Search for public opportunitiesRegister now and browse all open positions. It's free!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! Notify me when new projects of my interest are advertized!You define what you are interested in and we will send you an Email when a new project matches your criteria, it's that easy. You define what you are interested in and we will send you an Email when a new project matches your criteria, it's that easy. Results |
|---|
In this project, we want to investigate how we can leverage mixed reality (Microsoft HoloLens 2) to build accurate articulated object models through user interaction. Prior work has shown that interaction provides meaningful information for learning object articulation models. We will extend existing work through a feedback loop in which the human can (i) create new observations through interaction after observing the current model and (ii) provide corrections to the articulation axis. Using mixed reality, the user is expected to better assess the quality of the reconstructed object in three-dimensional space. Extensions of the project in several directions are possible - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| Become part of a great and motivated, young research team! This interesting project offers the unique opportunity to get experience with portable electrophysiological techniques, pupillometry, and advanced cognitive tasks. Furthermore, our motivated team is eager to mentor you in terms of good clini - Cognitive Science, Medical and Health Sciences, Psychology
- Bachelor Thesis, ETH Organization's Labels (ETHZ), Internship, Master Thesis, Other specific labels, Semester Project
| Multi-rotor drones are often the only viable solution for remote access and navigation in search and rescue missions in post-disaster scenarios and in exploring hardly accessible spaces. At the Environmental Robotics Laboratory, we are challenging this paradigm with drones that have an almost entirely soft and deformable frame. These novel platforms are aimed to impact and physically interact with the walls of narrow passageways and squeeze to crawl through. We are looking for a competent and motivated student willing to explore active stiffening and damping methods to mitigate the limitations of a soft drone and, potentially, uncover low-energy active morphing properties of the drone's frame. - Automotive Engineering, Composite Materials, Electrical Engineering, Flight Dynamics, Mechanical Engineering
- Internship, Master Thesis, Semester Project
| One of the main obstacles that sustainability experts are confronted with when computing recommendations that will allow stakeholders reducing their Greenhouse Gases (GHG) emissions is the availability, easy access, and quality of the data they require to perform accurate assessments of the stakeholder’s activities that emit GHGs. To improve this situation, academics are working on a system that could act as a one-stop-shop for contextualised, rich GHG data. In this project, you will be contributing towards the creation of such a system, working with real-life data in a real-life problem. - Engineering and Technology
- Master Thesis
| In recent years, the penetration of renewable energy resources in distribution grids has been steadily increasing, raising new challenges for power grids. Due to their large inertia, individual buildings may regulate their heating system to help stabilizing the electric network.
In our previous work, we designed an energy management system that self-exports a flexibility envelope to a system operator [1]. The envelope contains the maximal and minimum energy that the household can consume over an horizon of a day, considering some uncertainties on the weather and model errors.
However, the flexibility potential of prosumers highly depends on the underlying building model. On the one hand, a more complex model should yield more reliable results, reducing the uncertainties and therefore increasing the usable flexibility potential. On the other hand, it requires extensive data and engineering design.
This project aims at studying the impact of the epistimistic modelling uncertainty on the controller decisions and the flexibility potential of households. Some work already analyzed the impact of building models on an MPC controller. In this project, we would like to extend the analysis to the flexibility potential of prosumer units based on the flexibility envelope concepts used in previous works.
[1] Gasser, J., et al., Predictive energy management of residential buildings while self-reporting flexibility envelope. (2021), Applied Energy, 288, p.116653
- Building Science and Techniques, Optimisation, Stochastic Analysis and Modelling
- Master Thesis
| In recent years, the penetration of renewable energy resources in distribution grids has been steadily increasing, raising new issues such as voltage violations or line congestions. Due to their large inertia, individual buildings may regulate their heating system to help distribution system operators alleviating these congestions.
In our previous work, we designed an energy management system that self-exports a flexibility envelope to a system operator for system-level dispatch [1]. The envelope contains the maximal and minimum energy that the household can consume over an horizon of a day. Now, we would like to employ this information to reduce congestions in distribution grids.
[1] Gasser, J., et al., Predictive energy management of residential buildings while self reporting flexibility envelope. (2021), Applied Energy, 288, p.116653. - Building Science and Techniques, Electrical Engineering, Optimisation
- Master Thesis
| Have you ever wondered how the brain works? How does it change to store new memories? How do neurons exactly evolve to help us think? As you might have guessed, these are not easy questions. A way to explore possible answers is to simulate neural networks and explain biological mechanisms or even come up with new theories. So, if you want to use your mathematical or computational skills to solve a part of the brain mystery, this project could be something for you. - Biology, Information, Computing and Communication Sciences, Mathematical Sciences, Physics
- Bachelor Thesis, Master Thesis, Semester Project
| PROJECT DESCRIPTION:
In recent years, computer vision techniques for human pose estimation have increasingly become more accurate and robust [1]. However, these techniques are often trained and evaluated on data where humans display “ordinary” poses, such as pedestrians walking in the streets [2]. Several approaches have also been successful in reliably detecting human poses in more “active” situations such as dancing [3], workout [4] or yoga exercises [5].However, in the context of martial arts, most of the existing models are still struggling to robustly detect the fighters’ poses. While extracting data from fights could significantly transform the experience for athletes, coaches and fans alike, there are still some technical challenges to be addressed. The particularities of the movements displayed in martial arts (such as punches, kicks, clinch and ground fight situations) require alternative models and techniques to obtain meaningful results.
Depending on the interest and background of the student, projects with different focuses are possible:
- Adapting existing models for human pose estimation to martial arts situations through intelligent fine-tuning and post-processing techniques
- Developing novel computer vision models that are specifically trained on martial arts data (real and synthetic)
This student project is a collaboration with an industry partner. Combat IQ is a fast-growing startup that is specialized in data analytics for martial arts. Students will be co-supervised by Sena Kiciroglu (CVLab EPFL) and Dr. Christian Giang (Combat IQ). Students completing a full-time master thesis or master internship will also receive a monthly scholarship.
REQUIREMENTS:
Proficiency with Python and machine learning / computer vision related frameworks (e.g., PyTorch, OpenCV, OpenPose, Movenet, Mediapipe, CUDA, Tensorflow)
Interest for sports and sports analytics
Fluent in English
WE OFFER:
Scholarship for master theses and master internship
Work on real-world problems
Experienced mentors with a world-class academic network
Opportunity to work with professional martial arts athletes and coaches
REFERENCES:
[1] Wang, J., Tan, S., Zhen, X., Xu, S., Zheng, F., He, Z., & Shao, L. (2021). Deep 3D human pose estimation: A review. Computer Vision and Image Understanding, 210, 103225.
[2] Fabbri, M., Brasó, G., Maugeri, G., Cetintas, O., Gasparini, R., Ošep, A., ... & Cucchiara, R. (2021). Motsynth: How can synthetic data help pedestrian detection and tracking?. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 10849-10859).
[3] Katircioglu, I., Georgantas, C., Salzmann, M., & Fua, P. (2021). Dyadic human motion prediction. arXiv preprint arXiv:2112.00396.
[4] Vinzant et al., “3D Pose Based Motion Correction for Physical Exercises”, EPFL Masters Thesis 2021.
[5] Verma, M., Kumawat, S., Nakashima, Y., & Raman, S. (2020). Yoga-82: a new dataset for fine-grained classification of human poses. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops (pp. 1038-1039). - Computer Vision, Knowledge Representation and Machine Learning
- Internship, Master Thesis, Semester Project
| The Institute for Information Management is seeking a Research Assistant to support a data collection project. The project strives to investigate the association between voice and health status in a two-month longitudinal observational pilot study. Patients will collect speech samples at home using a mobile application installed on a tablet. After enrollment in the study, patients complete their first and last study visits with the assistance of study personnel. - Computer-Human Interaction, Family Care
- ETH Organization's Labels (ETHZ), Student Assistant / HiWi
| Model Predictive Contouring Control (MPCC) has shown to achieve very good results in the task of time-optimal multi-waypoint flight. MPCC methods have the freedom to select the optimal states of the system at runtime, dropping the need for a computationally expensive reference trajectory. Our recent work shows MPCC can achieve better lap times than state-of-the-art planning+tracking approaches, and that the method can be run in real-time.
- Intelligent Robotics
- Master Thesis, Semester Project
|
|
