Open Thesis Topics

In this work you will develop a game that has the streamer-audience live-streaming setup in mind. Similar to games such as Choice Chamber, this game allows the audience to be involved via Twitch Extensions or the Twitch chat and alters how the game unfolds for the streamer. The developed game should integrate different options for this involvement which are investigated in a user study.

Focus

This work will include the development of a game from scratch and a small to large user study (depending on whether it is a Bachelor's or Master`s thesis). Nonetheless, the proper game design and selection of suitable audience participation options is in the focus, thus, this work has an implementation focus (Bachelor) or a mixed focus (Master).

Prerequisites

  • Strong programming experience
  • Read papers on audience participation (1234)
  • Consumer of game live-streamer
  • Video game player
  • 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
  • At least 5 ideas for different audience intergation options (max. 1 A4 page)

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

This work focuses on context factors (e.g., stream type: casual stream vs. speedrun) that apply to audience influence options in game live-streams. Building on previous work, your task is to conduct studies in which different situations in typical game live-streams are shown and in which different audience influence options are presented. The relevant influence options for this thesis are not bound to the actual content of the game, instead they work independently of the streamed game (“beyond the game”). Typical examples include modifying the streamer’s room lighting, activating vibration feedback on the streamer’s arm, or exchanging keyboard bindings. The goal of these studies is to derive guidelines which context factors moderate the perception of these modifications.

Focus

The focus is on the study. Likely, you need to either create small mock up prototypes and find a streamer using them (for recording sessions) or you need to have good skills to create proper visualization material, to clarify what happens.

Prerequisites

  • Read our previously published papers on live-streaming.
  • Background or interest in game live-streams.
  • Completed HCI and/or the 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
  • Provide the information, whether you have contacts to streamers who would be willing to assist in the study
  • Assume that changing the lighting situation in the streamer’s room is the only possible audience influence option beyond the game. Under this assumption, list context factors that you think are relevant in live-streaming and explain how you would do an online study to investigate these contexts (max 2 A4 page)

 


See personal profile of Dr. Pascal Lessel

Recent advances in Machine learning (specifically Deep Learning) allowed robots to understand objects and the surrounding environment on a perceptual non-symbolic level (e.g. object detection, sensors fusion, and language understanding), however a trending area of research is to understand objects on a conceptual symbolic level so we can achieve a level of robots thinking like humans. Deep Reinforcement Learning (RL) recently attempted implicitly combining these symbolic and non-symbolic learning paradigms, but it has several drawbacks such as: (1) the need for very long training time with respect to traditional deep learning approaches, (2) convergence to optimum policy is not guaranteed and it can get stuck in a sub-optimal policy, and (3) a RL agent is trained over a simulated environment so it cannot foresee actions that only exist in the real environment. The goal of thesis is to train a robot that would explicitly learn on both perceptual and conceptual levels through direct feedback from a human expert along with its existing view (i.e. sensors) of the world.

 

Focus

This work will focus on Reinforcement Learning, Imitation Learning and the combination of both. This work will involve real-time implementation of a working system.

 

Prerequisites

  • Please read about the following papers [1] [2] [3] [4] [5]
  • Background or interest in RL, Computer Vision or AI Planning
  • Completed HCI, Statistics and/or Machine learning courses
  • Strong programming skills
  • Unity/SImulation environments background is a plus

 

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

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 when interacting with a vehicle, 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 (e.g., Graph 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

The student will develop a robotic system that navigates through a retail store and takes pictures of the shelves in order to send them to our existing Intelligent Agent. Based on these pictures, a classification will be made. If something is wrong, a Transfer of Control (ToC) will be triggered and the "Remote Expert" will receive a notification. Together with the student, we will decide how this will be implemented. For instance, it could be a dashboard, smartwatch/tablet/smartphone or even a VR/AR interface. Based on the information provided, the expert can now decide whether it is an actual error (which needs to be fixed) or if it was a false alarm -> i.e., s/he gives feedback to the system, so that it learns and improves over time (learning aspect is not part of this thesis). Overall, such a system is called Hybrid Intelligence.

 

Focus

The focus of this thesis lies on the conceptualization and implementation of a robotic framework to support retail robots. Additionally, a small evaluation of the system is expected. 

 

Prerequisites

  • You should have (very) good programming skills.
  • Before applying, please read and understand the concept of Hybrid Intelligence (see page 7/27 [1])
  • Last but not least, be enthusiastic about robots =)! 

 

How to apply

Please send an application to Martin Feick and/or Niko Kleer 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