Abstract
Making the transition to long-term interaction with social-robot systems has been identified as one of the main challenges in human-robot interaction. This article identifies four design principles to address this challenge and applies them in a real-world implementation: cloud-based robot control, a modular design, one common knowledge base for all applications, and hybrid artificial intelligence for decision making and reasoning. The control architecture for this robot includes a common Knowledge-base (ontologies), Data-base, “Hybrid Artificial Brain” (dialogue manager, action selection and explainable AI), Activities Centre (Timeline, Quiz, Break and Sort, Memory, Tip of the Day, \( \ldots \) ), Embodied Conversational Agent (ECA, i.e., robot and avatar), and Dashboards (for authoring and monitoring the interaction). Further, the ECA is integrated with an expandable set of (mobile) health applications. The resulting system is a Personal Assistant for a healthy Lifestyle (PAL), which supports diabetic children with self-management and educates them on health-related issues (48 children, aged 6–14, recruited via hospitals in the Netherlands and in Italy). It is capable of autonomous interaction “in the wild” for prolonged periods of time without the need for a “Wizard-of-Oz” (up until 6 months online). PAL is an exemplary system that provides personalised, stable and diverse, long-term human-robot interaction.
Highlights
There is an increasing interest in long-term human-robot interaction
This corresponds with the BMJ finding that, worldwide, the amount of children with Type 1 Diabetes Mellitus (T1DM) is increasing by 3% every year, whereas the causes of this increase are still unknown
For the Personal Assistant for a healthy Lifestyle (PAL) system such a distribution could mean that choosing how to support a child means figuring out what educational goals there are for the child, suggesting an activity to work towards that goal, and figuring out what to say to the child, and how to explain the importance of the goals
Summary
There is an increasing interest in long-term human-robot interaction. Social robots are commonly applied to education, health-care, public spaces, work environments, and home environments [58]. We propose four principles for the implementation of such a system: It must (1) have a connection to the cloud to delegate parts of the computational problems to external computers; (2) be modular to support parallel and incremental development of functionality; (3) have a common knowledge-base and vocabulary in the different system components and for the human-agent interaction; and (4) have hybrid artificial intelligence solutions (e.g., agent-based and machine learning) that all have their own contribution to the problem. The PAL system is a fully integrated and autonomous system that interacts with the children, their parents, and the health-care professionals for prolonged periods of time It is composed of a social robot, its (mobile) avatar, and an expandable set of (mobile) health applications (diabetes diary, educational quizzes, sorting games, etc.). We discuss and motivate the four design principles of our
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
