We present a novel implementation of a Rock-Paper-Scissors (RPS) game interaction with a social robot. The framework is tailored to be computationally lightweight, as well as entertaining and visually appealing through collaboration with designers and animators. The fundamental gesture recognition pipeline employs a Leap motion device and two separate machine learning architectures to evaluate kinematic hand data on-the-fly. The first architecture is used to recognize and segment human motion activity in order to initialize the RPS play, and the second architecture is used to classify hand gestures into rock, paper or scissors. The employed tabletop robot interacts in the RPS play through unique animated gestural movements and vocalizations designed by animators which communicate the robot’s choices as well as cognitive reflection on winning, losing and draw states. Performance of both learning architectures is carefully evaluated with respect to accuracy, reliability and run time performance under different feature and classifier types. Moreover, we assess our system during an interactive RPS play between robot and human. Experimental results show that the proposed system is robust to user variations and play style in real environment conditions. As such, it offers a powerful application for the subsequent exploration of social human-machine interaction.

Social robots are beginning to be utilized as part of the collective networks supporting pediatric treatment, however there are few studies on children's perceptions of these agents in hospitals from a privacy and safety perspective. Through a mixed-method and value-sensitive design approach, we introduced hypothetical vignettes and engaged in discussion with 15 youth who are either receiving cancer treatments or are in remission (ages 6-25), 11 of their parents, and 5 out of 8 of their clinical staff to learn how stakeholders in pediatric oncology discuss privacy concerns regarding child-robot interactions. Our thematic analysis imparts how stakeholders perceive robots as social, non-authoritative extensions of the hospital's care network. From this privacy-sensitive perspective, this study revealed that for maximizing a robot's social utility within care systems while critically engaging with the comfort and privacy preferences of stakeholders, robots should take on the role of 1) mediators of social interaction among various stakeholders, 2) companions for children and 3) informational tools for clinicians when consent is given by the family. We emphasize how assistive technologies in pediatrics should continue to be co-designed within communities for identifying appropriate roles and returning agency to stakeholders as they navigate the blurry boundaries of privacy in healthcare.