master thesis tu darmstadt

{{ child.heading }}

Quick access

Rechts- und Wirtschaftswissenschaften

Theses | Master's Thesis

The final thesis is generally regulated under § 23 of the General Examination Regulations (APB). Thereafter, separate registration and withdrawal procedures, repetition rules and examination authorisations apply to theses. In addition, the conditions for the issue of topics and receiving credit are specified in the respective study regulations under § 23 of the implementation regulations for the timeframe.

Students of Business Administration/Industrial Engineering and Business Information Systems write their bachelor's thesis in the Department of Law and Economics or in the respective technical department. Alternatively, an interdisciplinary, cross-departmental thesis can be written.

Students in the specialised, English-language master’s degree programmes Entrepreneurship and Innovation Management as well as Logistics and Supply Chain Management write their thesis with one of the research groups that offer modules in the core curriculum of their respective degree programme.

PO 2020 (WI/WINF/EIM/LSCM): workload 30 credit points (900 hours), timeframe 26 weeks

PO 2013 (WI) or PO 2011 (WINF) – expiring:

Master's thesis and study paper: workload 15 credit points (450 hours) each, timeframe 13 weeks each

Alternatively: Interdisciplinary, cross-departmental thesis: workload 30 credit points (900 hours), timeframe 26 weeks, separate application.

All theses are subject examinations and as such must be registered in the Office of Student Affairs within one week of the issue of the topic using the registration form. After receipt of the registration form, the thesis is recorded in TUCaN and the submission date (examination date) is deposited.

All relevant documents on this topic can be found under Downloads and Links | Further information and forms .

Office for Student Affairs

work +49 6151 16-575 91 / -92 fax +49 6151 16-57585

Work S1|03 81 Hochschulstraße 1 64289 Darmstadt

Please use our contact form

Opening Hours

Tuesday, 9 a.m. – 11 a.m.
Wednesday, 11 a.m. – 1 p.m.

Telephone Service Hours

Thursday, 1 p.m. – 3 p.m. Phone number: +49 6151-16 57591

We would like to customise the information and usability of this website to your preferences and needs. To this end, we use so-called cookies. Please choose which cookies you would like to enable when visiting our webpages. Some of these cookies are required to load and correctly display this website on your device. These are strictly necessary or essential cookies and cannot be deselected. The preferences cookie saves your language setting, while the statistics cookie regulates how the open-source statistical software “Matomo” analyses your visits to and activities on our website. For more information about cookies we use, please refer to our privacy policy .

{{ child.heading }}

Quick access

Department of Electrical Engineering and Information Technology

You are still looking for an exciting topic for your bachelor or master thesis? Here you can find a list of all open theses in our departments.

Links & Downloads

Guidelines for theses (opens in new tab)

LaTeX templates for TU design

Support by the TU Writing Center

Study Programmes B.Sc. and M.Sc. Biomedicall Engineering

Theses are possible at any time in cooperation with the Faculty of Medicine at the Goethe University Frankfurt.

In this case, please contact the Dean of Studies for Medical Technology at the Faculty of Medicine : dekanat.medizintechnik@kgu.de

Please support the Office of the Dean of Studies of the Medical Faculty with the following information in advance:

Course of studies, main focus and current semester of study
Planned start of the thesis
Preferred topic with a short justification (motivation in 2-3 sentences)

Please note: The main supervisor of the thesis is still a lecturer at the TU Darmstadt, even for theses written at the Faculty of Medicine.

For further information, please use the guidelines for the final thesis.

For general questions as well as questions about the first and second examiner at the Department of etit, you can contact the Student Advisory Service of the Department of etit: medizintechnik@etit.tu-…

Open Theses

Open theses at the Research Group of Computer Systems

Open theses at the Research Group Real-Time Systems

The Uniklinik Frankfurt would like to offer two topics for theses (opens in new tab) . The topics are aimed at all Master's students in our department.

Assessing the effectiveness of vibro-tactile feedback in bodyweight exercise

Master thesis

Serious Games

Supervisors : Dr.-Ing. Polona Caserman, Dr.-Ing. Thomas Tregel

Announcement as PDF

Drilling Speed Optimization and Vibration Mitigation for Directional Drilling using Bayesian Optimization

Department CCPS

Supervisors : Felix Häusser, M.Sc., Sebastian Hirt, M.Sc.

Conception and Development of Posture-Aware Language Models for Automatic Exercise Recognition

Supervisor : Dr.-Ing. Polona Caserman

Development and Setup of a Low Voltage Active Rectifier for a ETIT Demonstrator

Bachelor thesis, Master thesis

Institute Institut für Stromrichtertechnik und Antriebsregelung

Supervisor : Dr.-Ing. Michael Wolff

Development and Setup of a Transmission Line with Power Flow Indicator for a ETIT Demonstrator

Setup of coupled low voltage drive systems with speed control implementation for a etit demonstrator, development and setup of a handheld b-field probe with oscilloscope interface.

Bachelor thesis

Supervisors : Dr.-Ing. Michael Wolff, Hendrik Gockel, M.Sc.

Modeling and Simulation of Magnetic Coupling in EMC Filters

Institute TEMF

Supervisor : Dr.-Ing. Yvonne Späck-Leigsnering

Formation Path Planning using Model Predictive Control

Supervisor : Maik Pfefferkorn, M.Sc.

Entwicklung und Validierung eines EMV-Simulationsmodells für einen neuartigen eBike-Antrieb

Modern domain decomposition methods in both space and time.

Bachelor thesis, Master thesis, Projectseminar, HiWi Position

Department Computational Electromagnetics (CEM)

Supervisors : Mario Mally, M.Sc., Timon Seibel, M.Sc.

Decoding Neural Correlates of Music Perception and Enjoyment Using EEG Signals

Supervisor : Keivan Ahmadi, M.Sc.

Analysis of a Continuous Lur'e System with Sector-bounded, Slope-restricted Nonlinearities

Supervisor : Hoang Hai Nguyen, M.Sc.

Control of Networked Dynamical Systems:

Direct data-driven approach for system analysis and control, split-range control for applications with 2 manipulated control variables.

Supervisor : Johannes Pohlodek

Two-degrees-of-freedom (2DOF) Control for Speed of a DC Motor

Beobachtbarkeitsanalyse von elektrischen energiesystemen mit gemischten monitoring- systemen.

Department Elektrische Energieversorgung unter Einsatz Erneuerbarer Energien (E5)

Supervisor : Rafael Steppan, M.Sc.

Entwicklung eines Frameworks zum automatisierten Testen von Prädiktionshypothesen im Kontext des automatisierten Fahrens

Department Fachgebiet Regelungsmethoden und Intelligente Systeme

Supervisor : Markus Kramer, Dipl.-Ing.

Simulation of the signal influence by different line configurations

Benchmarking of energy management systems with optimality baselines.

Supervisor : Jens Engel, M.Sc.

Untersuchung des Einflusses von Über- und Unterdämpfung des Grid-Forming Umrichters auf die Frequenzstabilität

Supervisors : Siyuan Li, M.Sc., Aaron Hebing, M.Sc.

Design and Control of an Omnidirectional Robot

Bachelor thesis, Master thesis, Type of work flexible, HiWi Position

Department Self-Organizing Systems Lab

Supervisor : Mengguang Li

Implementation of an Eigenfrequency-Based Deformation Identification for RF Cavities

Seminar paper, Bachelor thesis, Proseminar, Projectseminar

Supervisors : Anna Ziegler, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Auslegung eines direktangetriebenen Synchrongenerators mit supraleitender Erregerwicklung für den Einsatz in einer Windkraftanlage

Institute Institut für Elektrische Energiewandlung (EW), Department Elektrische Antriebssysteme (EAS)

Supervisor : Dr.-Ing. Robin Köster

Auslegung eines supraleitend erregten Homopolargenerators für elektrisches Fliegen

Berechnung des magnetischen felds im stirnraum eines turbogenerators mithilfe eines 3d-fem-modells, elektromagnetische auslegung einer fünfphasigen permanentmagneterregten synchronmaschine als riemenstartergenerator.

Supervisor : M. Sc. Alexander Möller

Implementierung einer U/f -Steuerung in MATLAB Simulink für eine dreiphasige Asynchronmaschine

Implementierung einer lösungsmethode für das bean-modell der supraleitung als variationsproblem, coding for dna storage.

Bachelor thesis, Master thesis, Projectseminar, Type of work flexible

Supervisor : Erik Kubaczka

Lab-of-Origin

Simulative und messtechnische analyse geeigneter elektrodenkonfigurationen für dielektrische spektroskopie bis in den mhz-bereich.

Department Hochspannungstechnik (HST)

Supervisor : Michael Kempf, M.Sc.

Simulation des elektrisch-thermischen Verhaltens fester Isolierstoffe unter Belastung mit hochfrequenter Hochspannung (HFHV)

Messung der dielektrischen kenngrößen fester isolierstoffe bei beanspruchung mit hochfrequenter hochspannung (hfhv), development of an ai-method for predicting protein synthesis capability in microorganisms.

Bachelor thesis, Master thesis, Type of work flexible

Supervisor : Philipp Fröhlich

SPD Matrices Reimagined: A Novel Approach to Computer Vision

Development of a stream function approach for accelerator magnet design using the bembel c++ library.

Supervisors : Maximilian Nolte, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Predicting Radiated Emissions of eBikes

Genetic design automation in yeast using protein-based logic circuits.

Supervisor : Maik Molderings

Protein based Synthetic Circuits in Yeast using Translocation for improved Kineticss

Model-based deep learning with applications in wireless networks.

Department Nachrichtentechnische Systeme (NTS)

Supervisor : Lukas Schynol, M.Sc.

Performance Analysis of Array Calibration for 3-D Imaging with Air-Coupled Ultrasound

Supervisor : Raphael Müller, M.Sc.

OpenCL implementation of ’Volterra’ system models for GPU-accelerated computation

Department Integrierte Elektronische Systeme (IES)

Supervisor : Timo Oster, M.Sc.

Algorithm comparison for the determination of toroidal harmonics

Supervisors : Luisa Fleig, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Simulation of HVDC Cable Joints

Bachelor thesis, HiWi Position

Supervisors : Maren Greta Ruppert-Schmidt, M.Sc., Dr.-Ing. Yvonne Späck-Leigsnering

Surface Impedance Boundary Conditions for a Scattered Field Formulation

Master thesis, HiWi Position

Supervisors : Jonas Christ, M.Sc., PD Dr. rer. nat. Erion Gjonaj

Axisymmetric Finite Element Models of No-Insulation High-Temperature Superconducting Coils

Bachelor thesis, Master thesis, Projectseminar

Supervisors : Erik Schnaubelt, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Circuit Coupling for CERN’s Finite Element Quench Simulation (FiQuS) Framework

Directional h2-matrices for high-frequency electromagnetics, gradient-based optimization of electric machines with analytic sensitivities and isogeometric analysis.

Supervisors : Michael Wiesheu, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Magneto-Mechanical Coupling of an Electric Motor with Isogeometric Finite Elements

Untersuchung der dielektrischen eigenschaften fester isolierstoffe bei beanspruchung mit hochfrequenter hochspannung bis 50 khz, knowledge graph assisted protein models.

Supervisor : Fengyu Cai

Electrodynamic Model of a Pyrotechnical Switch for High Voltage Battery Systems

Supervisor : Prof. Dr.-Ing. Herbert De Gersem

Active Matter

Supervisor : Sascha Hauck

Optimization of a 320kV Cable Joint Specimen During Steady State Operation

Bachelor thesis, Master thesis, HiWi Position

Supervisor : Maren Greta Ruppert-Schmidt, M.Sc.

Importance Sampling for Failure Probability Estimation

Seminar paper, Bachelor thesis, Master thesis, Projectseminar

Supervisors : Dr.-Ing. Mona Fuhrländer, Prof. Dr. rer. nat. Sebastian Schöps

Numerical Simulation of a Plasmonic Niobium Photocathode for SRF Gun Applications

Supervisor : Dr.-Ing. Wolfgang Ackermann

Numerical Simulation of SRF Gun Coupler Kicks

Finite-element electric-machine simulations accelerated by cheap surrogates, simulation of the electromagnetic properties of accelerator cavities.

Supervisor : Dr. phil. nat. Wolfgang F.O. Müller

Using Fluorescent in Situ Hybridization (RNA-FISH) to quantify mRNAs in individual Saccharomyces cerevisiae

Supervisor : Yujie Zhong

Reinforcement Learning for Drone Swarms

Supervisor : Kai Cui

Predicting times of presence at delivery addresses using machine learning/ deep learning

Seminar paper, Bachelor thesis, Master thesis, Proseminar, Type of work flexible

Supervisor : Dr. Bastian Alt

Development of an AI-method for predicting the ability of protein synthesis in microorganisms

Supervisor : Prof. Dr. techn. Heinz Koeppl

Learning Sequential Chemical Reactions

Supervisor : Christian Wildner

Relaxed continuous time Markov chains

Bayesian optimization for the characterization of synthetic circuits, calibration of phased arrays for acoustic imaging with low-rank tensor approximation techniques.

Bachelor thesis, Master thesis, Proseminar, Projectseminar, Type of work flexible

Robust Shape Optimization of Electric Machines

Supervisors : Dr.-Ing. Melina Merkel, Prof. Dr. rer. nat. Sebastian Schöps

Neuronale Netzwerke zur Klassifizierung von Wolken auf Basis von Himmelsbildern

Supervisor : Dr.-Ing. Babak Zandi

Bootstrap Algorithms for Signal Processing

Seminar paper, Bachelor thesis, Master thesis, Proseminar

Department Signalverarbeitung

Supervisor : Prof. Dr.-Ing. Abdelhak M. Zoubir

Robust Classification and Clustering in Wireless Sensor Networks

Seminar paper, Bachelor thesis, Proseminar

Supervisor : Prof. Dr.-Ing. Michael Muma

Robust Regression for Estimating the Eyelid Position in Videokeratoscopic Images

Robust model selection for a biomedical application, study related matters (studying, exams etc.).

servicezentrum@etit.tu-...

work +49 6151 16-20212 fax +49 6151 16-20219

Work S3|21 103.1 Fraunhoferstraße 4 64283 Darmstadt

Consultation Hours

Tuesday, 14:00 to 16:00 and Thursday, 10:00 to 12:00

Please note that you can request and receive most documents by mail. Final documents are welcome to be picked up during office hours. In addition, there is always the possibility to arrange a consultation appointment on site, via Zoom or telephone.

Academic counselling and examination committee matters only by prior appointment.

Quick access

Schnelleinstieg

Communication Networks / Multimedia Communications Lab

Guidelines for Theses

Formal requirements for students for the execution of Bachelor Theses, Master Theses, Studienarbeiten at the Multimedia Communications Lab (KOM) under the supervision of Prof. Dr.-Ing. Ralf Steinmetz.

This information is meant as an overview of requirements, helpful tips, and notes for the application, registration, writing, submission, and presentation of theses at KOM. This is by no means complete nor legally binding. Always regard the current information provided by the University and your department.

Primarily, students from the departments (Fachbereiche) 1, 18, 20, and related study courses can write their thesis at KOM. The duration of a thesis depends on several factors like department, course of study, and part-time or full-time study.

Choice of Topic

Available topics can be found on poster displays at KOM or posted in Open Theses . Furthermore, students may propose their own topics within the field of research of the respective scientists . Topic-related questions can be discussed directly with the respective supervising scientist. In our lab, we provide theoretically and practically oriented theses. We also provide sufficient numbers of computers and workplaces in our student laboratories, enabling the completion of the implementation and writing entirely at KOM.

Expectation

Students are expected to independently acquire and portray the current scientifical and technological state-of-the-art (related work). All sources and references must be correctly cited (see information on Plagiarism ).

The search for scientific publications , like articles in journals or workshop and conference proceedings, can be supported by using search engines like TUbiblio by the ULB or Google Scholar . General statistical data can be found for example at Statista . In addition to the advice of respective supervisors, the university’s SchreibCenter provides a broad range of support for writing a thesis.

Registration

The official start of a thesis has to be registered at the examination management office (Prüfungssekretariat) in the respective department. In some cases, Studienarbeiten must also be registered.

Students must inform themselves of the respective process and requirements for starting and registering their thesis. KOM will not undertake any verification step to see whether a student is eligible to perform a thesis. See your examination office for more information.

Examination Terms

The General Examination Terms of the Technical University of Darmstadt ( Allgemeinen Prüfungsbestimmungen der TUD, APB ) contain the regulations for examinations and theses effective for the entire university.

This page gives only a short overview of some important topics. The English translation is for information purposes only. The legally binding document is the German version . See Rules and Regulations for an overview of available documents.

The following passages are excerpts of the English version of the APB:

" §38 Cheating and unlawful behavior

(1) In the event that cheating or any other infringements by a student in an examination situation comes to light, this examination shall be declared “insufficient”. The respective examiner shall decide in such cases, together with the responsible examination committee in case of doubt.

(2) The submission of a false declaration according to §§22 par. 7, 23 par. 7, the submission of another author’s work, a re-working of another author’s work, or a restructuring of another work, in whole or in part, in a graded paper is considered cheating (plagiarism)."

Note : Plagiarism is cheating and not tolerated! All passages of a text that are not originally from the specified author of the text must be clearly marked as such. Every work performed at KOM—theses, seminars, labs, etc.—is checked for plagiarism. See our information page on Plagiarism .

" §23 Final thesis

(7) The candidate must submit two printed copies of the final thesis for the examiners and one electronic version. If the thesis contains models or other material that cannot be represented in a text document, these must be submitted in an appropriate format, such as an image document. The corrected copy of the final thesis can be made part of the examination folder. All theses shall be saved electronically in the university files. The administration office will decide the details of this procedure. Upon submission of the final thesis, the candidate grants the university the right to store the thesis electronically in the State Library of Darmstadt (Universitäts- und Landesbibliothek Darmstadt)."

Note : Theses must be timely submitted electronically via TUbama , otherwise the thesis is immediately graded a 5.0! Furthermore, students must submit up to two written and signed copies at KOM, depending on the type of thesis and the department. Besides the general examination terms, specific regulations for each department and course of study may be applicable. Students are responsible to meet the given deadlines and also have to check that their submission meets all requirements for themselves.

1) Ottawa University

Comparison of ambiguous (dangerous) and distinct (not dangerous) wording

2) Purdue University

Table with advice for distinct quotations

3) Philipps-Universität Marburg

Example for a decision structure about plagiarism

Formal requirements for the written thesis

Each written thesis must adhere to the following requirements. Additional requirements may be defined by supervisors.

Adequate length , especially but not limited to, including an adequate overview and discussion of related work
Declaration about the thesis (Ehrenwörtliche Erklärung). Students must check before submitting their thesis, that the given declaration meets the latest update given by the university or their department. Consult your supervisor in case of uncertainty.
List of contents
Introduction
Background & related work
Assessment of available approaches and definition of the research gap
Own concept/approach/design in context of the research gap
Implementation. Ask your supervisor and see the Google Style Guides for information on how to properly style your code.
Conclusion and future work
Guidelines for bibliographies (German)
Google Scholar and common bibliography tools provide possibilities to correctly export citations or citation files.
Configuration files
(technical) specifications
additional figures or plots
performed surveys or survey data
evaluation data
(optional) index, list of abbreviations, list of figures, list of tables
Font size 11pt
Figures integrated and used within the text
Chapter structure not deeper than 3 layers (e.g., Chapter 1.2.3.)
1 author = First three letters of author + Year [Aaa21]
2–4 authors = First letter of each author + Year [ABCD21]
>4 authors = First letter of first three authors, "+", + Year [ABC+21]
Equal abbreviations are distinguished by annotating a, b, c, and so on [ABC+21a, ABC+21b]
Alphabetically listed sources

Students are provided a LaTeX Template for Student Theses (Steinmetz) and a LaTeX Template for Thesis Projects (Scheuermann) at KOM. Students can also find examples for good theses .

Students may write their thesis in German or English. However, we strongly encourage all students to write their thesis in English.

In addition to the electronic submission in TUbama and to the respective supervisors, students must submit up to two printed and signed copies of their thesis. The concrete number depends on the type of thesis and the department, consult your supervisor. Print version requirement

Double-sided A4
Glue binding (Leimbindung) with black binding
Black back cover
Transparent front cover sheet

Formal requirements for thesis presentations

Each thesis at KOM is completed by a final presentation with a student audience . It gives a detailed overview of the conducted work as well as the result of the thesis. The primary function of the final presentation is to provide students with the possibility to exercise the preparation of slides and presentation of their work. Therefore, each student must attend final presentations of other students as well. The final presentation is graded differently depending on the type of thesis and department.

Anmerkung für Studierende des FB 1: Der Vortrag ist kein Prüfungsgespräch.

An optional intermediate presentation providing an introduction to the topic, related work, and envisioned approach may be held for the scientific staff at KOM. It provides the students with the possibility to present and discuss their work within a small scientific audience.

Students shall use the Presentation Template (Steinmetz) or Presentation Template (Scheuermann) . The presentation should have a maximum length of 20 minutes . In case this length is exceeded, the presentation may be aborted by the supervisor. Presentation slides shall be in English . The oral presentation may be either in German or English.

The following structure of the presentation can be used as reference.

Title slide, including student name and supervisors
Motivation and goal of the thesis
Possible environments, frameworks, parameters of the thesis
Related work and available approaches to similar problems
possible approaches to the problem
current state, open issues
further tasks, time plan
applied approach to the problem
implementation and evaluation
result of the thesis and resolved issues
future work, open issues, further ideas
Conclusion of the presentation

Notes on preparing and designing presentations

(partially taken from "Mixtur für einen guten Vortrag" by Markus Roggenbach, University of Mannheim)

Number of slides: To prevent a "slide movie", each slide should contain an adequate amount of information which results in approximately 1 – 3 minutes of presentation time for a slide.

Preparation of the talk: Thinking is faster than talking. Loudly exercise the oral presentation beforehand so you know how long the presentation actually takes and to gain confidence in your given talk.

Design of presentation slides: Slides should support the presentation, not replace it. Neither should the presentation slides be empty and without any information, nor should every detail be described in the slides but not used in the presentation. A common but severe mistake are remarks like: “The rest can be taken from the slides”. Usually, slides are overloaded. The audience requires a significant amount of time to conceive the previously unknown slides. Thus, slides should preprocess and comprehensibly portray the most important aspects for the presenter. The structure of content must be implemented by graphical segmentation, like using different colors and fonts or the indentations of lists or notes. A well-used graphical representation or visualization can help to easily convey complex issues. Generally speaking: a picture is worth a thousand words.

Giving the talk: To overcome initial nervosity, it is often helpful to formulate and exercise the first few sentences of the presentation. This at least saves the beginning of the talk. But beware of simply reading off from your notes! This will result in a monotonous presentation style and a dull presentation for your audience. A motivated and energetic presentation style is key for a memorable presentation. Additionally, do not read off all information from your slides. They should contain only the most important notes and no full sentences in the first place.

General hint: If Siri or Alexa could present your slides by reading the content, it is most probably not a good presentation. Another common mistake is that speakers stand in front of their slides and obstruct the audience’s view. To overcome this issue, it may help to purposely pick a spot with an adequate distance to, e.g., the projection surface. This also helps to face the audience, not the presentation slides. If you point at specific parts of a slide, keep in mind not to obstruct the view to the part you are pointing out.

Der Fachbereich etit

Professuren
Fachbereichsleitung
Gleichstellungsteam
Werkstätten

Studieren bei etit

Studienangebot
Studienstart
Studienabschluss
Studium im Ausland

Forschung bei etit

Forschungsschwerpunkte
Unsere Experten
Promotionen

Für Studieninteressierte

Schüler:innen

Kurz gemeldet

BASt vergibt Forschungsauftrag zur Blendungsbewertung an die TU Darmstadt

Professor Pesavento Chair des Technical Area Committee „Signal processing for Multisensor systems“ der EURASIP

Dr. Andrea Ortiz erthält Dr. Wilhelmy-VDE-Preis für ihre Dissertation

Regionale Falling Walls Lab Gewinnerin aus Taiwan bei etit

Master Medizintechnik

Ab dem Wintersemster 2021/22 bieten wir in Kooperation mit der Goethe-Universität Frankfurt den Studiengang M.Sc. Medizintechnik an.

Mehr erfahren

Quickfinder für Studierende

Studiengänge

Lernzentren

Abschlussarbeiten

Abschlussdokumente

Semestertermine und Fristen

Forschungskooperationen gesucht?

Sie sind in den Bereichen Regenerative Energien, Medizintechnik, Autonomes Fahren, Künstliche Intelligenz oder weiteren Gebieten der Elektro- und Informationstechnik unterwegs und suchen universitäre Kooperationspartner. Wir freuen uns auf gemeinsame innovative Forschungsprojekte mit Ihnen.

Unsere Expert:innen

Sie suchen Expert:innen für Ihre Fragestellungen aus den Bereichen Elektrotechnik, Informationstechnik, Mechatronik, Medizintechnik oder Informationssystemtechnik. Zögern Sie nicht, uns zu kontaktieren!

Prof. Dr. Björn Scheuermann

bjoern.scheuermann@tu-...

work +49 6151 16-29107 fax +49 6151 16-29109

Work S3|20 120 Kommunikationsnetze Rundeturmstr. 10 64283 Darmstadt

Prof. Dr.-Ing. Ralf Steinmetz

steinmetz.office@kom.tu-...

work +49 6151 16-29101 fax +49 6151 16-29109

Work S3|20 219a Multimedia Kommunikation Rundeturmstr. 10 64283 Darmstadt

Wir möchten die Informationen und das Nutzungserlebnis auf dieser Webseite an Ihre Bedürfnisse anpassen. Deswegen verwenden wir sog. Cookies. Sie können selbst entscheiden, welche Cookies genau bei Ihrem Besuch unserer Webseiten gesetzt werden sollen. Einige Cookies sind für den Abruf der Website notwendig, damit diese auf Ihrem Endgerät richtig anzeigen werden kann. Diese essentiellen Cookies können nicht abgewählt werden. Der Komfort-Cookie speichert Ihre Spracheinstellung, während „Statistik“ die Auswertung durch die Open-Source-Statistik-Software „Matomo“ regelt. Weitere Informationen zum Einsatz von Cookies erhalten Sie in unserer Datenschutzerklärung .

{{ child.heading }}

Schnelleinstieg

Maschinenbau

Frau Schulz berät einen Studierenden während der Sprechzeiten im Studienbüro

Masterthesis

Wichtige infos zur masterarbeit.

Bevor Du Deine Thesis im MechCenter anmelden kannst, müssen bestimmte Abläufe eingehalten werden. Bitte beachte die folgenden Hinweise um einen reibungslosen Ablauf zu gewährleisten.

Master Maschinenbau (PO 2021) (wird in neuem Tab geöffnet)

Master Aerospace Engineering (PO 2021) (wird in neuem Tab geöffnet)

Anmeldung der Abschlussarbeit im MechCenter

Vorzeitiger Beginn

(wird in neuem Tab geöffnet) Vorzeitiger Beginn Master-Thesis (Master Maschinenbau – PO 2021) (wird in neuem Tab geöffnet)

Leistungsübersicht

Du beginnst Deine Thesis und Dein Abschluss rückt entsprechend in greifbare Nähe? Gerne möchten wir Dir folgenden Hinweis zu Deinen erbrachten Leistungen geben:

Bitte beachte, dass auf dem in TUCaN generierten Web-Leistungsspiegel an einigen Bereichssummen grüne Haken erscheinen, bevor die Bedingungen gemäß der Prüfungsordnung erfüllt sind. Diese Haken ergeben sich durch die technisch hinterlegten Regelungen und dürfen nicht als Bestätigung verstanden werden, dass die einzelnen Vorgaben gemäß des Studien- und Prüfungsplans (SPP) erfüllt sind. Bitte überprüfe anhand des SPP oder der Hinweise zur Studien- und Prüfungsplanung, ob Du tatsächlich in allen Bereichen die notwendigen CP erbracht hast.

Studien- und Prüfungsplan – Master Maschinenbau (wird in neuem Tab geöffnet)

Hinweise zur Studien- und Prüfungsplanung – Master Maschinenbau (wird in neuem Tab geöffnet)

Studien- und Prüfungsplan – Master Aerospace Engineering (wird in neuem Tab geöffnet)

Hinweise zur Studien- und Prüfungsplanung – Master Aerospace Engineering (wird in neuem Tab geöffnet)

Externe Abschlussarbeit

Solltest Du Deine Abschlussarbeit an einem anderen Fachbereich der TU Darmstadt oder in einer Einrichtung außerhalb der Universität (z.B. einem Unternehmen) schreiben wollen, bleibt gemäß der Allgemeinen Prüfungsbestimmungen sowie der Prüfungsordnung dennoch immer der hiesigen Professor oder Professorin verantwortlich für die Aufgabenstellung, die Betreuung und die Bewertung der Arbeit. Dabei besteht jedoch keine Verpflichtung seitens der Professoren, eine externe Thesis zu betreuen. Zusätzlich zur Betreuung durch einen hiesigen Professor, musst Du Dir vor Beginn eine Genehmigung von Seiten des Studiendekans einholen, um eine externe Abschlussarbeit schreiben zu dürfen.

Weitere Informationen findet man unter folgenden Links:

Externe Bachelor/ Master-Thesis (wird in neuem Tab geöffnet)

Merkblatt externe Abschlussarbeiten (TU Darmstadt)

Einreichung Thesis (wird in neuem Tab geöffnet)

Verlängerung

Information Thesisverlängerung (wird in neuem Tab geöffnet)

Ausgeschriebene Abschlussarbeiten

info@mechcenter.tu-...

work +49 6151 16-26101 fax +49 6151 16-26125

Work L1|01 80 - 90 Otto-Berndt-Straße 2 64287 Darmstadt

Postanschrift

Otto-Berndt-Str. 2 Postfach 10 06 36 64206 Darmstadt

{{ child.heading }}

Quick access

Institute for Production Engineering and Forming Machines

Current Master Theses

Below you will find currently open master theses.

Overview Bachelor and Master Theses

Aufbau eines modellbasierten Zustandsbeobachters für eine Servospindelpresse zur Fehlerdetektion und Diagnose

Development of a model-based condition monitor for a servo screw press for fault detection and diagnosis

Supervisor : Viktor Arne, M. Sc.

Announcement as PDF

Untersuchung der Umformbarkeit von Polygonkonturen mit Hilfe des Lochwalzen auf einer Servopresse mit drei Freiheitsgraden im Stößel

Investigation of the formability of polygon contours with the punch rolling process on a servo press with three degrees of freedom in the ram

Supervisors : Viktor Arne, M. Sc., Daniel Spies, M. Sc.

Datenbasierte Inline-Zustandsüberwachung für mehrstufige Hochgeschwindigkeits-Umformprozesse

data-based inline condition monitoring for predictiave maintance in multi-stage high speed forming processes

Supervisor : Jonas Moske, M. Sc.

Weiterentwicklung eines thermisch-gekoppelten Simulationsmodells von Werkzeugeinsätzen mit innovativem Kühlkonzept

Further development of a thermally coupled simulation model of tool inserts with an innovative cooling concept

Supervisor : Philipp Gehringer, M. Sc.

KI-basierte Prozessüberwachung: Unüberwachtes Lernen zur optischen Überwachung schnelllaufender Prozesse

AI-based processmonitoring: Unsupervised learning for optical monitoring of high-speed processes

Supervisors : Felix Georgi, M. Sc., Robin Krämer, M. Sc.

Automatisierung einer simulativen Optimierung von Schnittkonturen für einen Tiefziehprozess im Folgeverbund

Automation of a simulative optimisation of cutting contours for a deep drawing process in a progressive die

Prof. Dr.-Ing. Dipl.-Wirtsch.-Ing. Peter Groche

Director of the institute.

peter.groche@ptu.tu-...

work +49 6151-16-23143 fax +49 6151 16-23142

Work L1|01 148 Otto-Berndt-Straße 2 64287 Darmstadt

{{ child.heading }}

Quick access

Computational Electromagnetics (CEM)

Jobs, Seminar, Bachelor and Master Theses

The following list proposes topics for student thesis at the work group. Most topics can be completed as a student job, seminar project, bachelor or master thesis. Further theses in the mentioned subject areas are always possible on request. Please do not hesitate to contact us!

Please note that there are guidelines (opens in new tab) and Latex templates available to help creating presentations, writing reports, Bachelor's or Master's theses.

Thesis topics

Modern domain decomposition methods in both space and time.

Bachelor thesis, Master thesis, Projectseminar, HiWi Position

Parallel algorithms play an increasingly vital role in both research and industry for accelerating simulations. Domain Decomposition methods (DDMs), such as nonoverlapping Schwarz or Dirichlet-Neumann/Neumann-Neumann methods, are effective approaches for introducing spatial concurrency, thereby facilitating parallel computations. When the problems under examination are not only spatially dependent but also time-dependent, waveform relaxation enhances information exchange between different time steps [2, 3]. This, in turn, enhances additional concurrency in time when combined with Parareal methods.

The objective of this project is to implement selected algorithms from the provided references and evaluate their performance using discretized benchmark problems.

Supervisors : Mario Mally, M.Sc., Timon Seibel, M.Sc.

Announcement as PDF

Implementation of an Eigenfrequency-Based Deformation Identification for RF Cavities

Seminar paper, Bachelor thesis, Proseminar, Projectseminar

In particle accelerators, commonly multi-cell resonating structures are used, e.g. the superconducting 9-cell TESLA cavity. Such devices are manufactured from niobium sheets which are deep-drawn and welded together. During this welding process, misalignment occurs at the joints of the individual components, which leads to deviations from the desired eigenfrequencies and field patters, which negatively influences the accelerating performance of the electromagnetic cavities.

In order to quantify these uncertainties,700 observations are available from measurements at Deutsches Elektronen-Synchrotron (DESY) and found seven uncorrelated deformation variables to describe the cell misalignment.

The purpose of this thesis is to develop an optimization algorithm which allows for conclusions from the measured eigenfrequencies to the deformations of the cavity under consideration. To this end, the closed-form sensitivities with respect to the deformation variables should be used. Using these, an efficient optimization routine should be implemented to identify the misalignment.

Supervisors : Anna Ziegler, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Development of a Stream Function Approach for Accelerator Magnet Design using the Bembel C++ Library

Bachelor thesis

The determination of optimal current distributions on given surfaces is often the starting point for the electromagnetic design of coil dominated electromagnets utilized, e.g. in particle accelerators and magnetic resonance imaging (MRI). Geometrical and mechanical constraints as well as the particle beam size determine the coil winding surface, on which an optimal current density is to be determined.

In this Bachelor thesis, a stream function approach for the determination of optimal current densities on given surfaces shall be developed and implemented in Bembel, the BEM-based engineering library, see www.bembel.eu . The goal is an automated generation of winding paths, on given surfaces and field quality requirements.

Supervisors : Maximilian Nolte, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Algorithm comparison for the determination of toroidal harmonics

The classical way of expressing the field uniformity in accelerator magnets is by means of the Fourier coefficients of the trigonometric eigenfunctions of the Laplace equation also known as multipoles. When the magnets are curved (Fig. 1), higher-order terms appear and the scaling laws derived for straight magnets are no more applicable. The field reconstruction from field simulations or magnetic measurements should therefore be based on the eigenfunctions of the Laplace equation in the toroidal coordinate system, so called toroidal harmonics.

TU Darmstadt, together with the European Organization for Nuclear Research (CERN) formulated a linear inverse problem to determine the toroidal harmonics from the magnetic flux density.

In this thesis, different algorithms to solve this inverse problem shall be studied and compared on magnetic flux density measurements.

Supervisors : Luisa Fleig, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Axisymmetric Finite Element Models of No-Insulation High-Temperature Superconducting Coils

Bachelor thesis, Master thesis, Projectseminar

High-temperature superconducting (HTS) materials are a promising technology for high-field magnets in particle accelerators. In particular, no-insulation (NI) coils, i.e., coils wound without turn-to-turn insulation, have gained popularity due to their robustness [1]. Numerical methods such as the finite element (FE) method play a key role in developing HTS-based applications. The objective of this project is to extend CERN’s existing open-source Finite Element Quench Simulation (FiQuS) framework with 2D axisymmetric FE models of NI coils [2]. Since they are more efficient but less general than existing 3D models, they will complement the latter as an important tool in FiQuS to analyze NI coils. Following FiQuS’s ideals, a key aspect will be to hide the complexities CERN of the FE formulation from the users who are typically not FE experts.

Supervisors : Erik Schnaubelt, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Circuit Coupling for CERN’s Finite Element Quench Simulation (FiQuS) Framework

CERN started a project last year to build a comprehensive open-source quench simulation tool called FiQuS (Finite Element Quench Simulation). It is based on the finite element (FE) framework ONELAB and written mostly in Python. The idea is to build a flexible tool which allows users to build and simulate complex models from human-readable inputs hiding the complexity of the FE kernel. In order to simulate real-world accelerator magnet circuits, this project aims at coupling FE magnet models from FiQuS with electric circuits [1], which can then be solved by circuit simulators such as Xyce. A key aspect will be to hide the complexities of this coupling from the users who are typically not FE experts.

Directional H2-Matrices for High-Frequency Electromagnetics

Master thesis

Solving partial differential equations numerically with boundary element methods requires the application of fast methods to be competitive with other numerical methods. At high-frequencies, the existing implementation of H2-matrices breaks down and needs to be adapted in order to work efficiently.

The idea of the approach is to approximate a spherical wave in far distance hierarchically by plane waves. The implementation is carried out in the C++ library Bembel, see www.bembel.eu .

Gradient-Based Optimization of Electric Machines with Analytic Sensitivities and Isogeometric Analysis

Electric energy conversion is a key issue on the way to decarbonization. Computational design and optimization of electric motors is a very active research area with the aim to increase the efficiency and power density of electric drives. Yet, optimization in commercial solvers is often performed using time-consuming methods such as surrogates or genetic algorithms, taking days or weeks for one optimization.

This work combines the modeling of the motor using Isogeometric Analysis (IGA), which allows to exactly represent the geometry, with fast gradient based optimization. By using present state-of-the-art numerical modeling techniques together with efficient optimization algorithms, it is possible to reduce the optimization time to several minutes.

Supervisors : Michael Wiesheu, M.Sc., Prof. Dr. rer. nat. Sebastian Schöps

Magneto-Mechanical Coupling of an Electric Motor with Isogeometric Finite Elements

The need for higher energy efficiency and decarbonization give rise to a steadily increasing importance of electric drives. Simulations allow the physical limits to be pushed in order to increase the power density and make motors more cost-efficient. This work aims to investigate the influence of mechanical stresses in electric motors on the electromagnetic behavior and find out how stress dependent material properties can be mitigated or exploited. Simulations are performed in an Finite Element (FE) framework using Isogeometric Analysis (IGA), which allows to exactly represent the geometry. This enables an efficient coupling of the geometric, magnetic and mechanical systems.

Importance Sampling for Failure Probability Estimation

Seminar paper, Bachelor thesis, Master thesis, Projectseminar

Deviations in the manufacturing process of electronic components may lead to rejections due to malfunctioning. Uncertain design parameters (i.e. geometrical and material parameters) can be modeled as random variables. Then, the failure probability of a realization can be estimated. A standard approach for estimating failure probabilities is a Monte Carlo analysis. In a Monte Carlo analysis a large number of sample points is generated according to a given probability distribution. The percentage of sample points not fulfilling some predefined performance feature specifications denotes the failure probability. In order to obtain a reliable estimation, a large number of sample points is required. This leads to high computing costs, since for each sample point a PDE must be solved, e.g. with the finite element method (FEM). Current research deals with the reduction of computational effort. Importance sampling is an approach to reduce the number of FEM evaluations by generating sample points in critical regions with a higher probability.

Supervisors : Dr.-Ing. Mona Fuhrländer, Prof. Dr. rer. nat. Sebastian Schöps

Robust Shape Optimization of Electric Machines

Bachelor thesis, Master thesis

Due to the growing importance of e-mobility, the efficient simulation and optimization of electric energy converters, in particular electric machines, is becoming increasingly important. In the manufacturing process of these electric machines imperfections and small deviations from the nominal design can occur. In the worst case, these imperfections can lead to a significant decrease in quality or even failure of the machine. To avoid this, the machine can be optimized robustly, i.e., considering the deviations in the machine design. Robust optimization aims to find a machine design which is robust in terms of deviations from the nominal design, i.e., to find an optimum in terms of a goal function J which does not deteriorate significantly for small changes in the design parameters p , compare Fig. 2. In this project an electric machine is simulated using isogeometric analysis and the shape of the machine shall be optimized robustly considering uncertainties, using uncertainty quantification methods like the Monte Carlo method.

Supervisors : Dr.-Ing. Melina Merkel, Prof. Dr. rer. nat. Sebastian Schöps

Selected running and previous theses

Prof. dr. rer. nat. sebastian schöps.

sebastian.schoeps@tu-...

work +49 6151 16-24409 fax +49 6151 16-24027

Work S2|17 29 Schloßgartenstr. 8 64289 Darmstadt

{{ child.heading }}

Quick access

Software Technology Group

Open Theses

Queryella: data flow analysis platform.

Bachelor Thesis, Master Thesis

Queryella is a project to extend the current state of data flow analysis for apps. To be able to combine the different types of analytics, we are building a platform that allows arbitrary compositions of such analytics. The platform will support the development of static, dynamic and hybrid analytics to evaluate apps' handling of sensitive data against current security and privacy criteria. Not only Android or iOS apps should be analyzed, but we should be able to evaluate any application or web interface in the future.

In the context of this project, we are always in search of students who have a strong interest in data flow analysis. Potential topics may include the identification of sources and sinks for sensitive data, the development of pre-analyses to reduce the runtime of the actual data flow analysis, the development of evaluation criteria for security or privacy issues, or the visualization of analysis results.

If you are looking for a topic that will have an impact on the future handling of sensitive data, do not hesitate to contact Leonid Glanz.

Examiner : Prof. Dr.-Ing. Mira Mezini

Supervisor : Dr.-Ing. Leonid Glanz

Developing RL environment for code intelligence task

Master Thesis

Current code models use text-based signals (such as next token prediction or masked language modelling) in an unsupervised setting to pretrain the models followed by fine-tuning with a labelled dataset. While this has produced good performance, it has its limitations. CodeRL, on the other hand, uses reinforcement learning with feedbacks from unit tests to train an agent to generate code given a prompt. However, unit tests don’t capture all the information about code and are not always available.

The thesis will focus on developing an environment, that gives feedback through program analysis, within which an agent can learn to perform different tasks. Prior experience with program analysis would be required to work on this thesis.

Supervisor : Abhinav Ananad, M.Sc.

Retriveal-augmented code models

State-of-the-art models for code generation and understanding, such as CodeBERT and CodeT5, are basically LLMs designed for natural language (BERT, T5) but trained on a large corpus of code. However, LLMs are known to hallucinate, i.e, they often produce sentences and information that are factually incorrect. One way to prevent, or at least reduce the impact of, hallucination in LLMs is to augment them with information retrieval.

It is currently not known if these models hallucinate when used for code intelligence tasks too. The thesis would focus on developing methods to understand hallucinations in the models. Further, explore the possibilities of retrieval-based augmentation to reduce the effect of hallucinations.

Type Inference for Tractable Probabilistic Programming

In Probabilistic Programming, dedicated programming languages provide the means to describe the structure of a stochastic process and to then use machine learning to learn the parameters of that process from data. Usually, these languages use approximate methods to ensure tractability. We can however also use exact tractable models for this task.

To this end, the set of legal programs needs to be restricted, preferably at compile time. This restriction can be seen as a type inference problem, where types represent the permitted operations and algorithms of an expression.

The topic of this thesis is to find a way to express these restrictions as a type inference problem, for example as a Hindley-Milner type system.

Supervisor : David Richter, M.Sc.

Open Analyses Library

OPAL is a comprehensive library for static analyses that is developed in Scala to facilitate the writing of a wide range of different kinds of analyses. OPAL supports the development of analyses ranging from bug/bug pattern detection up to full-scale data-flow analyses.

In the context of this project we are always searching for students who are interested in static analysis and want to implement them using Scala. Topics of interest are, e.g., to develop needed base static analyses such as Call Graph Algorithm, analyses to find security issues or to visualize software.

If you are interested in OPAL, do not hesitate to contact Dominik Helm. For further information, you can also go to The OPAL Project

Supervisors : Dr.-Ing. Dominik Helm, Tobias Roth, M.Sc.

Reengineering of Industrial C Code

Sofware based systems already play a major role in industrial production and this role will only grow in the context of Industrie 4.0. In order to solve new challenges that arise in this context, existing software has to be adapted in different directions, e.g. to enable the addition of new sensors or enable the creation of a digital twin. For this purpose, we want to uncover Software Product Line features and models, which are already present implicitly, and make them explicit. Therefore the development of corresponding analyses and automatic refactorings is necessary.

Candidates would work on different topics that enable software reuse of industrial controllers written in C.

These topics include (but are not limited to):

• automatic identification and localization of features

• automatic code slicing of identified features

• adaption of analyses to the presence of C preprocessor macros

• automatic module extraction

Supervisor : Patrick Müller, M.Sc.

Current Members
Off-Campus Students
Robot Videos
Funded Projects
Publications by Year
Publications by Type
Robot Learning Lecture
Robot Learning IP
Humanoid Robotics Seminar
Research Oberseminar
New, Open Topics
Ongoing Theses
Completed Theses
External Theses
Advice for Thesis Students
Thesis Checklist and Template
Jobs and Open Positions
Current Openings
Information for Applicants
Apply Here!
TU Darmstadt Student Hiwi Jobs
Contact Information

Currently Open Theses Topics

We offer these current topics directly for Bachelor and Master students at TU Darmstadt who can feel free to DIRECTLY contact the thesis advisor if you are interested in one of these topics. Excellent external students from another university may be accepted but are required to first email Jan Peters before contacting any other lab member for a thesis topic. Note that we cannot provide funding for any of these theses projects.

We highly recommend that you do either our robotics and machine learning lectures ( Robot Learning , Statistical Machine Learning ) or our colleagues ( Grundlagen der Robotik , Probabilistic Graphical Models and/or Deep Learning). Even more important to us is that you take both Robot Learning: Integrated Project, Part 1 (Literature Review and Simulation Studies) and Part 2 (Evaluation and Submission to a Conference) before doing a thesis with us.

In addition, we are usually happy to devise new topics on request to suit the abilities of excellent students. Please DIRECTLY contact the thesis advisor if you are interested in one of these topics. When you contact the advisor, it would be nice if you could mention (1) WHY you are interested in the topic (dreams, parts of the problem, etc), and (2) WHAT makes you special for the projects (e.g., class work, project experience, special programming or math skills, prior work, etc.). Supplementary materials (CV, grades, etc) are highly appreciated. Of course, such materials are not mandatory but they help the advisor to see whether the topic is too easy, just about right or too hard for you.

Only contact *ONE* potential advisor at the same time! If you contact a second one without first concluding discussions with the first advisor (i.e., decide for or against the thesis with her or him), we may not consider you at all. Only if you are super excited for at most two topics send an email to both supervisors, so that the supervisors are aware of the additional interest.

FOR FB16+FB18 STUDENTS: Students from other depts at TU Darmstadt (e.g., ME, EE, IST), you need an additional formal supervisor who officially issues the topic. Please do not try to arrange your home dept advisor by yourself but let the supervising IAS member get in touch with that person instead. Multiple professors from other depts have complained that they were asked to co-supervise before getting contacted by our advising lab member.

NEW THESES START HERE

Imitation Learning for High-Speed Robot Air Hockey

Scope: Master thesis Advisor: Puze Liu and Julen Urain De Jesus Start: ASAP Topic:

High-speed reactive motion is one of the fundamental capabilities of robots to achieve human-level behavior. Optimization-based methods suffer from real-time requirement when the problem is non-convex and contains constraints. Reinforcement learning requires extensive reward engineering to achieve the desired performance. Imitation learning, on the other hand, gathers human knowledge directly from data collection and enables robots to learn natural movements efficiently. In this paper, we explore how imitation learning can be performed in a complex robot Air Hockey Task. The robot needs to learn not only low-level skills, but also high-level tactics from human demonstrations.

Requirements

Strong Python programming skills
Knowledge in Machine Learning / Supervised Learning
Good Knowledge in Robotics
Experience with deep learning libraries is a plus

References * Chi, Cheng, et al. "Diffusion policy: Visuomotor policy learning via action diffusion." arXiv preprint arXiv:2303.04137 (2023). * Liu, Puze, et al. "Robot reinforcement learning on the constraint manifold." Conference on Robot Learning. PMLR (2022). * Pan, Yunpeng, et al. "Imitation learning for agile autonomous driving." The International Journal of Robotics Research 39.2-3 (2020). Interested students can apply by sending an e-mail to [email protected] and attaching the required documents mentioned above.

Walk your network: investigating neural network’s location in Q-learning methods.

Scope: Master thesis Advisor: Theo Vincent and Boris Belousov Start: Flexible Topic:

Q-learning methods are at the heart of Reinforcement Learning. They have been shown to outperform humans on some complex tasks such as playing video games [1]. In robotics, where the action space is in most cases continuous, actor-critic methods are relying on Q-learning methods to learn the critic [2]. Although Q-learning methods have been extensively studied in the past, little focus has been placed on the way the online neural network is exploring the space of Q functions. Most approaches focus on crafting a loss that would make the agent learn better policies [3]. Here, we offer a thesis that focuses on the position of the online Q neural network in the space of Q functions. The student will first investigate this idea on simple problems before comparing the performance to strong baselines such as DQN or REM [1, 4] on Atari games. Depending on the result, the student might as well get into MuJoCo and compare the results with SAC [2]. The student will be welcome to propose some ideas as well.

Highly motivated students can apply by sending an email to [email protected] . Please attach your CV and clearly state why you are interested in this topic.

Knowledge in Reinforcement Learning

References [1] Mnih, Volodymyr, et al. "Human-level control through deep reinforcement learning." nature 518.7540 (2015): 529-533. [2] Haarnoja, Tuomas, et al. "Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor." International conference on machine learning. PMLR, 2018. [3] Hessel, Matteo, et al. "Rainbow: Combining improvements in deep reinforcement learning." Proceedings of the AAAI conference on artificial intelligence. Vol. 32. No. 1. 2018. [4] Agarwal, R., Schuurmans, D. & Norouzi, M.. (2020). An Optimistic Perspective on Offline Reinforcement Learning International Conference on Machine Learning (ICML).

Co-optimizing Hand and Action for Robotic Grasping of Deformable objects

This project aims to advance deformable object manipulation by co-optimizing robot gripper morphology and control policies. The project will involve utilizing existing simulation environments for deformable object manipulation [2] and implementing a method to jointly optimize gripper morphology and grasp policies within the simulation.

Required Qualification:

Familiarity with deep learning libraries such as PyTorch or Tensorflow

Preferred Qualification:

Attendance of the lectures "Statistical Machine Learning", "Computational Engineering and Robotics" and "Robot Learning"

Application Requirements:

Curriculum Vitae
Motivation letter explaining why you would like to work on this topic and why you are the perfect candidate

Interested students can apply by sending an e-mail to [email protected] and attaching the required documents mentioned above.

References: [1] Xu, Jie, et al. "An End-to-End Differentiable Framework for Contact-Aware Robot Design." Robotics: Science & Systems. 2021. [2] Huang, Isabella, et al. "DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets." arXiv preprint arXiv:2303.16138 (2023).

Geometry-Aware Diffusion Models for Robotics

In this thesis, you will work on developing an imitation learning algorithm using diffusion models for robotic manipulation tasks, such as the ones in [2, 3, 4], but taking into account the geometry of the task space.

If this sounds interesting, please send an email to [email protected] and [email protected] , and possibly attach your CV, highlighting the relevant courses you took in robotics and machine learning.

What's in it for you:

You get to work on an exciting topic at the intersection of deep-learning and robotics
We will supervise you closely throughout your thesis
Depending on the results, we will aim for an international conference publication

Requirements:

Be motivated -- we will support you a lot, but we expect you to contribute a lot too
Robotics knowledge
Experience setting up deep learning pipelines -- from data collection, architecture design, training, and evaluation
PyTorch -- especially experience writing good parallelizable code (i.e., runs fast in the GPU)

References: [1] https://arxiv.org/abs/2112.10752 [2] https://arxiv.org/abs/2308.01557 [3] https://arxiv.org/abs/2209.03855 [4] https://arxiv.org/abs/2303.04137 [5] https://arxiv.org/abs/2205.09991

Learning Latent Representations for Embodied Agents

Interested students can apply by sending an E-Mail to [email protected] and attaching the required documents mentioned below.

Experience with TensorFlow/PyTorch
Familiarity with core Machine Learning topics
Experience programming/controlling robots (either simulated or real world)
Knowledgeable about different robot platforms (quadrupeds and bipedal robots)
Resume / CV
Cover letter explaining why this topic fits you well and why you are an ideal candidate

References: [1] Ho and Ermon. "Generative adversarial imitation learning" [2] Arenz, et al. "Efficient Gradient-Free Variational Inference using Policy Search"

Characterizing Fear-induced Adaptation of Balance by Inverse Reinforcement Learning

Interested students can apply by sending an E-Mail to [email protected] and attaching the required documents mentioned below.

Basic knowledge of reinforcement learning
Hand-on experience with reinforcement learning or inverse reinforcement learning
Cognitive science background

References: [1] Maki, et al. "Fear of Falling and Postural Performance in the Elderly" [2] Davis et al. "The relationship between fear of falling and human postural control" [3] Ho and Ermon. "Generative adversarial imitation learning"

Timing is Key: CPGs for regularizing Quadruped Gaits learned with DRL

To tackle this problem we want to utilize Central Pattern Generators (CPGs), which can generate timings for ground contacts for the four feet. The policy gets rewarded for complying with the contact patterns of the CPGs. This leads to a straightforward way of regularizing and steering the policy to a natural gait without posing too strong restrictions on it. We first want to manually find fitting CPG parameters for different gait velocities and later move to learning those parameters in an end-to-end fashion.

Highly motivated students can apply by sending an E-Mail to [email protected] and attaching the required documents mentioned below.

Minimum Qualification:

Good Python programming skills
Basic knowledge of the PyTorch library
Basic knowledge of Reinforcement Learning
Good knowledge of the PyTorch library
Basic knowledge of the MuJoCo simulator

References: [1] Cheng, Xuxin, et al. "Extreme Parkour with Legged Robots."

Damage-aware Reinforcement Learning for Deformable and Fragile Objects

Goal of this thesis will be the development and application of a model-based reinforcement learning method on real robots. Your tasks will include: 1. Setting up a simulation environment for deformable object manipulation 2. Utilizing existing models for stress and deformability prediction[1] 3. Implementing a reinforcement learning method to work in simulation and, if possible, on the real robot methods.

If you are interested in this thesis topic and believe you possess the necessary skills and qualifications, please submit your application, including a resume and a brief motivation letter explaining your interest and relevant experience. Please send your application to [email protected].

Required Qualification :

Enthusiasm for and experience in robotics, machine learning, and simulation
Strong programming skills in Python

Desired Qualification :

Attendance of the lectures "Statistical Machine Learning", "Computational Engineering and Robotics" and (optionally) "Robot Learning"

References: [1] Huang, I., Narang, Y., Bajcsy, R., Ramos, F., Hermans, T., & Fox, D. (2023). DefGraspNets: Grasp Planning on 3D Fields with Graph Neural Nets. arXiv preprint arXiv:2303.16138.

Imitation Learning meets Diffusion Models for Robotics

The objective of this thesis is to build upon prior research [2, 3] to establish a connection between Diffusion Models and Imitation Learning. We aim to explore how to exploit Diffusion Models and improve the performance of Imitation learning algorithms that interact with the world.

We welcome highly motivated students to apply for this opportunity by sending an email expressing their interest to Firas Al-Hafez ( [email protected] ) Julen Urain ( [email protected] ). Please attach your letter of motivation and CV, and clearly state why you are interested in this topic and why you are the ideal candidate for this position.

Required Qualification : 1. Strong Python programming skills 2. Basic Knowledge in Imitation Learning 3. Interest in Diffusion models, Reinforcement Learning

Desired Qualification : 1. Attendance of the lectures "Statistical Machine Learning", "Computational Engineering and Robotics" and/or "Reinforcement Learning: From Fundamentals to the Deep Approaches"

References: [1] Song, Yang, and Stefano Ermon. "Generative modeling by estimating gradients of the data distribution." Advances in neural information processing systems 32 (2019). [2] Ho, Jonathan, and Stefano Ermon. "Generative adversarial imitation learning." Advances in neural information processing systems 29 (2016). [3] Garg, D., Chakraborty, S., Cundy, C., Song, J., & Ermon, S. (2021). Iq-learn: Inverse soft-q learning for imitation. Advances in Neural Information Processing Systems, 34, 4028-4039. [4] Chen, R. T., & Lipman, Y. (2023). Riemannian flow matching on general geometries. arXiv preprint arXiv:2302.03660.

Be extremely motivated -- we will support you a lot, but we expect you to contribute a lot too

Scaling Behavior Cloning to Humanoid Locomotion

Scope: Bachelor / Master thesis Advisor: Joe Watson Added: 2023-10-07 Start: ASAP Topic: In a previous project [1], I found that behavior cloning (BC) was a surprisingly poor baseline for imitating humanoid locomotion. I suspect the issue may lie in the challenges of regularizing high-dimensional regression.

The goal of this project is to investigate BC for humanoid imitation, understand the scaling issues present, and evaluate possible solutions, e.g. regularization strategies from the regression literature.

The project will be building off Google Deepmind's Acme library [2], which has BC algorithms and humanoid demonstration datasets [3] already implemented, and will serve as the foundation of the project.

To apply, email [email protected] , ideally with a CV and transcript so I can assess your suitability.

Experience, interest and enthusiasm for the intersection of robot learning and machine learning
Experience with Acme and JAX would be a benefit, but not necessary

References: [1] https://arxiv.org/abs/2305.16498 [2] https://github.com/google-deepmind/acme [3] https://arxiv.org/abs/2106.00672

Robot Gaze for Communicating Collision Avoidance Intent in Shared Workspaces

Scope: Bachelor/Master thesis Advisor: Alap Kshirsagar , Dorothea Koert Added: 2023-09-27 Start: ASAP

Topic: In order to operate close to non-experts, future robots require both an intuitive form of instruction accessible to lay users and the ability to react appropriately to a human co-worker. Instruction by imitation learning with probabilistic movement primitives (ProMPs) [1] allows capturing tasks by learning robot trajectories from demonstrations including the motion variability. However, appropriate responses to human co-workers during the execution of the learned movements are crucial for fluent task execution, perceived safety, and subjective comfort. To facilitate such appropriate responsive behaviors in human-robot interaction, the robot needs to be able to react to its human workspace co-inhabitant online during the execution. Also, the robot needs to communicate its motion intent to the human through non-verbal gestures such as eye and head gazes [2][3]. In particular for humanoid robots, combining motions of arms with expressive head and gaze directions is a promising approach that has not yet been extensively studied in related work.

Goals of the thesis:

Develop a method to combine robot head/gaze motion with ProMPs for online collision avoidance
Implement the method on a Franka-Emika Panda Robot
Evaluate and compare the implemented behaviors in a study with human participants

Highly motivated students can apply by sending an email to [email protected]. Please attach your CV and transcript, and clearly state your prior experiences and why you are interested in this topic.

Strong Programming Skills in python
Prior experience with Robot Operating System (ROS) and user studies would be beneficial
Strong motivation for human-centered robotics including design and implementation of a user study

References : [1] Koert, Dorothea, et al. "Learning intention aware online adaptation of movement primitives." IEEE Robotics and Automation Letters 4.4 (2019): 3719-3726. [2] Admoni, Henny, and Brian Scassellati. "Social eye gaze in human-robot interaction: a review." Journal of Human-Robot Interaction 6.1 (2017): 25-63. [3] Lemasurier, Gregory, et al. "Methods for expressing robot intent for human–robot collaboration in shared workspaces." ACM Transactions on Human-Robot Interaction (THRI) 10.4 (2021): 1-27.

Tactile Sensing for the Real World

Topic: Tactile sensing is a crucial sensing modality that allows humans to perform dexterous manipulation[1]. In recent years, the development of artificial tactile sensors has made substantial progress, with current models relying on cameras inside the fingertips to extract information about the points of contact [2]. However, robotic tactile sensing is still a largely unsolved topic despite these developments. A central challenge of tactile sensing is the extraction of usable representations of sensor readings, especially since these generally contain an incomplete view of the environment.

Recent model-based reinforcement learning methods like Dreamer [3] leverage latent state-space models to reason about the environment from partial and noisy observations. However, more work has yet to be done to apply such methods to real-world manipulation tasks. Hence, this thesis will explore whether Dreamer can solve challenging real-world manipulation tasks by leveraging tactile information. Initial results suggest that tasks like peg-in-a-hole can indeed be solved with Dreamer in simulation (see figure above), but the applicability of this method in the real world has yet to be shown.

In this work, you will work with state-of-the-art hardware and compute resources on a hot research topic with the option of publishing your work at a scientific conference.

Highly motivated students can apply by sending an email to [email protected]. Please attach a transcript of records and clearly state your prior experiences and why you are interested in this topic.

Ideally experience with deep learning libraries like JAX or PyTorch
Experience with reinforcement learning is a plus
Experience with Linux

References [1] 2S Match Anest2, Roland Johansson Lab (2005), https://www.youtube.com/watch?v=HH6QD0MgqDQ [2] Gelsight Inc., Gelsight Mini, https://www.gelsight.com/gelsightmini/ [3] Hafner, D., Lillicrap, T., Ba, J., & Norouzi, M. (2019). Dream to control: Learning behaviors by latent imagination. arXiv preprint arXiv:1912.01603.

Large Vision-Language Neural Networks for Open-Vocabulary Robotic Manipulation

Robots are expected to soon leave their factory/laboratory enclosures and operate autonomously in everyday unstructured environments such as households. Semantic information is especially important when considering real-world robotic applications where the robot needs to re-arrange objects as per a set of language instructions or human inputs (as shown in the figure). Many sophisticated semantic segmentation networks exist [1]. However, a challenge when using such methods in the real world is that the semantic classes rarely align perfectly with the language input received by the robot. For instance, a human language instruction might request a ‘glass’ or ‘water’, but the semantic classes detected might be ‘cup’ or ‘drink’.

Nevertheless, with the rise of large language and vision-language models, we now have capable segmentation models that do not directly predict semantic classes but use learned associations between language queries and classes to give us ’open-vocabulary’ segmentation [2]. Some models are especially powerful since they can be used with arbitrary language queries.

In this thesis, we aim to build on advances in 3D vision-based robot manipulation and large open-vocabulary vision models [2] to build a full pick-and-place pipeline for real-world manipulation. We also aim to find synergies between scene reconstruction and semantic segmentation to determine if knowing the object semantics can aid the reconstruction of the objects and, in turn, aid manipulation.

Highly motivated students can apply by sending an e-mail expressing their interest to Snehal Jauhri (email: [email protected]) or Ali Younes (email: [email protected]), attaching your letter of motivation and possibly your CV.

Topic in detail : Thesis_Doc.pdf

Requirements: Enthusiasm, ambition, and a curious mind go a long way. There will be ample supervision provided to help the student understand basic as well as advanced concepts. However, prior knowledge of computer vision, robotics, and Python programming would be a plus.

References: [1] Y. Wu, A. Kirillov, F. Massa, W.-Y. Lo, and R. Girshick, “Detectron2”, https://github.com/facebookresearch/detectron2 , 2019. [2] F. Liang, B. Wu, X. Dai, K. Li, Y. Zhao, H. Zhang, P. Zhang, P. Vajda, and D. Marculescu, “Open-vocabulary semantic segmentation with mask-adapted clip,” in CVPR, 2023, pp. 7061–7070, https://github.com/facebookresearch/ov-seg

Dynamic Tiles for Deep Reinforcement Learning

Linear approximators in Reinforcement Learning are well-studied and come with an in-depth theoretical analysis. However, linear methods require defining a set of features of the state to be used by the linear approximation. Unfortunately, the feature construction process is a particularly problematic and challenging task. Deep Reinforcement learning methods have been introduced to mitigate the feature construction problem: these methods do not require handcrafted features, as features are extracted automatically by the network during learning, using gradient descent techniques.

In simple reinforcement learning tasks, however, it is possible to use tile coding as features: Tiles are simply a convenient discretization of the state space that allows us to easily control the generalization capabilities of the linear approximator. The objective of this thesis is to design a novel algorithm for automatic feature extraction that generates a set of features similar to tile coding, but that can arbitrarily partition the state space and deal with arbitrary complex state space, such as images. The idea is to combine the feature extraction problem directly with Linear Reinforcement Learning methods, defining an algorithm that is able both to have the theoretical guarantees and good convergence properties of these methods and the flexibility of Deep Learning approaches.

Curriculum Vitae (CV);
A motivation letter explaining the reason for applying for this thesis and academic/career objectives.

Minimum knowledge

Good Python programming skills;
Basic knowledge of Reinforcement Learning.

Preferred knowledge

Knowledge of the PyTorch library;
Knowledge of the Atari environments (ale-py library).
Knowledge of the MushroomRL library.

Accepted candidate will

Define a generalization of tile coding working with an arbitrary input set (including images);
Design a learning algorithm to adapt the tiles using data of interaction with the environment;
Combine feature learning with standard linear methods for Reinforcement Learning;
Verify the novel methodology in simple continuous state and discrete actions environments;
(Optionally) Extend the experimental analysis to the Atari environment setting.

Deep Learning Meets Teleoperation: Constructing Learnable and Stable Inductive Guidance for Shared Control

This work considers policies as learnable inductive guidance for shared control. In particular, we use the class of Riemannian motion policies [3] and consider them as differentiable optimization layers [4]. We analyze (i) if RMPs can be pre-trained by learning from demonstrations [5] or reinforcement learning [6] given a specific context; (ii) and subsequently employed seamlessly for human-guided teleoperation thanks to their physically consistent properties, such as stability [3]. We believe this step eliminates the laborious process of constructing complex policies and leads to improved and generalizable shared control architectures.

Highly motivated students can apply by sending an e-mail expressing your interest to [email protected] and [email protected] , attaching your letter of motivation and possibly your CV.

Experience with deep learning libraries (in particular Pytorch)
Knowledge in reinforcement learning and/or machine learning

References: [1] Niemeyer, Günter, et al. "Telerobotics." Springer handbook of robotics (2016); [2] Selvaggio, Mario, et al. "Autonomy in physical human-robot interaction: A brief survey." IEEE RAL (2021); [3] Cheng, Ching-An, et al. "RMP flow: A Computational Graph for Automatic Motion Policy Generation." Springer (2020); [4] Jaquier, Noémie, et al. "Learning to sequence and blend robot skills via differentiable optimization." IEEE RAL (2022); [5] Mukadam, Mustafa, et al. "Riemannian motion policy fusion through learnable lyapunov function reshaping." CoRL (2020); [6] Xie, Mandy, et al. "Neural geometric fabrics: Efficiently learning high-dimensional policies from demonstration." CoRL (2023).

Dynamic symphony: Seamless human-robot collaboration through hierarchical policy blending

This work focuses on arbitration between the user and assistive policy, i.e., shared autonomy. Various works allow the user to influence the dynamic behavior explicitly and, therefore, could not satisfy stability guarantees [3]. We pursue the idea of formulating arbitration as a trajectory-tracking problem that implicitly considers the user's desired behavior as an objective [4]. Therefore, we extend the work of Hansel et al. [5], who employed probabilistic inference for policy blending in robot motion control. The proposed method corresponds to a sampling-based online planner that superposes reactive policies given a predefined objective. This method enables the user to implicitly influence the behavior without injecting energy into the system, thus satisfying stability properties. We believe this step leads to an alternative view of shared autonomy with an improved and generalizable framework.

Highly motivated students can apply by sending an e-mail expressing your interest to [email protected] or [email protected] , attaching your letter of motivation and possibly your CV.

References: [1] Niemeyer, Günter, et al. "Telerobotics." Springer handbook of robotics (2016); [2] Selvaggio, Mario, et al. "Autonomy in physical human-robot interaction: A brief survey." IEEE RAL (2021); [3] Dragan, Anca D., and Siddhartha S. Srinivasa. "A policy-blending formalism for shared control." IJRR (2013); [4] Javdani, Shervin, et al. "Shared autonomy via hindsight optimization for teleoperation and teaming." IJRR (2018); [5] Hansel, Kay, et al. "Hierarchical Policy Blending as Inference for Reactive Robot Control." IEEE ICRA (2023).

Feeling the Heat: Igniting Matches via Tactile Sensing and Human Demonstrations

In this thesis, we want to investigate the effectiveness of vision-based tactile sensors for solving dynamic tasks (igniting matches). Since the whole task is difficult to simulate, we directly collect real-world data to learn policies from the human demonstrations [2,3]. We believe that this work is an important step towards more advanced tactile skills.

Highly motivated students can apply by sending an e-mail expressing your interest to [email protected] and [email protected] , attaching your letter of motivation and possibly your CV.

Good knowledge of Python
Prior experience with real robots and Linux is a plus

References: [1] https://www.youtube.com/watch?v=HH6QD0MgqDQ [2] Learning Compliant Manipulation through Kinesthetic and Tactile Human-Robot Interaction; Klas Kronander and Aude Billard. [3] https://www.youtube.com/watch?v=jAtNvfPrKH8

Inverse Reinforcement Learning for Neuromuscular Control of Humanoids

Within this thesis, the problems of learning from observations and efficient exploration in overactued systems should be addressed. Regarding the former, novel methods incorporating inverse dynamics models into the inverse reinforcement learning problem [1] should be adapted and applied. To address the problem of efficient exploration in overactuted systems, two approaches should be implemented and compared. The first approach uses a handcrafted action space, which disables and modulates actions in different phases of the gait based on biomechanics knowledge [2]. The second approach uses a stateful policy to incorporate an inductive bias into the policy [3]. The thesis will be supervised in conjunction with Guoping Zhao ( [email protected] ) from the locomotion lab.

Highly motivated students can apply by sending an e-mail expressing their interest to Firas Al-Hafez ( [email protected] ), attaching your letter of motivation and possibly your CV. Try to make clear why you would like to work on this topic, and why you would be the perfect candidate for the latter.

Required Qualification : 1. Strong Python programming skills 2. Knowledge in Reinforcement Learning 3. Interest in understanding human locomotion

Desired Qualification : 1. Hands-on experience on robotics-related RL projects 2. Prior experience with different simulators 3. Attendance of the lectures "Statistical Machine Learning", "Computational Engineering and Robotics" and/or "Reinforcement Learning: From Fundamentals to the Deep Approaches"

References: [1] Al-Hafez, F.; Tateo, D.; Arenz, O.; Zhao, G.; Peters, J. (2023). LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning, International Conference on Learning Representations (ICLR). [2] Ong CF; Geijtenbeek T.; Hicks JL; Delp SL (2019) Predicting gait adaptations due to ankle plantarflexor muscle weakness and contracture using physics-based musculoskeletal simulations. PLoS Computational Biology [3] Srouji, M.; Zhang, J:;Salakhutdinow, R. (2018) Structured Control Nets for Deep Reinforcement Learning, International Conference on Machine Learning (ICML)

Robotic Tactile Exploratory Procedures for Identifying Object Properties

Goals of the thesis

Literature review of robotic EPs for identifying object properties [2,3,4]
Develop and implement robotic EPs for a Digit tactile sensor
Compare performance of robotic EPs with human EPs

Desired Qualifications

Interested in working with real robotic systems
Python programming skills

Literature [1] Lederman and Klatzky, “Haptic perception: a tutorial” [2] Seminara et al., “Active Haptic Perception in Robots: A Review” [3] Chu et al., “Using robotic exploratory procedures to learn the meaning of haptic adjectives” [4] Kerzel et al., “Neuro-Robotic Haptic Object Classification by Active Exploration on a Novel Dataset”

Scaling learned, graph-based assembly policies

scaling our previous methods to incorporate mobile manipulators or the Kobo bi-manual manipulation platform. The increased workspace of both would allow for handling a wider range of objects
[2] has shown more powerful, yet, it includes running a MILP for every desired structure. Thus another idea could be to investigate approaches aiming to approximate this solution
adapting the methods to handle more irregular-shaped objects / investigate curriculum learning

Highly motivated students can apply by sending an e-mail expressing your interest to [email protected] , attaching your letter of motivation and possibly your CV.

Experience with deep learning libraries (in particular Pytorch) is a plus
Experience with reinforcement learning / having taken Robot Learning is also a plus

References: [1] Learn2Assemble with Structured Representations and Search for Robotic Architectural Construction; Niklas Funk et al. [2] Graph-based Reinforcement Learning meets Mixed Integer Programs: An application to 3D robot assembly discovery; Niklas Funk et al. [3] Structured agents for physical construction; Victor Bapst et al.

Long-Horizon Manipulation Tasks from Visual Imitation Learning (LHMT-VIL): Algorithm

The proposed architecture can be broken down into the following sub-tasks: 1. Multi-object 6D pose estimation from video: Identify the object 6D poses in each video frame to generate the object trajectories 2. Action segmentation from video: Classify the action being performed in each video frame 3. High-level task representation learning: Learn the sequence of robotic movement primitives with the associated object poses such that the robot completes the demonstrated task 4. Low-level movement primitives: Create a database of low-level robotic movement primitives which can be sequenced to solve the long-horizon task

Desired Qualification: 1. Strong Python programming skills 2. Prior experience in Computer Vision and/or Robotics is preferred

Long-Horizon Manipulation Tasks from Visual Imitation Learning (LHMT-VIL): Dataset

During the project, we will create a large-scale dataset of videos of humans demonstrating industrial assembly sequences. The dataset will contain information of the 6D poses of the objects, the hand and body poses of the human, the action sequences among numerous other features. The dataset will be open-sourced to encourage further research on VIL.

[1] F. Sener, et al. "Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities". CVPR 2022. [2] P. Sharma, et al. "Multiple Interactions Made Easy (MIME) : Large Scale Demonstrations Data for Imitation." CoRL, 2018.

Adaptive Human-Robot Interactions with Human Trust Maximization

Good knowledge of Python and/or C++;
Good knowledge in Robotics and Machine Learning;
Good knowledge of Deep Learning frameworks, e.g, PyTorch;

References: [1] Xu, Anqi, and Gregory Dudek. "Optimo: Online probabilistic trust inference model for asymmetric human-robot collaborations." ACM/IEEE HRI, IEEE, 2015; [2] Kwon, Minae, et al. "When humans aren’t optimal: Robots that collaborate with risk-aware humans." ACM/IEEE HRI, IEEE, 2020; [3] Chen, Min, et al. "Planning with trust for human-robot collaboration." ACM/IEEE HRI, IEEE, 2018; [4] Poole, Ben et al. “On variational bounds of mutual information”. ICML, PMLR, 2019.

Causal inference of human behavior dynamics for physical Human-Robot Interactions

Highly motivated students can apply by sending an e-mail expressing your interest to [email protected] , attaching your a letter of motivation and possibly your CV.

Good knowledge of Robotics;
Good knowledge of Deep Learning frameworks, e.g, PyTorch
Li, Q., Chalvatzaki, G., Peters, J., Wang, Y., Directed Acyclic Graph Neural Network for Human Motion Prediction, 2021 IEEE International Conference on Robotics and Automation (ICRA).
Löwe, S., Madras, D., Zemel, R. and Welling, M., 2020. Amortized causal discovery: Learning to infer causal graphs from time-series data. arXiv preprint arXiv:2006.10833.
Yang, W., Paxton, C., Mousavian, A., Chao, Y.W., Cakmak, M. and Fox, D., 2020. Reactive human-to-robot handovers of arbitrary objects. arXiv preprint arXiv:2011.08961.

Incorporating First and Second Order Mental Models for Human-Robot Cooperative Manipulation Under Partial Observability

Scope: Master Thesis Advisor: Dorothea Koert , Joni Pajarinen Added: 2021-06-08 Start: ASAP

The ability to model the beliefs and goals of a partner is an essential part of cooperative tasks. While humans develop theory of mind models for this aim already at a very early age [1] it is still an open question how to implement and make use of such models for cooperative robots [2,3,4]. In particular, in shared workspaces human robot collaboration could potentially profit from the use of such models e.g. if the robot can detect and react to planned human goals or a human's false beliefs during task execution. To make such robots a reality, the goal of this thesis is to investigate the use of first and second order mental models in a cooperative manipulation task under partial observability. Partially observable Markov decision processes (POMDPs) and interactive POMDPs (I-POMDPs) [5] define an optimal solution to the mental modeling task and may provide a solid theoretical basis for modelling. The thesis may also compare related approaches from the literature and setup an experimental design for evaluation with the bi-manual robot platform Kobo.

Highly motivated students can apply by sending an e-mail expressing your interest to [email protected] attaching your CV and transcripts.

References:

Wimmer, H., & Perner, J. Beliefs about beliefs: Representation and constraining function of wrong beliefs in young children's understanding of deception (1983)
Sandra Devin and Rachid Alami. An implemented theory of mind to improve human-robot shared plans execution (2016)
Neil Rabinowitz, Frank Perbet, Francis Song, Chiyuan Zhang, SM Ali Eslami,and Matthew Botvinick. Machine theory of mind (2018)
Connor Brooks and Daniel Szafir. Building second-order mental models for human-robot interaction. (2019)
Prashant Doshi, Xia Qu, Adam Goodie, and Diana Young. Modeling recursive reasoning by humans using empirically informed interactive pomdps. (2010)

{{ child.heading }}

Quick access

Optimization

Master Theses

Master theses in discrete optimization.

A Master Thesis in the field Discrete Optimization deals with specific questions coming from integer programming, graph theory or topics on polyhedra. It aims at independently analyzing mathematical properties of optimization algorithms or their underlying structures.

For planning the thesis, the following steps are crucial. In a first meeting, student and professor agree on a topic. Subsequently, the student has 4-6 weeks time to read up on the subject and to search the literature. Then the thesis is formally registered in the office of student affairs. A TeX-template is available in the Downloads section of the department’s website. Alternatively, you can use the template of the course “ Arbeitstechniken ” from winter term 2015/16. While writing the thesis it is strongly recommended to keep contact with your supervisor at least once per month. Approximately one month before submission you should meet with your supervisor!

Requirements

Having passed the exams to the courses “Introduction to Optimization” and “Discrete Optimization” or “Nonlinear Optimization” is mandatory. Furthermore, it is recommended to actively attend an optimization seminar.

Prof. Pfetsch , Prof. Disser and staff members of the research group

Discrete Optimization of Gate Locations for Injection Molding of Seals for E-Mobility Applications (Prof. Pfetsch)
An application of tash-based shift-generation and workload assignment in the retail industry (Prof. Pfetsch)
Analysis of 0/1 sparse recovery problems and the application of lattice based reformulations (Prof. Pfetsch)
Utilizing Transformers in Information Set Monte Carlo Tree Search (Prof. Pfetsch)
Collision Avoidance of Rrailway Networks (Prof. Pfetsch)
Minimizing the effects of delays in rail traffic (Prof. Pfetsch)
Minimum Coverage by Convex Polygons (Prof. Pfetsch)
Generation of synthetic embryo data using Generative Adversarial Networks (GANs) (- with SimulaMet Oslo) (Prof. Pfetsch)
Anomalie Detection in the Results of Integrated Circuits Testing (Prof. Pfetsch)
Minimum Partition of Geometric Graphs into Plane Subgraphs (Prof. Pfetsch)
Solving semidefinite Programs with one Variable (Prof. Pfetsch)
A Benders Decomposition Approach to Correlation Clustering (Prof. Pfetsch)
Integer Programming Boosing for Classification (Prof. Pfetsch)
Compressed Sensing and Neural Networks (Prof. Pfetsch)
Decision Regions of artificial neural networks with ReLU-activation (Prof. Pfetsch)
Minimum Convexe Partitions (Prof. Pfetsch)
An ILP model for coordinated motion planning (Prof. Pfetsch)
Exact Rule Learning via Boolean Compressed Sensing (Prof. Pfetsch)
A solution for the “Integrated Time Tabling and Vehicle Scheduling”-problem (Prof. Pfetsch)
Global optimization with artificial neutral networks embedded (Prof. Pfetsch)
Facial reduction on binary semidefinite programs (Prof. Pfetsch)
Robust Optimization under Limited Resources – A Two-Stage Project Scheduling Problem under Uncertain Activity Durations for Shipbuilding Production Planning (Prof. Pfetsch)
Timetable optimization for a predetermined total delay time (Prof. Pfetsch)
Dial-a-Ride under restricted information model (Prof. Disser)
Bayesian Optimization on mixed domains for applications in chemical research (Prof. Pfetsch)
Reconstruction of lo- and l1-solutions for the analysis case (Prof. Pfetsch)
Evacuation on m Rays with k Searchers (Prof. Disser)
Kollaborative Auslieferung auf festem Pfad (Prof. Disser)
Preservation of graph properties under color refinement (Prof. Disser)
Incremental Maximization: Competitive Solutions and Improved Lower Bounds (Prof. Disser)
Topology optimization of gas networks (Prof. Pfetsch)
A Column Generation Approach for Logistic Networks with Tree Constraints (Prof. Pfetsch)
Optimal Decision Trees for Binary Data (Prof. Pfetsch)
Bit-cost analysis, implementation and empirical evaluation of the Fast Multiple Method for Trummer's Problem (Prof. Pfetsch)
Energy Efficient High-Rise Water Supply System (Prof. Pfetsch)
Generalized mixed-integer rounding cuts and disjunctions (Prof. Pfetsch)
Evaluation of Reingold's Algorithm for st-connectivity in log-space (Prof. Disser)
The graph exploration problem: A competitive analysis of various algorithms (Prof. Disser)
TSP, TRP and Dial-a-Ride on the Circle (Prof. Disser)
{0,1/2}-Schnitte für binäre lineare Codes (Prof. Pfetsch)
Disjunktive Schnittebenen für Kardinalitätsrestriktionen (Prof. Pfetsch)
Lösung von zeitexpandierten Fahrplanerzeugungsmodellen mittels Spaltengenerierung (Prof. Pfetsch)
Alternative Modelle zur periodischen Fahrplanoptimierung (Prof. Pfetsch)
Graphical Models with Total Cardinality Constraint (Prof. Pfetsch)
Kürzeste Wege und Flüsse unter Kardinalitätsrestriktionen (Prof. Pfetsch)
Approximation des Motorized Traveling Salesman Problems (Prof. Pfetsch)
Application of column generation to interview scheduling at konaktiva job fair (Prof. Pfetsch)
Transportoptimierung im Hauptlauf der Paketlogistik (Prof. Pfetsch)
Analyzing discrete decisions in gas networks (Prof. Pfetsch)
Shortest Path with Conflicts (Prof. Pfetsch)
Optimale Pausenplanung von LKW-Fahrern mit integrierter Parkplatzwahl (Prof. Pfetsch)
Rekonstruktion dünnbesetzter Lösungen mit Ganzzahligkeitsbedingungen (Prof. Pfetsch)
Integrality Aspects of Sparse Recovery via 1-Minimization (Prof. Pfetsch)
Synthesis of a Hydrostatic Power Transmission System using MINLP (Prof. Pfetsch)
Ein kombinatorischer Branch-and-Bound-Algorithmus für die Berechnung der Restricted Isometry Konstanten (Prof. Pfetsch)
Über die Aussagekraft von Rankings (Prof. Pfetsch)
Sherali-Adams Relaxierungen von Graphenisomorphie-Polytopen (Prof. Pfetsch)
Gemischt-ganzzahlige Optimierungsmethoden für Klassifikationsprobleme (Prof. Pfetsch)
Extended formulations and symmetry handling (Prof. Pfetsch)
Schnittebenenverfahren zur Optimierung submodularer Funktionen (Prof. Pfetsch)
Holes in mixed integer problems (Prof. Pfetsch)
Lösungsmethoden für das 3-dimensionale Packungsproblem mit Nebenbedingungen (Prof. Pfetsch)
Discrete tomography with sparse gradients (Prof. Pfetsch)
Kombinierte Optimierung von Zugrouten und Fahrplänen mit Orientierungsbedingungen (Prof. Pfetsch)
Analyse von XOR-Polytopen (Prof. Pfetsch)
Solving Linear Programs with Complementarity Constraints Using an Indicator Approach (Prof. Pfetsch)
Standortplanung und Netzwerkdesign im kombinierten Güterverkehr (Prof. Pfetsch)
Wahrscheinlichkeitsrestriktionen durch Überdeckungsformulierung (Prof. Pfetsch)
Untersuchung des elementaren Abschlusses von {0,1/2}-Ungleichungen (Prof. Pfetsch)
Modelle für das Störungsmanagement im ÖPNV (Prof. Pfetsch)
Linienplanung auf speziellen zugrundeliegenden Netzstrukturen (Prof. Pfetsch)
Graphenclustering auf medizinischen Netzwerken (Prof. Pfetsch)
Ressourceneinsatzplanung im Projektmanagement (Prof. Pfetsch)
Polyhedral description of star colourings (Prof. Pfetsch)
Semidefinite Relaxierungen für RIP und NSP im Compressed Sensing (Prof. Pfetsch)
Evaluierung und Erweiterung geometrischer Schnittebenen (Prof. Pfetsch)
Konstruktion von dünn besetzten Sensing-Matrizen (Prof. Pfetsch)

Constanze Drechsel

Secretary of the optimization group.

drechsel@mathematik.tu-...

work +49 6151 16-23444 fax +49 6151 16-23445

Work S4|10 138 Dolivostraße 15 64293 Darmstadt

{{ child.heading }}

Quick access

Exchange programmes

Studying at tu darmstadt.

back to list

Writing a Bachelor or Master Thesis at TU Darmstadt

If you are planning to write a Bachelor or a Master thesis at TU Darmstadt, you have to find a supervising professor at TU beforehand. For information please have a look at our website of the departments at TU Darmstadt and contact the prospective professor. As soon as you have found a supervisor at TU Darmstadt, please inform us at europe-incomings@zv.tu-… communicating us the name and email address of her/him. This document (opens in new tab) has to be signed by your prospective supervisor. The completed form can also be submitted as soon as you are in Darmstadt. Your supervisor can exempt you from any language requirements.

In the Department for Architecture, it is not possible for international exchange students to write a Bachelor or Master thesis there.

Important Information: A Bachelor or Master Thesis is only supervised at TU Darmstadt. The final grading takes place at the home university.

Internationale Beziehungen und Mobilität International Relations & Mobility

Work S1|01 Karolinenplatz 5 64289 Darmstadt

Tanja Torres Alberich

tanja.torres@tu-...

work +49 6151 16-24061 fax +49 6151 16-24052

Work S1|01 514 Karolinenplatz 5 64289 Darmstadt

Region Europe

Europe Incomings: For more information please contact us under europe-incomings@zv.tu-…

Europe Work-Placement (Internship): For more information please contact us under europe-internships@zv.tu-…

{{ child.heading }}

Quick access

Institute of Applied Geosciences

Master's Theses

Research topics of trophee master's theses.

List of topics of recent master's theses, to give an idea on the research topics that our students work on.

Provenance of Quaternary deposits in the Upper Rhine Graben: Insights from detrital garnet geochemistry in the Viernheim drill core
Analysis of the wastewater management concept of an industrial park and development of an online visualization tool for its optimization
Temporal and spatial trends of C and O isotopes in loess deposits of South Germany
Determination and statistical analysis of PAH in soils of the Canary Islands
Analysis of polycyclic aromatic hydrocarbons (PAHs) in groundwater samples from a tar oil contaminated site – Determination of source areas and degradation potential
Geochemical and petrophysical logging of the well “Kraichgau 1002” across the Permic Triassic boundary
Evaluation of methods for the characterization of different groundwater contamination sources in an existing polycyclic aromatic hydrocarbon contamininant plume
Immobilization of lead in contaminated soils in Matehuala, San Luis Potosi, Mexico to reduce environmental risk
Modeling the potential of green infrastructure to reduce runoff at the micro-watershed level in Costa Rica
Provenance of Quaternary deposits in the upper Rhine graben: Insights from detrital garnet geochemistry in the drill core 'Pfungstadt GWM 1.3
Development of an Interactive WebGIS Platform for the Visualization of a 3D Hydrogeological Model, Bandung Basin, Indonesia
Sorption isotherms of BTEX compounds on biochars derived from different feedstocks
High resolution determination of stable isotopes and inorganic parameters in rainfall samples from the darmstadt area
Determination of Arsenic and Uranium concentrations in Surface and Groundwater system from the Cox`s Bazar area, Bangladesh
Gadolinium anomalies in river waters influenced by discharge of waste water treatment plants, south Hesse, Germany
Sinkholes in the Eastern Part of Hessen (Germany) – GIS based mapping and interpretation
Water Flow and Reactive Nitrate Transport Modeling in the Unsaturated Zone at a reference site in the Hessian Ried
Development of a low cost and socially accepted in situ solution of an ecological greywater treatment in Flores, Costa Rica
Sinkhole detection and analysis using GIS and Python – a case study from Eastern Hesse
Upscaling of Geomechanical properties in layered rock
Global analysis of the relationship between vegetation and transit times of water in the subsurface using literature date on stable water isotopes
Determination of Polycyclic Aromatic Hydrocarbons (PAHs) and Polychlorinated Biphenyls (PCBs) in Soils of Samos (Greece) and Iceland
Hydrochemical investigation of River Lahn and its tributaries to analyse spatial variability of water quality with respect to natural background and anthropogenic impacts
Sinkholes Detection in the Eastern part of Hessen (Germany), GIS-based mapping and Interpretation
Analysis of the spatial and temporal distribution of stable isotopes and their driving factors in the Upper Claro River Basin, Colombian Andes
Isotopic Fractionation During Degradation of Chlorination Byproducts in Water-Laboratory Experiments
Hydrological Investigation of a Thermal Anomaly on the Groundwater of Tarail Upazila, Kishoreganj, Bangladesh
Petrophysical analysis of the drill cores TB1 and TB2 in the Rotliegend Group (Lower Langen Formation), Sprendlinger Horst
Analyse und Bewertung von Abfall- und nebenprodukten der chemischen Industrie – Sustainable Waste Management
Sorption of Carbamazepine, Ibuprofen & Sulfamethoxazole on soil and isolated biomass in column experiment
Erstellen eines Konditionierungskonzepts und Durchführung von Vorversuchen zur Auswahl der geeigneten Mittel für einen maschinellen Vortrieb mittels EPB Schildmaschine in Frankfurt
Landslide Susceptibility Mapping using Statistical Analysis and GIS-Case study: Steinau an der Strasse, Germany
Erstellen eines Excel-basierten Werkzeugs zur Abschätzung der wahrscheinlichen Sanierungsdauer bei Pump-and-Treat Sanierungen
Preparation of an Excel-based tool for the estimation of the probable remediation time applying ISCO technologies
Hydrogeological framework and hydrochemistry of the groundwater in the Wa Municipality, Ghana
Petrophysical and hydraulical properties of andesitic geothermal reservoir rocks of Los Humeros and Acoculco, Mexico
Geochemical and isotopic characterics of groundwater in the hard rock terrain of Yanoya Basin in Sri Lanka – implications to occurrence of chronic kidney disease
Geochemical and stable water isotope characterization of bottled mineral waters for water source evaluation
Naturally Occurring Radioactivity in Paleozoic Enticho Sandstone Aquifer, Adigrat area, North Ethiopia
Determination of bicarbonate concentration in water samples based on major ions and electrical conductivity in comparison to bicarbonate titration
GIS based landslide susceptibility and hazard assesment in Schlüchtern Hesse, Germany
Determining Geotechnical Properties of Soil amd Rocks by Surface Measurements, Methods and Case Studies
Biodiversity assessment of an abandoned agricultural land for future biomass production in Poland, using remote sensing derived data and a spatially explicit approach
Assessment of water management and investigation of water optimization techniques for Toyota European manufacturing plants
Development of MODFLOW based tools to estimate the required remediation time in ISCO: Modeling the influence of heterogeneity
Development of a Green Roof / Green Façade model to estimate related energy savings for buildings – Data acquisition at a reference building for model calibration
Isotope chemistry of calcretes in sediment cores of well WW203302 in the Cubango megafan, Northern Namibia

AOR Dr. Thomas Schiedek

schiedek@geo.tu-...

work +49 6151 16-20635 fax +49 6151 16-23601

{{ child.heading }}

Quick access

Automotive Engineering

Master Theses

If you are interested to start your Master Thesis in the field of automotive engineering take a look at our current topics!

No matching topics in the list?

If you can't find a matching topic in the list below you can always apply for a thesis or project using our webform for unsolicited applications. All research associates of FZD will have the chance to see your application.

Webform for unsolicited applications for projects and theses

Currently no items available.

FZD Lectures

lehre@fzd.tu-...

COMMENTS

File format for theses
Theses must be submitted to the ULB via the TUbama Portal in the file format PDF/A (archivable PDF). In general, the required file format for the thesis is defined by the examiners (§ 22 APB). The archivable PDF/A format can generally be created from all standard text editing programs. However, it is necessary to select the correct settings ...
Master's Thesis
Master's thesis and study paper: workload 15 credit points (450 hours) each, timeframe 13 weeks each. Alternatively: Interdisciplinary, cross-departmental thesis: workload 30 credit points (900 hours), timeframe 26 weeks, separate application. All theses are subject examinations and as such must be registered in the Office of Student Affairs ...
Thesis
Theses are possible at any time in cooperation with the Faculty of Medicine at the Goethe University Frankfurt. In this case, please contact the Dean of Studies for Medical Technology at the Faculty of Medicine : [email protected]. Please support the Office of the Dean of Studies of the Medical Faculty with the following information ...
Thesis
External thesis. Should you wish to write your thesis at another department of the TU Darmstadt or at an institution outside the university (e.g. a company), the local professor remains responsible for the formulation of the assignment, supervision and assessment of the thesis in accordance with the General Examination Terms and the Examination ...
PDF Guidelines External Master Thesis in Materials Science
The Master Thesis (MT) is an integral part of the study program master materials science at TU Darmstadt. The MT summarizes a research project of 26 weeks. During their research, students learn to manage and carry out defined research projects. This practical research experience provides a solid basis for a career in research (e.g. towards a
External Thesis: Information Sheet
All important information on external theses is summarised in the information sheet that is available in German (opens in new tab) and English (opens in new tab). Contact Related articles
Guidelines for Theses
Formal requirements for students for the execution of Bachelor Theses, Master Theses, Studienarbeiten at the Multimedia Communications Lab (KOM) under the supervision of Prof. Dr.-Ing.Ralf Steinmetz. This information is meant as an overview of requirements, helpful tips, and notes for the application, registration, writing, submission, and presentation of theses at KOM.
Abschlussarbeiten
Zusätzlich zur Betreuung durch einen hiesigen Professor, musst Du Dir vor Beginn eine Genehmigung von Seiten des Studiendekans einholen, um eine externe Abschlussarbeit schreiben zu dürfen. Weitere Informationen findet man unter folgenden Links: Externe Bachelor/ Master-Thesis. Merkblatt externe Abschlussarbeiten (TU Darmstadt)
Master Theses
If you can't find a matching topic in the list below you can always apply for a thesis or project using our webform for unsolicited applications. All research associates of FZD will have the chance to see your application. Currently no items available. If you are interested to start your Master Thesis in the field of automotive engineering take ...
Master Thesis
Master Theses in Nonlinear Optimization. The topics of Master Theses in nonlinear optimization are in general related to specific applications or deal with analytical questions regarding optimization. Depending on the topic and preferences, the thesis includes scientific aspects from numerics, analysis, partial differential equations or ...
Master Theses
Currently advertised Master's theses - Here you will find an overview of all the current offers for Master's theses in the various fields of mechanical and aerospace engineering. ... Ongoing research at the Institute for Paper Technology of the Technische Universität Darmstadt is focused on the simulation and optimization of corrugated ...
Projects and Theses
Projects and Theses. TU Darmstadt. MB. FZD. Education. Theses & ADPs. If you are looking for a thesis or project idea, please take a look at the following topics that our students can choose as the focus of their theses or projects. Contact. Picture: Jan-Christoph Hartung.
PtU
Below you will find currently open master theses. Below you will find currently open master theses. Skip menu. Quick access {{ child.heading }} ... TU Darmstadt; Maschinenbau; PtU; Study and Teaching; Bachelor and Master Theses; Current Master Theses; ... [email protected]... work +49 6151-16-23143 fax +49 6151 16-23142. Work L1 ...
Jobs, Seminar, Bachelor and Master Theses
2022. Bachelor thesis, Master thesis, Projectseminar. Electric energy conversion is a key issue on the way to decarbonization. Computational design and optimization of electric motors is a very active research area with the aim to increase the efficiency and power density of electric drives.
Theses
Bachelor Thesis, Master Thesis. State-of-the-art models for code generation and understanding, such as CodeBERT and CodeT5, are basically LLMs designed for natural language (BERT, T5) but trained on a large corpus of code. However, LLMs are known to hallucinate, i.e, they often produce sentences and information that are factually incorrect.
Currently Open Theses Topics
Currently Open Theses Topics. We offer these current topics directly for Bachelor and Master students at TU Darmstadt who can feel free to DIRECTLY contact the thesis advisor if you are interested in one of these topics. Excellent external students from another university may be accepted but are required to first email Jan Peters before ...
Master Thesis
It aims at independently analyzing mathematical properties of optimization algorithms or their underlying structures. For planning the thesis, the following steps are crucial. In a first meeting, student and professor agree on a topic. Subsequently, the student has 4-6 weeks time to read up on the subject and to search the literature.
Writing a Bachelor or Master Thesis at TU Darmstadt
In the Department for Architecture, it is not possible for international exchange students to write a Bachelor or Master thesis there. Important Information: A Bachelor or Master Thesis is only supervised at TU Darmstadt. The final grading takes place at the home university. If you are planning to write a Bachelor or a Master thesis at TU ...
Master's Theses
Research Topics of TropHEE Master's Theses - List of topics of recent master's theses, to give an idea on the research topics that our students work on. ... IAG LinkedIn-Seite des IAG der TU Darmstadttelegram tu darmstadt Twitter - TU Darmstadt YouTube - IAG Telegram-Seite der TU Darmstadt. Directions. Sitemap. Legal note. Accessibility ...
Master Theses
If you can't find a matching topic in the list below you can always apply for a thesis or project using our webform for unsolicited applications. All research associates of FZD will have the chance to see your application. Currently no items available. If you are interested to start your Master Thesis in the field of automotive engineering take ...