ETH Competence Center for Materials and Processes (MaP)Acronym | MaP | Homepage | http://www.map.ethz.ch/ | Country | Switzerland | ZIP, City | 8093 Zürich | Address | Leopold-Ruzicka-Weg 4 | Phone | +41 44 633 37 53 | Type | Academy | Parent organization | ETH Zurich | Current organization | ETH Competence Center for Materials and Processes (MaP) | Members | |
Open OpportunitiesThe goal of the project is to assess the feasibility of using commercially available plantar pressure monitoring devices (so called smart insoles) on the diabetic population. Pressure ulcers are a common complication of the diabetic foot, and monitoring plantar pressure continuously is a potential measure of prevention. Diabetic patients are often prescribed personalized footwear (e.g., curved insoles that accommodate any deformity in the feet). This project aims at assessing the potential of the smart insoles available on the market to monitor plantar pressure in diabetic patients with such custom footwear. - Biomedical Engineering, Medical and Health Sciences
- Bachelor Thesis, Semester Project
| The remarkable agility of animals, characterized by their rapid, fluid movements and precise interaction with their environment, serves as an inspiration for advancements in legged robotics. Recent progress in the field has underscored the potential of learning-based methods for robot control. These methods streamline the development process by optimizing control mechanisms directly from sensory inputs to actuator outputs, often employing deep reinforcement learning (RL) algorithms. By training in simulated environments, these algorithms can develop locomotion skills that are subsequently transferred to physical robots. Although this approach has led to significant achievements in achieving robust locomotion, mimicking the wide range of agile capabilities observed in animals remains a significant challenge. Traditionally, manually crafted controllers have succeeded in replicating complex behaviors, but their development is labor-intensive and demands a high level of expertise in each specific skill. Reinforcement learning offers a promising alternative by potentially reducing the manual labor involved in controller development. However, crafting learning objectives that lead to the desired behaviors in robots also requires considerable expertise, specific to each skill.
- Information, Computing and Communication Sciences
- Master Thesis
| 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
| In recent years, advancements in reinforcement learning have achieved remarkable success in teaching robots discrete motor skills. However, this process often involves intricate reward structuring and extensive hyperparameter adjustments for each new skill, making it a time-consuming and complex endeavor. This project proposes the development of a skill generator operating within a continuous latent space. This innovative approach contrasts with the discrete skill learning methods currently prevalent in the field. By leveraging a continuous latent space, the skill generator aims to produce a diverse range of skills without the need for individualized reward designs and hyperparameter configurations for each skill. This method not only simplifies the skill generation process but also promises to enhance the adaptability and efficiency of skill learning in robotics. - Engineering and Technology, Information, Computing and Communication Sciences
- Master Thesis
| The Advanced Manufacturing Lab (am|z) is excited to announce a thesis opportunity focusing on the development of a highly parallelizable modeling framework for additive manufacturing (AM) processes, particularly laser powder bed fusion (LPBF). Our research primarily delves into advancing manufacturing techniques, with a special emphasis on additive manufacturing. We have developed a robust numerical simulation framework called iMFREE utilizing Smoothed Particle Hydrodynamics (SPH) for multi-physics applications like LPBF. However, there is a need to enhance computational efficiency, specifically through parallelization via Message Passing Interface (MPI). This project offers an excellent chance for students to deepen their knowledge in parallel computation while working hands-on with a mature computational framework. - Engineering and Technology, Information, Computing and Communication Sciences
- ETH Zurich (ETHZ), Master Thesis
| The goal of the project is to develop and test a smart sock prototype for plantar pressure measurements. Existing previously developed textile pressure sensors are to be integrated in a standard sock. This technology can be used for plantar pressure monitoring in diverse wearable applications ranging from healthcare to sports. - Biomedical Engineering, Medical and Health Sciences
- Master Thesis
| The study of small-molecule supramolecular hydrogelators (SMSHs) is of great interest, both fundamental and applicative. Their self-assembly most often leads to the formation of fibrillar structure and can be used as a model for the fibrillation of biologically-relevant entities, also their ability to form gels with tunable mechanical properties suggest many promising materials-related applications. In this context, aminoacid-based SMSHs (AA-SMSHs) have a special relevance because of opportunities offered e.g. in terms of biocompatibility and biomimetics, as well as in terms of variety of molecular design possibilities. Usually, the sol-gel behavior of AA-SMSHs is pH-dependent thanks to the presence of one or more pH-responsive groups, especially carboxylic acid –COOH ones. For these reasons, pH-responsive SMSHs (aminoacid-based and non) have been and still are the subject of intense investigation. Nevertheless, their behavior is far from being completely understood. - Biological and Medical Chemistry, Biomaterials, Materials Engineering, Physical Chemistry of Macromolecules, Supramolecular Chemistry
- Bachelor Thesis, Internship, Master Thesis, Semester Project
| Combine two exploding fields in computer science: machine learning and agent-based modelling.
Based on preclinical and in vitro studies of cell behaviour and cytokine reaction-diffusion and mechanical tests we have generated an in-house biofidelic agent-based model of the human skeleton and its response to diseases and their treatments. This model reproduces the effects of several widely used osteoporosis treatments on key parameters used to quantify fracture risk. This rule-based approach involves studying bone mechanobiology at the cell scale and extrapolating this to millions of cells at the tissue scale to understand the pharmacokinetics of treatments and identify possible new therapies and approaches to patient-specific treatment.
An alternative approach to in silico prediction of response to treatment is a supervised learning approach where we simply input baseline and follow-up bone scans to a CNN with twelve layers constructed using keras. We then attempt to dive into the black box and quantify what characteristics of the input govern the response of our model. The issue is the clinical data is not big enough to do this well so we use the agent-based model as input to the ML approach to construct a proxy model! This also helps us understand, validate and quantify the uncertainty in the agent-based model. To decide which runs of the agent-based model to use as input to the ML approach to construct the proxy model we use polynomial chaos expansion. - Animal Physiology-Cell, Artificial Intelligence and Signal and Image Processing, Cell Development (incl. Cell Division and Apoptosis), Cellular Interactions (incl. Adhesion, Matrix, Cell Wall), Computation Theory and Mathematics, Modeling and Simulation, Protein Targeting and Signal Transduction
- Bachelor Thesis, Master Thesis, Semester Project
| Problem:
Accurately estimating the weight of food items is a significant challenge in healthcare applications. While state-of-the-art 3D cameras can precisely measure food volume, the lack of datasets with labeled food densities remains a major obstacle for accurately determining food amounts.
Goal of the thesis:
The thesis aims to create a dataset that includes the volume, weight, and 3D scans of various food items using a state-of-the-art structured light camera. Due to the vast variety of foods, compiling a comprehensive dataset is impractical. Therefore, the project will also include training and testing a machine learning model to predict the densities of food items that were not seen during its training.
- Food Engineering, Food Processing, Health Information Systems (incl. Surveillance), Nutrition and Physiology
- Bachelor Thesis, ETH Zurich (ETHZ), Master Thesis, Semester Project
| This project aims to develop advanced
earthquake forecasting models using
bio-inspired Spiking Neural Networks (SNNs).
By exploiting the inherent flexibility of SNNs,
the project will create sparse, multi-step
forecasting models capable of integrating
data from various sources. These models will
be built and tested using the NEST neural
simulator, emphasizing neuroplasticity,
neuromodulation, and neural Darwinism
principles. The goal is to enhance the
efficiency of earthquake predictions by
learning more effectively from limited and
lower-quality data, potentially leading to
significant improvements in forecasting
methods and ultimately reducing the risks
associated with seismic events. - Earthquake Seismology, Knowledge Representation and Machine Learning, Neural Networks, Genetic Alogrithms and Fuzzy Logic
- ETH Zurich (ETHZ), Master Thesis, Semester Project
|
|