A Motivational Approach to Support Healthy Habits in Long-term Child–Robot Interaction

Abstract

We examine the use of role-switching as an intrinsic motivational mechanism to increase engagement in long-term child-robot interaction. The present study describes a learning framework where children between 9 and 11-years-old interact with a robot to improve their knowledge and habits with regards to healthy life-styles. Experiments were carried out in Italy where 41 children were divided in three groups interacting with: (i ) a robot with a role-switching mechanism, (ii ) a robot without a role-switching mechanism and (iii ) an interactive video. Additionally, a control group composed of 43 more children, who were not exposed to any interactive approach, was used as a baseline of the study.During the intervention period, the three groups were exposed to three interactive sessions once a week. The aim of the study was to find any difference in healthy-habits acquisition based on alternative interactive systems, and to evaluate the effectiveness * raquel.ros.espinoza@gmail.com † oleari.elettra@hsr.it ‡ pozzi.clara@hsr.it § sacchitelli.francesca@hsr.it ¶ baranzini.daniele@hsr.it bagherzadhal.anahita@hsr.it * * sanna.alberto@hsr.it † † y.demiris@imperial.ac.uk of the role-switch approach as a trigger for engagement and motivation while interacting with a robot. The results provide evidence that the rate of children adopting healthy habits during the intervention period was higher for those interacting with a robot. Moreover, alignment with the robot behaviour and achievement of higher engagement levels were also observed for those children interacting with the robot that used the role-switching mechanism. This supports the notion that role-switching facilitates sustained long-interactions between a child and a robot.

Child–Robot Relationship Formation: A Narrative Review of Empirical Research

“…Children trusted humans more than robots in some contexts, whereas in other situations their trust in robots was greater than, or did not differ from, their trust in humans [17,18,120,123]. Findings for engagement were inconsistent [112,120,149], but children enjoyed an interaction more when they interacted with a friend than when they interacted with a robot [122,123]. However, regardless of whether they interacted with a robot or with an adult, children felt equally comfortable and experienced similar levels of enjoyment [17,149].…”

“…Although strategic and emotional interaction and cognitive states seemed to be associated [3, 57,59,81], no clear patterns were detected. However, memory-based interaction seemed to foster anthropomorphism [86,112]. Unless children's companionship expectations of a robot were violated [85], social presence remained constant over time across interaction styles [3, 82,127].…”

“…For example, evidence emerged that when children were highly engaged, they also tended to feel close to a robot [28,54,133]. Accordingly, when children's engagement in robot interaction did not vary, their closeness or trust in the robot also remained unchanged [82,112]. However, other studies report variations in engagement but not in closeness [73,145] or trust [61,89].…”

Children’s acceptance of social robots

“…In general, children showed intentional (Guneysu & Arnrich, 2017;Hashimoto, Kato, & Kobayashi, 2011;Pulido et al, 2017; Saint-Aimé, Grandgeorge, Le Pévédic, & Duhaut, 2011; Saint-Aimé, Le Pévédic, & Duhaut, 2011) and behavioral acceptance (Wiles et al, 2016) of all social robots. Moreover, children showed the same degree of intentional acceptance towards a robot as to a human (Serholt, Basedow, Barendregt, & Obaid, 2014), an interactive video (Ros et al, 2016), and a tablet (Tozadore, Pinto, Ranieri, Batista, & Romero, 2017). For the tablet, this was also true for behavioral acceptance .…”

“…Children had a higher intentional acceptance of certain robot functions (e.g., providing education) compared to others (e.g., companionship) (Al-Taee et al, 2016), but their intentional acceptance was equal across different robot roles (i.e., friend vs. machine) (Westlund, Martinez, Archie, Das, & Breazeal, 2016). A third study (Ros et al, 2016) found no effect of role-switching on intentional robot acceptance. Finally, one study analyzed the effect of conversational violation (i.e., the robot bringing up information it could not possibly have) but did not find an effect on intentional acceptance (Leite & Lehman, 2016).…”