Research Group Hybrid Society

Researchers: Britta Wrede (head), Sebastian Gieselmann, Katrin Lohan, Lars Schillingmann, Anna Vollmer, Manja Lohse

When taking the reasoning of current robotic research seriously we have to face the possibility that in the future humans and robots will live together in a shared environment and form a hybrid society of natural and artificial agents. We can thus expect to see more and more humans interacting with robots. This vision opens new research questions and opportunities that we want to tackle in the research group „Hybrid Society“.

On the one hand, robots will be able to profit from interactions with humans. As humans are experts when it comes to understanding and handling tasks in the real world, they are a valuable source of information for robots. But how can robots make use of this information? In our group we target at enabling robots to be tutored by humans. Research has shown that adults provide specifically designed input to infants in tutoring situations. We expect to see similar behavior in human-robot tutoring situations provided that the robot displays a certain degree of social behavior. Based on such behavior we are currently determining ways for the robot to understand the meaning of a demonstrated action and to detect when an action is being demonstrated in order to be learned by the robot.

On the other hand, the main goal for robots is to help humans and support them in their daily activities. However, in order for robots to be really helpful they not only must be able to learn and carry out tasks and actions. They must also display socially acceptable behavior and be understandable and predictable for their interaction partners. This entails not only to the propositional content of an interaction as modelled by a dialog management component, which enables to build a common ground of shared information between the user and the robot. Also, the robot should be able to take the affective components of an interaction into account by reading the human’s emotional expressions and by producing appropriate emotional signals. We suppose that such an alignment of emotional behavior will make interaction with the robot not only more satisfying but also more efficient.

External PhDs

Holger Brandl
Thurid Vogt
 

Former PhDs

Dr. Sonja Hüwel
Dr. Shuyin Li
Dr. Jan F. Maas