Exoskeletons are a potential solution to assist therapists in their workflow and patients when undergoing rehabilitation. In this project, a continuum manipulator-based solution for the knee will be adapted to an exoskeleton solution for the hand.

The Werner Siemens Chair of Synthetic Biotechnology at the Department of Chemistry at the Technical University of Munich in Garching focuses on the isolation, characterization, and process-oriented optimization of enzymes and microorganisms for the production of industrial platform chemicals. A key research area is the fermentation of filamentous fungi with the aim of producing extracellular proteins, natural products and pigments for a variety of industrial applications.

Aerosol vaccination offers great potential due to the immune response directly at the site of infection. Thus, in this project we aim for the development of an aerosol inhalator for the vaccine application as aerosol.

During protein synthesis, amino acids form peptide bonds through reactions between their amino (NH₂) and carboxyl (COOH) groups. Interestingly, small carboxylic acids such as lactate, acetate, or citrate also possess COOH groups and can form N-acyl or pseudopeptide conjugates with amino acids.

This project aims to analyze the contribution of different input features to biomechanical prediction models based on wearable sensor data. The focus lies on applying and evaluating explainable AI (XAI) techniques to a transformer-based architecture. By integrating post-hoc interpretability methods with a state-of-the-art transformer model, the project aims to systematically quantify the impact of individual sensor features on the prediction of lower-body kinematics and kinetics.

Projects: AgriRestore and InspectAI The AgriRestore project investigates the movement and community interactions of wild bees in agricultural landscapes using harmonic radar. The thesis is part of a collaboration between the Chair of Plant–Insect Interactions at TUM and Anhalt University of Applied Sciences. Fieldwork will be conducted at research sites throughout Saxony-Anhalt.

Develop a state-of-the-art robotic trust scale by combining technical knowledge , UX, and clinical insights to guide the future of assistive healthcare robotics.

Master's thesis in the area of affinity chromatography.

The objective of this thesis is to develop a model embedding context information of surgical scenes alongside global scene context to extract surgical phases and actions. Building upon recent advances in deep learning-based semantic segmentation and representation learning, the project investigates how object-level understanding can contribute to higher-level tasks such as surgical phase recognition and workflow modeling.

Super-Resolution Cardiac MRI using Conditional Diffusion Models

Analysis of Minimal-Complexity AVR Strategies for Small CHP Units to Ensure Grid Code Compliance

This thesis is about the development and enhancement of existing simulations for fiber-optic ultrasound detection in combination with mid-IR optoacoustics. The outcome of this work will be directly applied in our experimental setup with the option for you to conduct these experiments on your own.

Concrete LLM-related topics including novel architectural designs, large-scale pretraining and deployment, parameter efficiency, dynamic neural network, etc.

Super-Resolution Cardiac MRI using Conditional Diffusion Models

Are you passionate about advancing AI in online learning? Join the EngageCam project to explore cutting-edge techniques for personalized engagement detection.

This project focuses on evaluating and optimizing approaches for egocentric dynamic neural novel view synthesis systems. Current methods are to be surveyed for their capability to be used with egocentric video material, ability to reconstruct for longer durations, and suitability for the operating room. Key improvement possibilities, such as the use of dynamic spatial anchors, should be implemented and evaluated.

Building on Social Comparison Theory and emotion theories, the goal of this master's thesis is to explore the emotions that might account for positive or negative effects of upward social comparisons on reduced consumption behavior. You will employ a qualitative research design (e.g. focus groups) with relevant informants. The focus is on the exploration of emotions after social comparisons with target persons who act particularly sustainable in terms of reducing overall consumption. By exploring informants' subjective experiences, you will categorize and analyze the specific emotions (such as benign envy, malicious envy, shame, and inspiration) that arise from the comparison and may subsequently affect informants' the decision to consume less. Through this research, you will gain insights into how behavioral interventions and public policy promoting sustainable and reduced consumption can be refined by targeting specific emotional states via social comparisons.

This thesis explores how VLM-based scene analysis can be combined with RL-based end-to-end driving to improve decision-making in autonomous driving tasks. The project will be developed in CARLA and later tested on a real F1TENTH racing car, offering the student a rare opportunity to deploy advanced algorithms on physical hardware such as Jetson Orin / Nano.

Biomechanical experiment on soccer players (both female and male) in lab settings, to study the effect of an insole on muscular activity, kinematics, kinetics. To help reduce non-contact injuries in football Link to the thesis soccer_thesis.

Robot Foundation Models use visual, multi-modal, and language inputs to perform complex manipulation tasks. This data-driven approach to robot control has shown tremendous success. Current research focuses on reliable task fulfillment, sample-efficient learning, and novel training strategies. We offer several thesis on the topic. Please find all information and the thesis announcement here: https://nextcloud.in.tum.de/index.php/s/dpJ8wL5rPQso5NN