often brittle design efforts.
By introducing a loosely guided reference—a simple trajectory representing the desired flow of the task—we aim to reduce the exploration space while maintaining the flexibility of RL. This approach bridges the gap between pure RL and demonstration-based methods, enabling the learning of complex maneuvers like climbing, jumping, and dynamic obstacle traversal without heavy reliance on reward engineering or exact demonstrations.
- Information, Computing and Communication Sciences
- Master Thesis
| This thesis aims to apply explainable AI techniques to analyze time series data from the Virtual Peg Insertion Test (VPIT), uncovering additional metrics that describe upper limb impairments in neurological subjects, such as those with stroke, Parkinson's disease, and multiple sclerosis. By preserving the full dimensionality of the data, the project will identify new patterns and insights to aid in understanding motor dysfunctions and support rehabilitation.
- Engineering and Technology, Information, Computing and Communication Sciences, Medical and Health Sciences
- Master Thesis
| This thesis will compare the Virtual Peg Insertion Test (VPIT) with the Inverse3 haptic device by Haply to evaluate its effectiveness as a tool for assessing upper limb function. The focus will be on comparing both the hardware features and software capabilities to determine if the Inverse3 can serve as a valid alternative to VPIT for clinical assessments. - Engineering and Technology, Information, Computing and Communication Sciences, Medical and Health Sciences
- Collaboration, Master Thesis
| In this project, the student applies concepts from current advances in image generation to create artificial events from standard frames. Multiple state-of-the-art deep learning methods will be explored in the scope of this project. - Artificial Intelligence and Signal and Image Processing
- Master Thesis, Semester Project
| The goal of this project is to develop a shared embedding space for events and frames, enabling the training of a motor policy on simulated frames and deployment on real-world event data. - Artificial Intelligence and Signal and Image Processing
- Master Thesis, Semester Project
| Unlock the potential of differentiable simulation on ALMA, a quadrupedal robot equipped with a robotic arm. Differentiable simulation enables precise gradient-based optimization, promising greater tracking accuracy and efficiency compared to standard reinforcement learning approaches. This project dives into advanced simulation and control techniques, paving the way for improvements in robotic trajectory tracking. - Intelligent Robotics
- Bachelor Thesis, Master Thesis, Semester Project
| Mobility is typically self-optimized for a particular region to accommodate internal travel needs. However, as soon as one considers multiple, interacting regions (e.g., urban areas interacting with agglomerations, and agglomerations interacting with rural areas), important coordination issues occur, including scheduling mismatches, fleet allocations, and congestion peaks. In short, a mobility system composed of self-optimized mobility systems seems to often operate suboptimally.
In this project, we will investigate the idea of strategic interactions of future mobility stakeholders across heterogeneous regions, such as urban areas, agglomerations, and rural areas, leveraging techniques from network design, optimization, game theory, and policy making. - Automotive Engineering, Information, Computing and Communication Sciences, Mathematical Sciences, Mechanical and Industrial Engineering, Transport Engineering
- Master Thesis, Semester Project
| Join a team of scientists improving the long-term prognosis and treatment of Spinal Cord Injury (SCI) through mobile and wearable systems and personalized health monitoring.
Joining the SCAI Lab part of the Sensory-Motor Systems Lab at ETH, you will have the unique opportunity of working at one of the largest and most prestigious health providers in Switzerland: Swiss Paraplegic Center (SPZ) in Nottwil (LU). - Artificial Intelligence and Signal and Image Processing, Computer Software, Data Format, Information Systems
- ETH Zurich (ETHZ), Internship, Lab Practice, Student Assistant / HiWi
| The uprise of consumer-grade fitness trackers has opened the doors to long-term activity monitoring in the wild in research and clinics. However, Fitbit does not identify napping episodes shorter than 90 minutes. Hence, there is a need to establish a robust algorithm to detect naps. - Artificial Intelligence and Signal and Image Processing, Biomedical Engineering, Biosensor Technologies, Electrical and Electronic Engineering
- Bachelor Thesis, ETH Zurich (ETHZ), Master Thesis
| This research aims to advance biohybrid robotics by integrating living biological components with artificial materials. The focus is on developing computational models for artificial muscle cells, a critical element in creating biohybrid robots. Challenges include modeling the complex and nonlinear nature of biological muscles, considering factors like elasticity and muscle fatigue, as well as accounting for fluid-structure interaction in the artificial muscle's environment. The research combines first principle soft body simulation methods and machine learning to improve understanding and control of biohybrid systems. - Biological Mathematics, Biomechanical Engineering, Biophysics, Mechanical Engineering, Modeling and Simulation, Robotics and Mechatronics, Simulation and Modelling
- Bachelor Thesis, Master Thesis, Semester Project
| We are enhancing soft robot modeling by developing a GPU-accelerated version of our FEM-based framework using CUDA. This research focuses on optimizing parallel computations to significantly speed up simulations, enabling larger problem sizes and real-time control. By improving computational efficiency, we aim to advance soft robotics research and facilitate more detailed, dynamic simulations. - Mechanical Engineering, Programming Techniques, Robotics and Mechatronics, Simulation and Modelling
- Bachelor Thesis, Master Thesis, Semester Project
| We are advancing soft robot simulation with FEM and energy-based methods to model complex, adaptive behaviors. This research entails developing the framework to support diverse designs, integrate new physics models, and optimize performance, enabling enhanced control and real-world applications of soft robots. - Mechanical Engineering, Robotics and Mechatronics, Simulation and Modelling
- Bachelor Thesis, Master Thesis, Semester Project
| 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
| We want to train an excavator agent to learn in a variety of soil using a fast, GPU-accelerated soil particle simulator in Isaac Sim.
- Intelligent Robotics, Robotics and Mechatronics
- Master Thesis, Semester Project
| We want to train RL agents on our new particle simulator, accelerated on the GPU via warp in Isaac sim. - Intelligent Robotics
- Master Thesis, Semester Project
| In this project, our goal is to leverage precomputed embeddings(VAE in Isaacsim) from 3D earthworks scene reconstructions to train reinforcement learning agents. These embeddings, derived from incomplete point cloud data and reconstructed using an encoder-decoder neural network, will serve as latent representations. The main emphasis is on utilizing these representations to develop and train reinforcement learning policies for digging tasks.
- Intelligent Robotics
- Master Thesis, Semester Project
| We want to train RL agents on our new particle simulator, accelerated on the GPU via warp in Isaac sim.
- Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| We want to train multiple agents in the Terra environment, a fully end-to-end GPU-accelerated environment for RL training. - Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| About the project: This thesis aims to design a framework for robust fine-motor action decoding using multi-modal (sEMG and depth sensing camera) Bayesian sensor fusion and machine learning approach - Engineering and Technology, Information, Computing and Communication Sciences, Medical and Health Sciences
- Bachelor Thesis, Master Thesis, Semester Project
| Seismologists use earthquake recordings to monitor seismic activity, but these recordings are often mixed with noise from the environment, making it challenging to automatically process earthquake signals. This project focuses on using deep learning techniques to remove noise from earthquake recordings. By building on existing methods and introducing new ideas, the goal is to create a reliable tool that makes earthquake monitoring more accurate and efficient. - Artificial Intelligence and Signal and Image Processing, Earthquake Seismology
- Master Thesis
| When drones are operated in industrial environments, they are often flown in close proximity to large structures, such as bridges, buildings or ballast tanks. In those applications, the interactions of the induced flow produced by the drone’s propellers with the surrounding structures are significant and pose challenges to the stability and control of the vehicle.
A common methodology to measure the airflow is particle image velocimetry (PIV). Here, smoke and small particles suspended in the surrounding air are tracked to estimate the flow field. In this project, we aim to leverage the high temporal resolution of event cameras to perform smoke-PIV, overcoming the main limitation of frame-based cameras in PIV setups.
Applicants should have a strong background in machine learning and programming with Python/C++. Experience in fluid mechanics is beneficial but not a hard requirement. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| diaxxo, a start-up from ETH Zürich, is revolutionizing molecular diagnostics with a cutting-edge Point-of-Care PCR device. Their innovative technology facilitates rapid, accurate diagnostic testing across human, veterinary, and food applications, especially in developing countries. The PCR process amplifies DNA sequences to identify pathogens accurately. Key to diaxxo's system are specialized aluminum cartridges containing pre-loaded, dried reagents, essential for precise diagnostics. However, current manufacturing challenges in reagent loading and drying affect cartridge quality.
The project aims to develop a Quality Control station using advanced imaging and AI to ensure accurate reagent placement and drying, enhancing diagnostic reliability and effectiveness. - Control Engineering, Image Processing, Mechanical and Industrial Engineering, Safety and Quality, Software Engineering
- Bachelor Thesis, Master Thesis, Semester Project
| Autonomous nano-drones, i.e., as big as the palm of your hand, are increasingly getting attention: their tiny form factor can be a game-changer in many applications that are out of reach for larger drones, for example inspection of collapsed buildings, or assistance in natural disaster areas. To operate effectively in such time-sensitive situations, these tiny drones must achieve agile flight capabilities. While micro-drones (approximately 50 cm in diameter) have already demonstrated impressive agility, nano-drones still lag behind. This project aims to improve the agility of nano-drones by developing a deep learning–based approach for high-speed obstacle avoidance using only onboard resources.
- Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Autonomous nano-sized drones, with palm-sized form factor, are particularly well-suited for exploration in confined and cluttered environments. A pivotal requirement for exploration is visual-based perception and navigation. However, vision-based systems can fail in challenging conditions such as darkness, extreme brightness, fog, dust, or when facing transparent materials. In contrast, ultrasonic sensors provide reliable collision detection in these scenarios, making them a valuable complementary sensing modality. This project aims to develop a robust deep learning–based navigation system that fuses data from an ultrasonic sensor and a traditional frame-based camera to enhance obstacle avoidance capabilities.
- Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Autonomous nano-sized drones hold great potential for robotic applications, such as inspection in confined and cluttered environments. However, their small form factor imposes strict limitations on onboard computational power, memory, and sensor capabilities, posing significant challenges in achieving autonomous functionalities, such as robust and accurate state estimation. State-of-the-art (SoA) Visual Odometry (VO) algorithms leverage the fusion of traditional frame-based camera images with event-based data streams to achieve robust motion estimation. However, existing SoA VO models are still too compute/memory intensive to be integrated on the low-power processors of nano-drones. This thesis aims to optimize SoA deep learning-based VO algorithms and enable efficient execution on MicroController Units.
- Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Investigate how neural rendering can become the backbone of comprehensive, next generation data-driven simulation
- Engineering and Technology, Information, Computing and Communication Sciences
- Internship, Master Thesis
| The objective of the project is to train a neural network taking any floorplan modality as input and outputting an embedding in a latent space shared by all the floorplan modalities. This is beneficial for downstream applications such as visual localization and model alignment. Check the attached the documents for more details.
The thesis will be co-supervised between CVG, ETH Zurich and Microsoft Spatial AI lab, Zurich. - Computer Vision
- ETH Zurich (ETHZ), Master Thesis
| This project aims to develop a novel algorithm for tracking a person's health condition changes using daily life wearable sensor data, biosignals, and information from nearable sensors. With the Life-long-logging system, we want to provide meaningful data for medical staff and directly engage patients and their caregivers. - Artificial Intelligence and Signal and Image Processing, Engineering and Technology
- Bachelor Thesis, ETH Zurich (ETHZ), Internship, Master Thesis, Semester Project
| The StrongAge Dataset, collected over one year, provides a rich data repository from unobtrusive, contactless technologies combined with validated mood and cognition questionnaires. This project aims to uncover digital biomarkers that can transform elderly care, addressing critical research questions related to sleep, cognition, physical activity, and environmental influences. - Biomechanical Engineering, Signal Processing
- Bachelor Thesis, ETH Zurich (ETHZ), Internship, Lab Practice, Master Thesis, Semester Project, Student Assistant / HiWi
| This project aims to advance super-resolution imaging techniques, specifically localization optoacoustic tomography (LOT), for optimal imaging of the mouse brain. LOT allows for angiographic imaging beyond the acoustic diffraction limit, enabling blood velocity measurements and oxygen saturation quantification, which enhances understanding of microvascular dynamics and disease. Key tasks include designing hardware for scanning the mouse brain, developing biocompatible particles for in vivo tracking of blood vessels, creating algorithms for accurate blood flow velocity measurement, and implementing AI-based methods for efficient super-resolution imaging. The project also involves participation in experiments with healthy and disease mice. - Artificial Intelligence and Signal and Image Processing, Biomaterials, Interdisciplinary Engineering
- Master Thesis
| The aim of the project is to investigate the benefits, requirements and drawbacks of physics informed neural networks in the context of personalised cardiac and cardiovascular models - Biomechanical Engineering, Clinical Engineering, Computation Theory and Mathematics, Fluidization and Fluid Mechanics, Neural Networks, Genetic Alogrithms and Fuzzy Logic, Simulation and Modelling
- Master Thesis
| The project focuses exploiting generative AI to build synthetic numerical phantom for cardiac anatomy and function suitable for representing population variability. - Biomechanical Engineering, Information, Computing and Communication Sciences
- Master Thesis
|
|
