A framework for designing socially assistive robot interactions

Robots are increasingly tested in different socially assistive scenarios. Future applications range from dieting, coaching, tutoring to autism therapy. In such applications the success of the system is commonly evaluated by the ability to encourage the user to keep up with a task. Hence, one important requirement for supportive systems is to have an interactional motivational model that formalizes the way how users can be assisted. In this paper we describe our framework for coordinating motivational interaction scenarios with socially assistive robots (SAR) in the context of sport assistance. We exemplify three different sport scenarios where we have used the same motivational interaction model. Furthermore, we show how this model can be used to systematically test the different aspects of motivation in the context of SAR in sport domains. Therefore, we have conducted an experiment to evaluate the importance of acknowledgement from SAR for human interaction partners. The results show that users exercise longer if acknowledgment is included into the motivational model.