This project investigates the use of behavior trees (BTs) for modeling and managing collaboration between humans and artificial agents. The aim is to develop methods for the automatic generation and adaptation of BTs, with large language models (LLMs) serving as tools to support these processes. Human users may guide the adaptation of BTs with the assistance of LLMs, or the project may focus on representing human behavior within BTs. Implementation will be in Python and includes developing algorithms for BT creation and adaptation, as well as integrating LLMs to facilitate these tasks. The effectiveness of the methods will be evaluated in cooperative scenarios involving human participants.
This topic is suitable for a group project.
Please contact fschroeder@techfak.de
| Frequency | Weekday | Time | Format / Place | Period | |
|---|---|---|---|---|---|
| by appointment | n.V. | 13.10.2025-06.02.2026 |
| Module | Course | Requirements | |
|---|---|---|---|
| 39-M-Inf-P Project Projekt | Projekt | Ungraded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.