Max Planck ETH Center for Learning Systems| Acronym | MPG ETH CLS | | Homepage | http://learning-systems.org/ | | Country | [nothing] | | ZIP, City | | | Address | | | Phone | | | Type | Alliance | | Current organization | Max Planck ETH Center for Learning Systems | | Members | |
Open OpportunitiesThe project shall enable all people – regardless of their physical or cognitive abilities – to work in the kitchen - Engineering and Technology, Medical and Health Sciences
- Master Thesis, Semester Project
| The project aims to describe vibration of internal organs during jogging and what benefits these vibrations may have for human health. - Biomedical Engineering
- Master Thesis
| This project aims to extend traditional NavMesh techniques for use in legged robots with discrete rotational symmetry, such as ANYmal. While NavMeshes are commonly used in gaming for path planning, their adoption in robotics is limited due to assumptions about agent shape and reliance on static, geometry-based maps. We propose an online approach that dynamically generates NavMeshes in real time from RGB-D camera data, enabling robots to adapt to their environments. Additionally, we plan to embed semantic information into the meshes, allowing robots to navigate more effectively by understanding both geometric and environmental contexts. Our system will be validated in simulated environments and on real robots, offering a robust framework for path planning, obstacle avoidance, and reinforcement learning applications. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis, Semester Project
| Lab-on-a-chip (LoC) devices can be effectively utilized for manipulating the growth of single cells such as pollen tubes (PTs), the fastest growing single cells. Integrating the LoC devices with the cellular force microscope (CFM) allows for in-situ mechanical characterizations of PTs while investigating and manipulating their growth in a highly automated manner. The goal of this project is to develop LoC devices for single cell manipulation and integrate them with CFM for in-situ biomechanical characterizations. - Biomedical Engineering, Mechanical Engineering
- Bachelor Thesis, Master Thesis, Semester Project
| Dynamic Population Games (DPGs) are an important class of games that models many real-world problems, including energy systems, epidemics, and the recently proposed “karma economies” for fair resource allocation. A DPG consists of a large population of self-interested agents each solving an individual Markov Decision Process (MDP). The MDP of each agent is coupled to the actions of others and is hence parametrized by the policies adopted in the population. Computing the Nash equilibrium of a DPG is challenging as it involves iteratively solving MDPs many times. This suffers from the well-known curse of dimensionality which severely limits the size of the state and action spaces that are computationally tractable.
Madupite is a novel distributed high-performance solver for large-scale infinite horizon discounted MDPs, which leverages PETSc to implement inexact policy iteration methods in a distributed fashion. Despite its software complexity, Madupite comes with a very intuitive Python interface and a detailed documentation, that allow any Python user to easily deploy it to efficiently simulate and solve large-scale MDPs in a fully distributed fashion. Preliminary benchmarks have showcased the great potential of Madupite, which is capable of efficiently handling MDPs with millions of states.
Motivated by the recent development of Madupite, this project aims at developing fast computation tools that are capable of solving large-scale DPGs. - Computer Software, Engineering and Technology
- Bachelor Thesis, Semester Project
| In this project we seek to reconstruct 3D Gaussian Splatting scenes and capture motion as it happens. - Computer Graphics, Computer Vision, Intelligent Robotics
- Master Thesis
| This project aims to create large scale 3D Gaussian Splatting scenes using online robotic data. - Computer Graphics, Computer Vision, Intelligent Robotics
- Master Thesis
| This thesis will tackle the challenge of multi-modality in robot learning by integrating diffusion models into reinforcement learning (RL). The project is in collaboration with Prof. Gerhard Neumann from KIT (https://alr.iar.kit.edu/21_65.php) - Intelligent Robotics, Knowledge Representation and Machine Learning
- Bachelor Thesis, Master Thesis, Semester Project
| Causl Discovery aims to find causal relations from data, being increasingly important in various fields such as health science. Despite the growing amount of work on applying causal discovery methods with expert knowledge to areas of interest, few of them inspect the uncertainty of expert knowledge (what if the expert goes wrong?). This is highly important since in scientific fields, causal discovery with expert knowledge should be cautious and an approach taking expert uncertainty into account will be more robust to potential bias induced by individuals. Therefore, we aim to develop an iterative causal discovery method with experts in the loop to enable continual interaction and calibration between experts and data.
Besides, fusing datasets from different sources is essential for holistic discovery and reasoning. This project will also focus on developing methods of machine learning and data fusion over distinct contexts under the scope of SCI.
Based on the qualifications of the candidates, we can arrange a subsidy/allowance to cover traveling or living costs. - Expert Systems, Health Information Systems (incl. Surveillance), Statistics
- Internship, Master Thesis, Semester Project
| The goal of this project is to apply LLMs to teach the ANYmal robot new low-level skills via Reinforcement Learning (RL) that the task planner identifies to be missing. - Intelligent Robotics
- Master Thesis
|
|
