A Cloud-based Robot System for Long-term Interaction: Principles, Implementation, Lessons Learned

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.

System software architecture for advancing human robot interaction by cloud services and multi-robot cooperation

“…However, the framework needs more research and testing in actual settings. The authors in [5] debate over standards and utilization of a cloud-based robot system for long-term interaction. The authors developed a cloud-based and modular system called "Personal Assistant for a Healthy Lifestyle".…”

Goal Ontology for Personalized Learning and Its Implementation in Child's Health Self-Management Support

“…We added achievements in AchievementType as substantial goals that can only be attained by first attaining a set of smaller goals. A first version of the "goal-tree" was implemented in OWL/RDF and integrated in the PALO ontology, which was connected to the PAL system [36], [38], [39] 2) Expert Sessions: To improve the content of the domain model (POM), we consulted domain experts. The aim of these sessions was to get them acquainted with the model and to elicit content.…”

“…The PAL system is an mHealth application to support children of 7-14 years old with diabetes mellitus type 1 in their self-management training. Kaptein et al [39] provide a comprehensive overview of the system components; in this section, we will elaborate on the role of POM in goal setting and adaptation of system interaction.…”

Design and Evaluation of a Personal Robot Playing a Self-Management for Children with Obesity

“…However, achieving good interaction levels and acceptability in the long-term can be challenging using robotic systems, as the children may get bored after using it for a certain amount of time. To address such issues, a recent study [36] integrated mobile health applications and used hybrid artificial brain (with technologies such as artificial intelligence (AI) and machine learning (ML)) with a cloud-based robotic system to enable the prolonged use of the system. and desires and, therefore, progress with the child [37].…”

“…It is important to identify these factors that may influence the child learning process. It is important for the robot to assess the child's knowledge level, and accordingly, it should select the topics that are not too difficult nor too easy but are at the right level of difficulty customized for each child [36,42]. Figure 11 presents the education quiz percentage for the 16 users.…”