— The explanatory text is provided here in English only. However, the thesis may also be written in German. —
We have one thesis project available that focusses on the anticipation of human behaviour. An experimental setup and a data set already exist where participants were asked to make tea in a VR environment. There were several intermediate steps that had to be performed – sometimes in the correct order, sometimes in any order – with levels of varying difficulty.
Why is this topic relevant?
Anticipating human behaviour in everyday situations is crucial because much of our interaction relies on subtle non-verbal cues such as body movements, gaze direction, and general behavioural patterns. These signals often indicate intention before anything is explicitly communicated. However, interpretation is not always straightforward, as such cues can be ambiguous and context-dependent, leading to uncertainty. This is particularly important in cooperative settings, where successful coordination depends on correctly inferring others’ actions and goals. While humans are often able to manage this to a reasonable degree despite occasional errors, it remains a significant challenge. For robots and autonomous systems, however, developing a reliable understanding of these anticipatory cues is essential for safe and effective interaction in shared environments. Investigating this topic further can (a) help to better understand human cognition in general and (b) make human-robot interactions more pleasant.
Focus of your work
The work described here starts by developing some first modelling idea of the data. The data set is huge, includes different types of data (behavioural, eye tracking, etc.) and there is a variety of different research questions that can be addressed. Part of the work is to find an own focus (of course in consultation with us) since it will not be possible to include all aspects. The goal is to develop some (cognitive) model that is able to use at least some of the available information to anticipate human behaviour.
Your model should of course be tested with some unseen data (test data set). If you like, it might also be possible to test your model afterwards as part of a small new evaluation study (the VR environment is available at the university).
Depending on your interests, different questions can be investigated. Your own interests and suggestions are expressly welcome and can also be developed further in the course of your work!
What you should bring with you
- Prior experience with data processing and (cognitive) modelling or a willingness to learn
- Interest in relevant factors of underlying principles of human behaviour
- Independent and proactive working style
What you will learn (at least) during your thesis
- In-depth knowledge of (cognitive) modelling
- Better understanding of the diversity of anticipation and what needs to be considered
- Insights into how to examine a technical setup and its effect on humans
- Depending on the focus of the thesis: analysing eye-tracking data
What we offer
- An existing experimental setup and data that you can use (no need to collect data first)
- Expertise in various fields, such as psychology, cognitive science, computer science, and robotics
- A reliable contact person who will support you with questions or problems
- The satisfaction of having contributed to ongoing research, meaning that your thesis will have added value beyond its immediate scope
- Communication and thesis in German or English (depending on your preference)
Sounds like your kind of role? Let’s talk. Please let us know:
- Who are you, what are you studying and what stage are you at (bachelor’s/master’s)?
- What is your background? Have you already taken any of our modules, e.g. HMI, Intelligent Agents, CCS?
- When would you like to start and what are your temporal requirements?
- What interests you about this topic? Which aspects are particularly relevant to you?
- Do you have any preferences regarding what you would like to learn during your thesis or how you would like our collaboration to be structured?