Making New “New AI” Friends: Designing a Social Robot for Diabetic Children from an Embodied AI Perspective

Abstract

Robin is a cognitively and motivationally autonomous affective robot toddler with "robot diabetes" that we have developed to support perceived self-efficacy and emotional wellbeing in children with diabetes. Robin provides children with positive mastery experiences of diabetes management in a playful but realistic and natural interaction context. Underlying the design of Robin is an "Embodied" (formerly also known as "New") Artificial Intelligence (AI) approach to robotics. In this paper we discuss the rationale behind the design of Robin to meet the needs of our intended end users (both children and medical staff), and how "New AI" provides a suitable approach to developing a friendly companion that fulfills the therapeutic and affective requirements of our end users beyond other approaches commonly used in assistive robotics and child-robot interaction. Finally, we discuss how our approach permitted our robot to interact with and provide suitable experiences of diabetes management to children with very different social interaction styles.

Hedonic quality or reward? A study of basic pleasure in homeostasis and decision making of a motivated autonomous robot

“…For this study, we have used the humanoid robot Nao, since we have developed our pleasure model with the intention to implement it in the autonomous social robot toddler Robin based on a Nao robot, (www.emotion-modeling. info/robin) (Cañamero & Lewis, 2016; Lewis & Cañamero, 2014) that we started developing as part of the EU project ALIZ-E.…”

Embodied Robot Models for Interdisciplinary Emotion Research

“…Finally, as affectively autonomous agents with their own needs, motivations, affective processes and interactions, that engage and disengage in interaction with humans in a coherent trade-off between attending to the human, being social, and being independent, provide a meaningful interaction partner that is more easily perceived and treated as an agent by us [23]. Such affectively autonomous robots could also make contributions to psychology and neuroscience well beyond the use of robots as passive perceptual stimuli, allowing us to study emotions in interacting agents in systematic and controlled ways.…”

“…Like in biological systems, for autonomous robots that need to survive and interact in their environments, pleasure (or its functional robot equivalent) can provide signals to assess the positive or negative quality of the perceived stimuli, the behavior being executed, or the interaction with others. In my group, we have developed robot models of different roles of pleasure, where "pleasure" was used, for example, as a signal to learn object affordances in the context of decision making [26], to improve internal homeostasis and adaptation to the environment [27], [63], or to convey a positive message in human-robot interaction contexts [23]. Following the approach adopted in [17], in the above models, pleasure was modeled in terms of release of simulated hormones that affect different aspects of the underlying robot architecture-in the above examples, the learning algorithms, the motivational decision-making model, and the expressive behavioral elements, respectively.…”

“…For our pleasure study, we used the humanoid robot Nao, since we developed our pleasure model with the intention to include it in the Nao-based Robin companion robot [23]. In a simple "two-resource problem" (TRP) action selection task, the robot had to timely alternate between searching for and consuming two survival-related resources-small colored balls representing "water" and "food"-distributed around a walled environment in different ways in the different experimental conditions tested.…”

The Philosophical Case for Robot Friendship

“…There are many more examples of roboticists trying to work out the behavioural cues indicative and friendship and trying to design robots that can perform those cues e.g. Cañamero and Lewis 2016. superintelligent robots using our bodies as resources to pursue their own, anti-humanistic, ends (Bostrom 2014).…”