Reusable Motivational Instruction Patterns for Socially Assistive Robots

Robots are increasingly tested in socially assistive scenarios. Future applications range from dieting, coaching, tutoring to autism therapy. In order to have a successful interaction with an artificial system, these systems need to have an interactional motivation model of how to assist users and encourage them to keep on with the task. In previous work, we have investigated how to build such a model for a specific scenario (e.g. indoor cycling). In this paper we want to show how to advance this model to be generalizable for other sport scenarios like rowing or bodyweight training. Therefore, we describe our framework for coordinating interaction scenarios with socially assistive robots.