Open Thesis Topics

Mobile robotic platforms can assist workers in a warehouse during commissioning tasks. Therefore, they need to understand the behaviour of the human. Modern computer vision techniques can be used to understand human gestures during interaction. The recognition can be improved by understanding the context within the gesture is performed: A pointing gesture can be enriched with spatial information about the gesture, the object the human is pointing at, and the storage location related to the performed action.

Focus

In this work you will investigate techniques how to derive spatial information from gestures and set them into the context of the objects involved. A prototypic solution focusing on a specific use case will be implemented and tested in the human-robot collaboration laboratory. The goal is the estimation of the optimum height for unloading and loading the robotic platform with a height adjustable table.

Prerequisites

  • First experience with applied computer vision
  • Python and OpenCV knowledge
  • Willing to work in the laboratory
  • Strong motivation and ability to work independently
  • ROS experience is an advantage

How to apply

Please send me an email with the following pieces of information:

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you would be a good fit for this topic (experience in related CV projects)
  • Your transcript of records

See personal profile of Sönke Knoch

In this work you will investigate different customization degrees (e.g., just having the option to disable or enable gamification; full customization of every aspect the gamification offers) for a gamification intervention. The context in which this should be tested can be negotiated and this will also moderate the type of study to conduct (e.g., lab study vs. online study). Also the aspects that you want to investigate can be negotiated as well (e.g., user experience, task efficiency, ...)

Focus

This work will mainly focus on conducting studies. To do these, you also need to implement a study prototype.

Prerequisites

  • Read our papers on "bottom-up" gamification (1234)
  • Background or interest in gamification
  • Experience with web development
  • Completed HCI and/or Statistics lecture and ideally already attended at least one seminar at our chair

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you be a good fit for this topic
  • Your transcript of records
  • A suggestions of at least 3 different customization degrees (not including the two examples mentioned here) (max. 1 A4 page)

See personal profile of Dr. Pascal Lessel

In this work you will investigate whether "bottom-up" gamification has a positive impact on the experience of "flow" in comparison to a baseline (not using gamification) and a non-customizable gamification condition. The context in which this should be tested can be negotiated and this will also moderate the type of study to conduct (e.g., lab study vs. online study).

Focus

This work will mainly focus on conducting studies. To do these, you also need to implement a study prototype.

Prerequisites

  • Read our papers on "bottom-up" gamification (1234)
  • Be familiar or get familiar with the concept of flow experience
  • Background or interest in gamification
  • Experience with web development
  • Completed HCI and/or Statistics lecture and ideally already attended at least one seminar at our chair

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you be a good fit for this topic
  • Your transcript of records
  • Which literature on flow you have read before applying for this topic. (You should definitely read at least one paper on this topic before applying!)

See personal profile of Dr. Pascal Lessel

In this work you will investigate the effects of offering a choice to enable or disable gamification in different context. Previously, (see below) we could show that offering this choice is beneficial in the context for image tagging for those that dislike the gamification used in the system. To get further insights, more contexts and more game configurations need to be considered. If this topic is done as Bachelor's (Master's) Thesis, you should select one (two) different context (that is suitable for a study) and implement one (two) further game configuration (per context), besides the to-be-implemented points and leaderboards.

Focus

The study prototypes needed to be implemented. Thus you should have solid (most likely web) programming skills. Additionally, user studies should be carried out.

Prerequisites

  • Read our previously published paper on "Enable or Disable Gamification?": Enable or Disable?
  • Read our papers on "bottom-up" gamification (123)
  • Background or interest in gamification
  • Experience with web development
  • Completed HCI and/or Statistics lecture and ideally already attended at least one seminar at our chair

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you be a good fit for this topic
  • Your transcript of records
  • Which other context would you pick and why do you think this is a reasonable context for a study setting (max 1 A4 page)

See personal profile of Dr. Pascal Lessel

In this work your task is to focus on creative live-streams on Twitch and to integrate means to allow for audience participation in these creative processes. For this, we will most likely focus on creative screens in which the streamer creates (digital) paintings. You will implement a Twitch Extension that allows the audience to participate in this drawing process, e.g., by allowing them to draw on a canvas (based on rules to be determined first). An export of the audience drawing is then provided to the streamer who finishes the art. More or different approaches can be investigated as well.

Focus

The main focus will be on the concept and implementation – so you should have a good programming skill. In addition, a user study should be conducted to investigate the users' perception.

Prerequisites

  • Experience with web development
  • Completed HCI and ideally already attended at least one seminar at our chair
  • Ideally, contact to art streamers

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you be a good fit for this topic
  • Your transcript of records
  • A description of which live-streams you consume and if you stay in contact to streamers already
  • A short sketch of how you can imagine to integrate the audience besides the above mentioned idea

See personal profile of Dr. Pascal Lessel

In this work your task is to investigate why “Bottom-up” gamification (i.e., you are able to customize the gamification to your needs) produces positive results. We want to focus on multiple aspects in a user study: ownership (“it is cool, because I could create it and I can identify with it), autonomy (“it is cool, because I was allowed to change it”), good fit (“it is cool, because it fits perfectly to me”) or time invest (“it is cool, because it took me so long to create it). We will conceptualize a study concept in this Master thesis that helps us to answer which of the aforementioned factors seems to be a driving factor for why “bottom-up” gamification is able to outperform “top-down” gamification.

Focus

The main focus will be the study. Thus, you should have a solid understanding of study design or be willing to read books in this area. It can be assumed that you also need to implement a “bottom-up” context to investigate the four aspects.

Prerequisites

  • Read our papers on "bottom-up" gamification (1234)
  • Completed HCI and ideally already attended at least one seminar at our chair
  • Background or interest in gamification

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you be a good fit for this topic
  • Your transcript of records
  • A one pager in which you describe how would a study looks like in which you find out whether or not time invest is a relevant factor in a “bottom-up” scenario. Obviously, if this is reasonable you can re-use this part already for the real study.

See personal profile of Dr. Pascal Lessel

In this work your task is to develop a prototype of a live-streaming platform that should offers a tailored experience for viewers. This means that the watching experience is slightly different for every viewer. While the core video content remains untouched, aspects such as overlays and sounds (last donators, donation goals, last subscriber effects etc.) that are typically present directly in the video content should be separated to disable these locally for viewers. This thesis consists of three parts. In the first part, an online study should be conducted that investigates which kind of options viewers actually want to be customizable. In the second part, the results are transferred into a prototype. In the third part (only for Master students), an actually study with streamers, their viewers and this prototype should be done.

Prerequisites
  • Good experience with web development
  • Completed HCI and ideally already attended at least one seminar at our chair
  • Ideally, contact to streamers (this is also relevant if this is done as a Bachelor thesis, as this might also help for the first part).

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you be a good fit for this topic
  • Your transcript of records
  • A description of which live-streams you consume and if you stay in contact to streamers already
  • A (at least) one page overview (bullet points) of features that you can imagine that could be tailored in this context

See personal profile of Dr. Pascal Lessel

In customization of gamification interventions, we often work on the level of game elements, either by enabling or disabling certain elements in the system, or by allowing users to adjust some attributes of elements (e.g., changing whether an action gives 100 instead of 200 points). While these systematic approaches help to understand how users interact in such situations, it needs to be considered that these are somewhat artificial for users.

Therefore, in this work, we want to focus on situations in which users had customized game-related aspects on their own. To this end, we want to focus on board games and “house rules” in particular. In an online study (maybe complemented with interviews) participants should report on past experiences where they, on purpose, changed the official ruleset of a board game to make it a better fit or which other parts they have changed. This mainly qualitative work should be complemented by a set of standardized measurements that participants needs to answer (e.g., Hexad User Types Questionnaire) to find out, whether relationships can be derived between individual traits and the way board games are customized. The goal is to get insights into further ways how customization should be offered in gameful systems and what parameters user wants to be able to adjust and whether this is moderated by specific attributes.
The final step is to implement a gamified system that implements the found results and to test it in a small (Bachelor’s Thesis) or large (Master’s Thesis) user study to see whether it also generalizes to the gamification domain.

Focus

This work will mainly focus on setting up and conducting user studies and analyzing the results. To do the last study, you also need to implement a study prototype.

Prerequisites

  • Read our papers on "bottom-up" gamification (1234)
  • You should have a strong interest in board games and you should be an active member of a board game community. This is necessary, to be able to distribute the questionnaire to the correct target group and to get enough responses. If you only consume board game channels on YouTube this does not count for being “active member”. In contrast, if you, for example, are a Patreon of a board game creator, where you see a high chance that he/she/they might be distribute the link to our study, you are.
  • Background or interest in gamification
  • Completed HCI and/or the Statistics lecture and ideally already attended at least one seminar at our chair
  • You should be willing to do the qualitative research analysis.

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis.
  • When you plan to finish the thesis.
  • A short motivational statement why this topic is interesting for you.
  • A summary why you be a good fit for this topic. Here, please also cover which board game experience you have, how many board games you own, your top 5 board games and in which board game communities you are actively involved in.
  • Your transcript of records.
  • Which kind of house rules you have implemented in your played board games (~at least 500 characters). If you do not have house ruled so far, please state this and think about a potential house rule for a game and explain it (at least 500 characters).
  • Now, based on this text, please describe how you would do the qualitative research analysis (max. 1 A4 page); cite appropriate literature.

 


See personal profile of Dr. Pascal Lessel

In this thesis you will investigate virtual object deformations through the use of tangible proxy objects in VR. This requires the implementation of a deformable physical prototype (e.g., bendable, twistable, etc.) which acts as a counterpart for several virtual objects. The goal of this thesis is the creation of tangible proxies providing realistic haptic sensations in VR validated through a user study.

 

Focus

This work will mainly focus on implementing a prototype. Thus, solid programming (C#, Unity3D) and/or hardware skills (Arduino) are necessary. In addition, a user study may be carried out to evaluate the prototype.

 

Prerequisites

  • Read the following papers [1] [2] [3] (might require VPN)
  • Be familiar or get familiar with the concept of tangible interfaces [4]
  • Background or interest in Virtual Reality
  • Experience with Unity3D, 3D printing and/or Arduino
  • Completed HCI and/or Physical Computing lecture and ideally already attended at least one seminar at our chair

 

How to apply

Please send me an email with the following pieces of information (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement (max 0.5 pages) why this topic is interesting for you
  • Your transcript of records and your CV

See personal profile of Martin Feick

Human as well as robotic grasp prediction has experienced the development of numerous methods for learning suitable grasping motions with respect to a wide variety of objects.In the field of robotics, various (learning-based) approaches have been proposed [1][2]. An enormous amount of methods have been applied for predicting a human's grasping motions as well. However, the majority of these methods utilise subsymbolic learning models that do not allow more detailed insights regarding the decision making of the system. This thesis aims to investigate the possibilities of applying hybrid artificial intelligence approaches to the field of human grasp prediction (explainable AI).

 

Focus

The student is expected to work on the conceptualization of hybrid learning approaches for making explainable predictions in the field of human grasp prediction. Optimally, the student implements a prototype (Python) for demonstrating the approache's applicability.

 

Prerequisites

  • The following thesis provides a gentle introduction to deep-learning based grasp prediction, familiarize yourself with it's basic ideas [3]
  • Also, the following TechTalks article provides a reasonable and easy to grasp introduction to the concept and potential importance of hybrid AI [4]
  • You should have a good command of a variety of machine- and deep-learning algorithms
  • Be familar with implementing basic learning applications in Python using Scikit-learn and/or Keras
  • Last but not least, be enthusiastic about the investigation of potential research directions in a widely unexplored field!

 

How to apply

Please send an application to Niko Kleer or Martin Feick containing the following information. (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement (max 0.5 pages) why this topic is interesting for you
  • Your transcript of records and your CV

See personal profile of Martin Feick
Teaching a robot basic motions for grasping objects is a complex task that research has been tackling from numerous perspectives. Common approaches for deriving basic grasping motions include applying Deep Learning to large collections of images [1]. In other cases, additional hardware such as a glove might be used for capturing a human's motions which can be translated to a more specific grasping type [2]. Unfortunately, many of these approaches cannot be applied in real world applications. This thesis aims to investigate the possibility of teaching a robot basic grasping motions based on raw data while refraining from the usage of additional, and at the same time, cumbering hardware.

 

Focus

The student is expected to work on the implementation of a system that allows predicting the human's grasping motion while investigating the applicability/potential of various learning algorithms.

 

Prerequisites

The following thesis provides a gentle introduction to deep-learning based grasp prediction, familiarize yourself with it's basic ideas [3]:

  • You should be familiar with the concept of Deep Learning and how to implement CNNs using Keras
  • Previous exposure to OpenCV and applying learning algorithms to videos is a plus
  • Last but not least, be enthusiastic about the investigation and application of learning algorithms in the context of robotics!

 

How to apply

Please send an application to Niko Kleer or Martin Feick containing the following information. (if you do not answer every point, your application will not be considered):

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement (max 0.5 pages) why this topic is interesting for you
  • Brief summary on your prior knowledge regarding learning algorithms (specifically reinforcement learning) 
  • Your transcript of records and your CV

 


See personal profile of Martin Feick

Die falsche Nutzung von Gehhilfen (Krücken) nach einer Operation kann zu ungewollten Nebenwirkungen führen, wie beispielsweise die Verkümmerung der Beinmuskulatur. Um dies zu verhindern und die schnelle und möglichst vollständige Rehabilitation zu erreichen, soll schon von Anfang an ein korrektes Gehen mit Krücken erlernt werden.

In dieser Arbeit soll ein interaktiver Krückentrainer auf Basis von Kinect (o.ä.) und Unity erstellt werden. Ziel ist es, ein System zu entwickeln, dass Patienten, basierend auf aktueller Lehrmeinung, das Gehen (und Treppensteigen, etc.) an einer oder zwei Gehstützen beibringt. Hierbei soll in Echtzeit auf Fehler eingegangen werden und entsprechend durch passendes Feedback entgegengewirkt werden. Das System soll zudem, sofern Covid-19 Regelungen dies zulassen, möglichst mit Benutzern getestet werden. 

Fokus

Der Fokus der Arbeit liegt auf der Implementierung des Assistenzsystems. Um diese durchzuführen Bedarf es aber auch entsprechender Recherche und ggF (Telefon-)Interviews mit Physiotherapeuten o.ä.

Voraussetzungen

Nice-to-Have

  • Erfahrung mit der Kinect o.ä.

  • Erfahrung mit OpenCV, bzw. der Vorlesung IPCV

  • Gute deutsche Sprachkenntnisse für eventuelle Interviews

Bewerbung

Bitte schick mir eine E-Mail an felix.kosmalla@dfki.de mit folgenden Inhalten

  • Wann du mit der Arbeit anfangen willst

  • Wann du planst die Arbeit abgeschlossen zu haben

  • Kurzes Motivationsschreiben warum dich das Thema interessiert, inklusive kurzer Abschnitt warum du denkst, dass du das Thema erfolgreich bearbeiten kannst.

  • Transcript of Records

     

Nach einem ersten Gespräch wirst du eine (Implementierungs) Aufgabe bekommen, mit der wir feststellen können, ob einer erfolgreichen Bearbeitung des Themas nichts im Weg steht.

 


See personal profile of Felix Kosmalla

Referencing resolution is a trending topic that remains unsolved due to the high variance in users' behavior when performing a referencing task. Referencing resolution is simply identifying the object a user is intending to select through speech, pointing, gaze or multi modal fusion of all the previous modalities. Referencing is used in multiple domains in HCI such as Human Robot Interaction (HRI) [Nickel et al. 2003; Whitney et al. 2016; Kontogiorgos et al. 2018; Sibirtseva et al. 2019], and Vehicle and Drone interaction [Rümelin et al. 2013; Roider et al. 2017; Gomaa et al. 2020]. However, most of the current research focus on stationary first-person view when interacting with the object. In this thesis, you will work on the task of multi-modal real-time reference resolution using speech, gaze and/or pointing gestures from a moving source in third person perspective when interacting with industrial robot or retail delivery drone. 

 

Focus

This work will focus on gesture identification, gaze tracking, object detection, speech recognition and/or modality fusion techniques. This work will involve real-time implementation of a working system.

 

Prerequisites

  • Please read about the following papers [1] [2] [3] [4] [5] [6]
  • Background or interest in gesture recognition, NLP or gaze tracking
  • Completed HCI, Statistics and/or Machine learning courses
  • Strong programming skills

 

How to apply

Please  send me an email  with the following pieces of information:

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you would be a good fit for this topic
  • Your transcript of records and CV

See personal profile of Amr Gomaa

Vehicles get exponentially smarter every day; Manufacturers are continuously adding more features to smart cars. While these functionalities are added to enhance driver's experience and make their rides smoother, they often come with extra complexity that causes more stress and might make the trip more dangerous. Several researchers attempted conceptualizing / introducing situation-aware personalized adaptive interfaces that would ultimately reduce the interface complexity [Garzon et al. 2010; Garzon et al. 2011; Garzon 2012; Siegmund et al. 2013; Walter et al. 2015; Hasenjäger et al. 2017; Knauss et al. 2018]. However, as far as we know, there is no actual implementation for such interface due to the lack and obtaining difficulty of such training data. 

 

Focus

In this thesis, you will work on a two-stage project that 1) Identify certain activities or scenarios based on driving behavior for the use in traditional or autonomous driving situations using state diagrams or specific schema, 2) Use a hybrid deep learning approach ( eg Graphical Neural Networks or Deep Reinforcement Learning) to find adaptive patterns in behavior using small amount of data. You will focus on activity recognition, situation awareness and hybrid learning approaches combining symbolic and sub-symbolic learning.

 

Prerequisites

  • Please read about the following papers [1] [2] [3]  [4] [5] [6]
  • Familiar with deep learning concepts and / or state diagrams / graphical modeling
  • Completed AI Planning, Statistics and / or Machine learning courses
  • Strong programming skills

 

How to apply

Please   send me an email   with the following pieces of information:

  • When you plan to start the thesis
  • When you plan to finish the thesis
  • A short motivational statement why this topic is interesting for you
  • A summary why you would be a good fit for this topic
  • Your transcript of records and CV

See personal profile of Amr Gomaa

Kleine Einzelhändler in Innenstädten oder Einkaufszentren profitieren aktuell kaum von der Digitalisierung im Handel. Es fehlen überzeugende Anwendungen, die einen Mehrwert mit den entsprechenden, digitalisierten Informationen generieren. Im Rahmen einer Abschlussarbeit in Zusammenarbeit mit Horn & Company Data Analytics soll untersucht werden, wie Konzepte zur Unterstützung lokaler Einzelhändler aussehen könnten,  vielversprechende Konzepte zu entwickeln und zu evaluieren.

Inhalte der Abschlussarbeit:

  • Ideengenerierung
  • Erste Evaluation: Erste Befragungen und Detaillierung der Ideen
  • Ideenauswahl: Auswahl von Fokusideen (ein oder mehrere) auf Basis der ersten Evaluation
  • Ideenverfeinerung: die ausgewählten Ideen werden spezifiziert, Konzepte zu Daten, Architektur, Oberflächen etc. erstellt, ggf. Mock-Ups gemacht
  • Implementierung von Prototypen
  • Zweite Evaluation: Detaillierte Befragungen


Bewerbung:

Bitte sende mir eine E-Mail mit den folgenden Informationen:

  • Gewünschter Start der Arbeit
  • Geplante Fertigstellung der Arbeit
  • Ein kurzes Motivationsstatement, warum das Thema interessant für dich ist
  • Eine kurze Zusammenfassung, warum du gut für die Bearbeitung des Themas geeignet bist
  • Übersicht besuchter Lehrveranstaltungen

See personal profile of Frederic Kerber

Motivation
Die Eyeled GmbH hat sich als Anbieter von Apps für Weltleitmessen etabliert. Die Apps enthalten alle relevanten Informationen für den Besucher zur Vorbereitung und für den Messebesuch selbst.
Bereits im Vorfeld kann der Nutzer eine Liste von Ausstellern zusammenstellen, die er besuchen möchte und optional auch schon konkrete Gesprächstermine vereinbaren. Außerdem kann er sich Vorträge vormerken, die auf der Messe in Foren gehalten werden.
Wünschenswert wäre es, wenn das System dem Besucher einen optimalen Plan vorschlagen könnte, bei dem die Termine alle wahrgenommen werden können und gleichzeitig die Laufwege möglichst kurz sind.

Thema
Das Traveling Salesman Problem ist ein Optimierungsproblem der Theoretischen Informatik, das bereits sehr gut untersucht ist. Es stehen heute viele heuristische und exakte Methoden zur Lösung zur Verfügung. Die zusätzliche Hinzunahme von Termin-Restriktionen erschwert das Problem erheblich. In dieser Arbeit soll ein System umgesetzt werden, das Lösungen für den beschriebenen Anwendungsfall vorschlägt. Zu untersuchen ist, bis zu welcher Anzahl von Eingabeparametern eine optimale Lösung in vertretbarer Zeit bestimmt werden kann und ab wann auf einen heuristischen Algorithmus zurückgegriffen werden muss.

 

Inhalte der Arbeit

  • Evaluation des derzeitigen Stands der Forschung
  • Konzeption des Systems
  • Prototypische Umsetzung und Evaluierung
  • Schnittstellendefinition und Integration mit bestehender Messe-App (Anpassungen an Messe-App ist nicht Teil der Anforderungen)
  • Erweiterungsmöglichkeiten: Automatische Vorschläge zum Besuch von auf dem Weg liegenden Ausstellern, die zum Interessenprofil des Besuchers passen

 

Voraussetzungen

  • Interesse am Thema Datenstrukturen und Algorithmen
  • Gute bis sehr gute Programmierkenntnisse (Node.js)
  • Datenbankkenntnisse (SQLite)

 

Bewerbung
Bitte sende eine E-Mail an Frederic Kerber mit den folgenden Informationen:

  • Gewünschter Start der Arbeit
  • Geplante Fertigstellung der Arbeit
  • Ein kurzes Motivationsstatement, warum das Thema interessant für dich ist
  • Eine kurze Zusammenfassung, warum du gut für die Bearbeitung des Themas geeignet bist
  • Übersicht besuchter Lehrveranstaltungen

 

Ansprechpartner

DFKI: Frederic Kerber
Eyeled GmbH: Christoph Bartelmus


See personal profile of Frederic Kerber