Abschlussarbeiten, Bachelor- und Masterarbeiten

Master's Thesis in Mathematics / Computer Science or CE/EE

benedikt.hoock@tum.de — Sat, 05 Sep 2026 16:44:00 +0200

Agentic AI for Biomedical Text Generation - Master's Thesis / Internship @ Helmholtz Munich

raeesa.yousaf@helmholtz-munich.de — Wed, 02 Sep 2026 14:10:00 +0200

[Master Thesis / Guided Research] Live Streaming of Submap Gaussian Splatting to VR: Comparing Region-of-Interest Annotation Strategies for Waypoint Guidance

Hannah.schieber@tum.de, hex-thesis.ortho@mh.tum.de — Tue, 01 Sep 2026 15:02:00 +0200

Bachelorarbeit | A Conversational Web Application for Patient Anamnesis in Ambulatory Trauma Surgery

laura.amenda@tum.de — Fri, 28 Aug 2026 11:25:00 +0200

Ziel dieser Arbeit ist die Weiterentwicklung einer LLM-basierten Webanwendung, die Patienten vor dem Arztgespräch in der unfallchirurgischen Ambulanz in natürlicher Sprache befragt und daraus eine strukturierte Zusammenfassung für den behandelnden Arzt generiert.

Abschlussarbeit NPU-Accelerated AI for Eye Tracking - Algorithm Development & Embedded Deployment

alexander.zimmer@tum.de — Sun, 23 Aug 2026 23:32:00 +0200

External Thesis @ Bosch Research Aufgaben - Während deiner Tätigkeit analysierst du den bestehenden Raytracing-basierten Eye-Tracking-Algorithmus und identifizierst dessen rechenintensive Kernfunktionen. - Des Weiteren benchmarkst du den Algorithmus auf einer Mikrocontroller-CPU und bewertest dabei präzise dessen Laufzeit, Speicherbedarf sowie Genauigkeit. - Darüber hinaus untersuchst du detailliert, welche Algorithmus-Teile sich durch den Einsatz von DSP-, Matrix- oder NPU-Einheiten effizient beschleunigen lassen. - Du entwickelst und testest innovative neuronale Modellansätze, um zentrale Eye-Tracking-Berechnungsschritte zu approximieren oder direkt zu beschleunigen. - Die entwickelten Modelle implementierst, quantisierst sowie exportierst du mithilfe von Python/PyTorch und ONNX speziell für die Zielhardware. - Umfassend vergleichst du die unterschiedlichen Ansätze hinsichtlich ihrer Genauigkeit, Laufzeit, des Speicherbedarfs und ihrer Deploybarkeit. - Nicht zuletzt dokumentierst du deine Forschungsergebnisse präzise und leitest daraus konkrete Empfehlungen für die zukünftige Entwicklung ab. Profil - Ausbildung: Studium im Bereich Elektrotechnik, Mechatronik, Embedded Systems, Informatik, Physik, Data Science oder vergleichbar - Erfahrungen und Know-how: Interesse an Mikrocontrollern, Embedded AI, Machine Learning oder Signalverarbeitung; Erfahrung mit Python; Kenntnisse in PyTorch, C/C++, ONNX oder Modellquantisierung sind von Vorteil - Persönlichkeit und Arbeitsweise: du arbeitest gerne praxisorientiert, analysierst systematisch und möchtest Algorithmen auf realer Hardware evaluieren - Arbeitsalltag: hybrides Arbeitsumfeld mit Bürotagen und mobiles Arbeiten nach Absprache; praktische Tests auf Embedded-Hardware sind Teil der Thesis - Sprachen: gutes Deutsch und Englisch Betreuung in Zusammenarbeit mit einem TUM-Lehrstuhl möglich (Chair of Human-Centered Technologies for Learning). Bei Fragen im Voraus kann über den angegebenen Kontakt gerne vermittelt werden. Bei konkretem Interesse bitte direkt über das Bosch Stellenportal bewerben: https://jobs.bosch.de/job/Abschlussarbeit-NPU-Accelerated-AI-for-Eye-Tracking-Algorithm-Development-Embedded-Deployment-Reutlingen-Kusterdingen?id=3c2e23eb-378f-4290-b637-45234e66934a

Master’s Thesis: Human-AI Collaboration in a Realistic Decision-Making Task

zelun.tony.zhang@tum.de — Thu, 20 Aug 2026 19:19:00 +0200

Master’s Thesis: Evaluation of restored landscapes for GIZ-projects ProSoil and Soil Matters (incl. remote sensing)

nikolaus.froehlich@tum.de — Mon, 17 Aug 2026 11:07:00 +0200

Evaluating the success of different soil improving interventions in dryland ecosystems using socio-economic ground data and remote sensing.

Master’s Thesis: Remote sensing methods for the monitoring and evaluation of restored landscapes worldwide

nikolaus.froehlich@tum.de — Mon, 17 Aug 2026 10:06:00 +0200

In collaboration with World Vision, which implements ecosystem restoration and regeneration projects worldwide, a remote sensing–based monitoring approach will be developed. We are looking for motivated students to support this goal.

Master's Thesis Project: Dissecting Visually Guided Behavior through State-Space Analysis of Neural and Behavioral Data

berkutay_mert@psych.mpg.de — Wed, 12 Aug 2026 10:45:00 +0200

Master’s Thesis in Translational DNA Damage Biology

yizhu.li@tum.de — Mon, 10 Aug 2026 00:05:00 +0200

Master's thesis, research internship or guided research (MA/SA/GR): CT-Based Virtual Donor–Recipient Liver Matching

Cagatay.Alici@med.uni-muenchen.de — Fri, 31 Jul 2026 16:40:00 +0200

CT-Based Virtual Donor–Recipient Liver Matching

Master’s Thesis, Clinical Application Project, Guided Research Project

Overview & Motivation

Motivation: Donor livers may be rejected because they are considered too large or too small for a recipient. Current matching methods rely mainly on body size and estimated liver volume, but do not capture the patient-specific 3D shape of the liver or the available space inside the abdomen.

Problem: A poorly fitting graft may compress nearby organs or blood vessels and make implantation or abdominal closure difficult. Conversely, anatomically suitable grafts may be rejected because conventional measurements suggest a mismatch.

Goal: This project will develop a CT-based virtual matching framework that creates 3D models of the donor liver and recipient anatomy, virtually places the graft inside the recipient, and measures how well it fits.

The proposed pipeline will produce:

A 3D model of the donor liver and relevant recipient anatomy.
A realistic virtual position of the donor liver.
Interpretable measurements describing potential fitting problems.

Your Tasks

Literature Review: Review relevant work on donor–recipient matching, image segmentation, 3D registration, virtual organ placement, and surgical planning.
Method Design: Develop a framework for patient-specific virtual liver graft placement and geometric compatibility assessment.
Implementation: Apply the developed framework to real donor and recipient CT scans to simulate graft placement, visualize the predicted result, and quantify donor–recipient fit.
Evaluation: Validate the predicted graft placement using postoperative CT scans and compare the proposed approach with conventional matching methods based on body weight and liver volume.

Requirements

Must-have: Strong programming skills in Python. Good understanding of 3D geometry or computer vision. Interest in medical image analysis and interdisciplinary research.
Nice-to-have: Experience with CT image analysis, image segmentation, registration, or numerical optimization. Familiarity with tools such as SimpleITK, VTK, VMTK, TotalSegmentator, 3D Slicer, or ImFusion is an advantage.

A medical background is not required. Anatomical and clinical guidance will be provided by the supervisory team.

What We Offer

Clinical Impact: Work on a real problem in liver transplantation.
Research Opportunity: Gain experience in medical imaging, 3D modelling, geometric optimization, and surgical planning.
Mentorship: Close technical supervision from a computer science PhD researcher and regular input from liver-transplant specialists.
Publication Potential: Successful results may contribute to a publication in medical image computing, computer-assisted intervention, or transplantation research.

The expected result is a reproducible research prototype demonstrating whether patient-specific 3D modelling can provide useful information beyond conventional donor–recipient size-matching methods. The long-term goal is to improve donor-organ utilization, reduce unsuccessful allocation attempts, support reduced-size or split-liver planning, and prevent complications caused by oversized grafts.

Related Works

Briceño J, Ciria R, de la Mata M. Donor–recipient matching in liver transplantation. Transplant International. 2013.
Fukazawa K, Nishida S. Size mismatch in liver transplantation. Journal of Hepato-Biliary-Pancreatic Sciences. 2016.
Park S, et al. Improved graft survival using three-dimensional printing of the intra-abdominal cavity to prevent large-for-size syndrome. Annals of Hepato-Biliary-Pancreatic Surgery. 2025.
Bojstedt J, et al. Preoperative simulation for pediatric kidney transplantation using CT imaging and 3D printing. Frontiers in Transplantation. 2026.

Interested?

Please send an email outlining your interest in the project, along with your latest transcript of records and CV, to: Cagatay.Alici@med.uni-muenchen.de.

BA/SA/MA: Development of Acoustic Membranes for Dry-Coupled Ultrasound Detection in Non-Invasive Glucose Monitoring

maximilian.gotsch@tum.de — Wed, 29 Jul 2026 15:05:00 +0200

Masterarbeiten: Leukemia Intrinsic Resistance (Beginning October 2026 WiSe)

nadia.el-khawanky@tum.de — Fri, 24 Jul 2026 14:19:00 +0200

Master thesis or research internship (MA/SA): Interferometer stabilization for optical ultrasound detection in non-invasive glucose monitoring

maximilian.gotsch@tum.de — Wed, 15 Jul 2026 11:56:00 +0200

MA: Cognitively-realistic Spatial Visual Search Behavior for Embodied AI

andrey.rudenko@tum.de — Tue, 14 Jul 2026 16:13:00 +0200

MA: Development and Evaluation of a Scalable Whole-Body Data Collection Framework for Vision-Language-Action Learning on Quadrupedal Mobile Manipulators

yuan_avs.gao@tum.de — Fri, 10 Jul 2026 15:01:00 +0200

Abschlussarbeiten, Bachelor- und Masterarbeiten

zfp@ed.tum.de; kerstin.kracht@tuhh.de — Wed, 01 Jul 2026 14:37:00 +0200

Sie suchen gerade eine Diplomarbeit, ein Thema für eine Bachelor oder Master Thesis? Dann sind Sie hier richtig. In diesem Bereich sind Abschlussarbeiten aus allen Fakultäten zu finden.
Beachten Sie auch den entsprechenden Stichwortindex.

Wenn Sie selbst eine Diplomarbeit ausschreiben wollen, lesen Sie bitte vorher unbedingt das 'Best Practice Manual Stellenanzeigen'.

Production and Purification of membraneproteins using E. coli and Chromatography

j.galbusera@tum.de — Tue, 23 Jun 2026 11:08:00 +0200

In this master’s thesis, several membrane proteins will be recombinantly produced using Escherichia coli as an expression host. These membrane will then be tested by a project partner as potential vaccines.

Bachelor’s thesis: Effect of anaerobic fungal pre-treatment on biomethane potential

cristina.gonzalez-rivero@tum.de — Mon, 22 Jun 2026 16:34:00 +0200

THESIS OBJECTIVES As part of the BMLEH (FNR)-funded project LCR-PILZE, the potential of anaerobic fungi to improve methane yield during biogas production is being investigated in a pilot-scale biogas plant. The main hypothesis to be tested is if biological pre-treatment with anaerobic fungi accelerates degradation of lignocellulose-rich agricultural fermentation residues resulting in a more efficient biogas production. For this, the biogas production of 4 selected anaerobic fungi strains is determined using anaerobic batch reactors. TASKS Determination of biomethane potential (BMP) of anaerobic fungi in batch tests Assessment of lignocellulose degradation efficiency Comparison of the effects of biological pre-treatment of lignocellulosic residues with chemical and physical pre-treatment methods Hands-on work at the biogas pilot plant in Dürnast REQUIREMENTS Enrolled Bachelor’s student in Biology, Molecular Biotechnology, Bioprocess Engineering or a related field Good theoretical background in microbiology Experience with microbiological laboratory methods, ideally anaerobic microbiology Interest in sustainable biogas production processes WHAT WE OFFER Opportunity to contribute to an interdisciplinary and sustainable research project Training in methods of (anaerobic) microbiology and chemical analytics Insights into technical scale biogas plant Interested? Send an e-mail including a letter of motivation and short CV (incl. relevant expertise/internships etc.) to: cristina.gonzalezrivero@lfl.bayern.de

Master's Thesis: Adaptive Cooperative Perception for ETSI-Based Vehicle-to-Infrastructure Systems Using Covariance-Aware Movement Clustering

erik-leo.hass@tum.de — Thu, 11 Jun 2026 15:55:00 +0200

The Chair of Robotics, Artificial Intelligence, and Real-Time Systems offers a Master’s thesis focusing on adaptive cooperative perception for ETSI-based Vehicle-to-Infrastructure systems using covariance-aware movement clustering and track-to-track fusion. The thesis investigates how object information from CAM and CPM messages, including covariances, velocities, and object parameters, can improve multi-agent object association and global tracking in urban traffic scenarios.

Bachelor- und Masterarbeiten oder Forschungspraxis an der Professur für Energiemanagement-Technologien

student-applications.emt@ed.tum.de — Mon, 01 Jun 2026 15:15:00 +0200

Du begeisterst dich dafür, modernste Informationstechnologien einzusetzen, um die Energie- und Klimakrise zu lösen, und möchtest in einem dynamischen Forschungsumfeld arbeiten? Dann lass uns gemeinsam die Energiesysteme der Zukunft gestalten!

Pollution and Perception: How ozone degrades social discrimination systems in ants

jan.buellesbach@tum.de — Sat, 25 Apr 2026 17:15:00 +0200

Ants recognize their nestmates by “smelling” the waxy hydrocarbons on each other’s bodies—but ozone pollution can chemically alter these cues and confuse entire colonies. This project dives into the chemosensory mechanisms behind this phenomenon: How do antennal sensilla detect oxidized versus intact hydrocarbons? You will combine behavioral assays and chemical analysis to unravel how environmental change reshapes insect communication.

Bachelor- /Master-Thesis or Research Internship in Evolutionary Biology & Chemical Ecology

jan.buellesbach@tum.de — Wed, 22 Apr 2026 16:45:00 +0200

Bachelor- / Master thesis: Unlock the Secrets of Wasp Courtship

jan.buellesbach@tum.de — Wed, 22 Apr 2026 16:00:00 +0200

Master thesis: Pollution and Perception - How ozone degrades social discrimination systems in ants

jan.buellesbach@tum.de — Wed, 22 Apr 2026 15:55:00 +0200

Master's Thesis: From Signals to Glucose. Modeling and Inversion in Mid-Infrared Optoacoustic Spectroscopy

alexander.prebeck@tum.de — Fri, 17 Apr 2026 10:00:00 +0200

Master's Thesis on Physical System Modelling for non-invasive Glucose Measurements

Master’s Thesis in Cardiac Gene Therapy and Translational Genome Editing

vijayanand.rajendran@tum.de — Mon, 06 Apr 2026 18:35:00 +0200

Master thesis in Hydrology of the Biodiversity Exploratories

alejandra.parreno@tum.de — Sun, 22 Mar 2026 16:55:00 +0100

Masters Thesis in Soil Science

alejandra.parreno@tum.de — Sun, 22 Mar 2026 16:55:00 +0100

Chemical mimicry and sexual dimorphism in mites

jan.buellesbach@tum.de — Thu, 05 Mar 2026 09:55:00 +0100

Bulb mites show a dramatic male dimorphism, developing either into deadly fighters or harmless scramblers, raising the question of why the ill-equipped scramblers still persist in nature. This project explores whether scramblers escape aggression from fighter males by chemically mimicking females, using detailed analyses of their surface chemical profiles. By linking behaviour and chemistry, you will uncover the mechanisms that maintain these surprising alternative tactics.

How do insects adapt to different host plants?

jan.buellesbach@tum.de — Wed, 04 Mar 2026 15:15:00 +0100

Explore how insects’ surface pheromones—used for waterproofing, communication, and mate choice—shift during adaptation to new environments. Working with experimental evolution lines of seed beetles, you’ll test how host plants alter chemical profiles and, potentially, pheromonal communication. Gain hands‑on experience with chemical analysis, evolution experiments, and multivariate data to study rapid trait evolution.

BASAMA:

yuan_avs.gao@tum.de — Fri, 13 Feb 2026 14:40:00 +0100

Talk2Drive: A Conversational Preference-Aligned Driving Framework Using Multi-Modal Large Language Models

MA: Fine-Tuning an LLM Agent for Automated OpenSCENARIO Generation and CARLA Execution

yuan_avs.gao@tum.de — Fri, 13 Feb 2026 13:50:00 +0100

BASAMA: Learning from BEV and Dash-Camera Views: A Multimodal Large Language Model for Quantitative Risk Assessment

yuan_avs.gao@tum.de — Fri, 13 Feb 2026 13:45:00 +0100

BASA: Generation of New Driving Scenarios in CARLA Using OpenSCENARIO

yuan_avs.gao@tum.de — Fri, 13 Feb 2026 13:45:00 +0100

SA/MA: Diffusion-based safety-critical scenario generation

yuan_avs.gao@tum.de — Fri, 13 Feb 2026 13:00:00 +0100

[HiWi / Working Student / Research Internship]

peter.gu@tum.de — Tue, 27 Jan 2026 17:40:00 +0100

[Master Thesis / Research Internship] Joint Communications and Sensing Using Software-Defined Radios

peter.gu@tum.de — Tue, 27 Jan 2026 17:30:00 +0100

[Thesis, Internship] Deep Reinforcement Learning for Robot Control

oliver.hausdoerfer@tum.de — Mon, 05 Jan 2026 23:05:00 +0100

[Thesis, Internship] Foundation Models for Robot Manipulation

oliver.hausdoerfer@tum.de — Mon, 05 Jan 2026 22:50:00 +0100

Master’s Thesis: Simulation of Fiber-Optic Ultrasound Detection for Non-Invasive Optoacoustic Spectroscopy

maximilian.gotsch@tum.de — Thu, 27 Nov 2025 15:40:00 +0100

As part of the EU-funded GLUMON project, we are developing a novel approach for non-invasive glucose monitoring based on optoacoustic mid-infrared spectroscopy. This technology has the potential to enable continuous and pain-free blood glucose measurement — a real step forward in diabetes care. The main goal of this development is further miniaturization and an alternative to the current transmission mode measurement. You will investigate the combination of mid-infrared spectroscopy and fiber-optic ultrasound detection using COMSOL Multiphysics. Your work will greatly enhance existing simulations of the two regimes and combine them to identify key performance indicators for a miniaturized non-invasive glucose probe. Thesis Objectives The goal of this thesis is to develop and enhance existing simulations for fiber-optic ultrasound detection in combination with mid-IR excitation. The outcome of your simulation will be directly applied in an experimental setup with the option for you to conduct these experiments on your own. Tasks • Literature review of ultrasound propagation and interaction with different materials, optoacoustic signal generation • Development of a COMSOL simulation that integrates both domains of optoacoustics • Characterization and validation of the model with experimental data • If desired: experiments can be performed by you! Requirements • Enrolled Master’s student (m/f/d) in Physics, Computer Science, Data Science, Electrical Engineering, Mechanical Engineering or a related field • Solid programming skills in Python or MATLAB • Good understanding of optical and acoustic principles • Experience with COMSOL What We Offer • Opportunity to contribute to a cutting-edge, interdisciplinary research topic with real-world impact • Exposure to both academic research and practical applications through collaboration with a MedTech startup • Flexible working conditions (on-site lab work and remote work possible) Interested? Send an E-Mail including a Letter of Motivation and your latest Transcript of Records to: maximilian.gotsch @tum.de Maximilian Gotsch (Chair of Biological Imaging, Institute for Biological and Medical Imaging) TranslaTUM, Einsteinstraße 25, 81675 München

Masterarbeit (& Forschungspraktikum)

fr.beck@tum.de — Wed, 26 Nov 2025 13:30:00 +0100

Masterarbeit / Forschungspraktikum (ab 01/2026) für die rekombinante Expression von Ei-Proteinen und deren funktionelle, sowie biochemische Analyse.

Master's Thesis: Safe Reinforcement Learning for Real-World Control Systems - Siemens AG

olivia.garland@siemens.com — Wed, 15 Oct 2025 10:20:00 +0200

Driving The Dream Reaction: Electrochemical Flow Reactor Construction for Formaldehyde Synthesis

hamzah.elfaitory@tum.de — Tue, 07 Oct 2025 12:50:00 +0200