Co-constructing explainability with an interactively learning robot (B05)

• Subject Area: Methods in Artificial Intelligence and Machine Learning ; Early Modern History
• Term: since 2021
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 438445824

Research focus of B05 is the double loop of training and understanding. In the training loop the robot continuously adapts and refines its movements based on user input. The understanding loop allows the hu-man trainer to develop a deeper comprehension of the robot's learning mechanisms through real-time interaction and explanations provided during the process. The focus is on its use in healthcare scenarios where laypersons with probably low technology affinity train a robot to perform specific movements. The ultimate vision of B05 is to create a co-constructive system that can be trained by anyone.

• DFG Programme: CRC/Transregios
• Subproject of: TRR 318: Constructing explainability
• Applicant Institution: Universität Paderborn
• Project Heads: Professor Dr. Carsten Schulte, since 1/2026; Professorin Dr. Anna-Lisa Vollmer