Flexible User-Robot Interaction
Three strands of research for the goal of more flexible HRI.
In the long-term, non-expert users should be able to tell their preferences and demands to a robot that assists them in a non-technical way. This requires a high degree of interactional flexibility. However, compared to human-human interaction, current human-robot (teaching/learning) interaction (HRI) is still very rigid. In this project, we work on making HRI more flexible in three main strands of research.
Together with the FLOWERS team lead by Pierre-Yves Oudeyer at INRIA Bordeaux - Sud-Ouest, we study how humans in unfamiliar, constrained situations (similar to HRI) negotiate meaning. We use a new experimental setup, the CoCo game.
- In collaboration with Softbank Robotics Europe, we investigate how state-of-the-art machine learning algorithms cope with human feedback.
- The goal of this research strand is to transfer the concept of pragmatic frames from developmental linguistics to HRI in a smart home environment as the cognitive service robotics apartment (CITEC project). In particular, we study the use of non-anthropomorphic system interaction signals in the context of pragmatic frames.
Recent Best Paper/Poster Awards
Philippsen A, Reinhart F, Wrede B (2016)
International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob)
Richter V, Carlmeyer B, Lier F, Meyer zu Borgsen S, Kummert F, Wachsmuth S, Wrede B (2016)
International Conference on Human-agent Interaction (HAI)
Carlmeyer B, Schlangen D, Wrede B (2016)
International Conference on Human Agent Interaction (HAI)