Perspective taking is essential in composing effective interaction and collaboration; therefore, its importance extends to scenarios where one side of the interaction is a robot or an agent. Furthermore, it is a cognitive skill that develops at an early age and consolidates in elementary school years. In this study, we describe the design and implementation procedure of a gamified platform to evaluate children's perspective taking ability while interacting with a robot. The game is designed with different levels of difficulty with educational implications such as practicing mathematics. We share our insights on the design and the usability of such platforms in children's education, while we detail how they can be beneficial to model the robot's cognitive framework.

In this paper, we present a user-study designed to examine the effect of reward/coercion persuasive strategies inspired by social power. We ran the study with 90 participants in a persuasion scenario in which they were asked to make a real choice to select a less-desirable option. The preliminary results indicated that the robot succeeded in persuading the users to select a less desirable choice compared to a better one. However, no difference was found in the perception of the robot regarding the persuasion strategies.

To be considered socially intelligent, agents must be able to adjust their behavior to different social contexts. However, those adjustments must be recognized and understood by other agents and humans, particularly to identify the social motivations that triggered such changes. In this work, we report on an experimental study that explores how external observers attribute social motivations to behavior and appearance changes that agents make to adapt to the context. Furthermore, we study how the presence of other agents in the context might impact the attribution of motivations to specific changes. Our results indicate that participants identify agents’ appearance changes as more socially and spatially motivated than behavioral changes. Additionally, agents’ awareness is rated higher when the agents adjust their physical characteristics compared to behavioral changes.