Socio-Cognitive Engineering of a Robotic Partner for Child's Diabetes Self-Management

Area of Science:

• Robotics and Human-Computer Interaction
• Child Health Technology
• Socio-cognitive Engineering

Background:

• Social robots are scarce in real-world applications, limiting their potential for sustained human benefits like child health.
• Developing long-lasting human-robot partnerships requires a structured methodology to integrate diverse needs and technologies.
• Children with chronic diseases need continuous support for effective self-management.

Purpose of the Study:

• To present a socio-cognitive engineering (SCE) methodology for developing enduring human-robot partnerships.
• To detail the application of the SCE methodology in creating the Personal Assistant for a healthy Lifestyle (PAL) robot for pediatric diabetes management.
• To establish a framework for prolonged "blended" care integrating robots into children's chronic disease management.

Main Methods:

• Application of the SCE methodology in a European project, involving iterative refinement over three cycles.
• Identification and development of four key partnership functions: joint objectives, agreements, experience sharing, and feedback & explanation.
• Integration of a common knowledge base and interaction design tailored for prolonged disease self-management in children.

Main Results:

• The PAL robot effectively supported children's diabetes management by acting as a partner.
• The SCE methodology successfully integrated diverse scientific disciplines, technologies, practices, and user needs.
• The robotic partner fostered children's autonomy, competence, and relatedness, aligning with Self-Determination Theory principles.

Conclusions:

• The developed SCE methodology and human-robot partnership framework enable long-duration "blended" care for children with chronic conditions.
• The PAL robot represents a novel human-agent/robot system with evolving collective intelligence.
• The underlying ontology and design rationale can serve as a foundation for future long-term human-robot partnerships in real-world settings.