Editorial: Computational Approaches for Human-Human and Human-Robot Social Interactions

摘要

Automatised detection and analysis of nonverbal social signals can be of particular relevance not only to human-human interaction (HHI), but also to human-robot interaction (HRI). Over the last decade, much research effort has been dedicated to improving robots' capabilities regarding perceiving, interacting, and cooperating with humans. Indeed, social HRI requires augmenting robots' standard functionality by the ability to recognize and interpret human social signals, in order to be able to engage naturally and intuitively with a human. Simultaneously, research efforts are being put in examining the human side of HRI, namely, the human mechanisms social cognition in interactions with artificial agents (embodied robots specifically). This is crucial in order to understand how the human brain processes social signals carried out by non-human agents, and whether such agents can evoke mechanisms of social cognition in humans. Also in this case, ML techniques have proved to be useful to explore patterns of neural and behavioural activity of the human counterparts. This Research Topic is dedicated to exploring computational techniques for the analysis of nonverbal social signals in HHI as well as HRI. Specifically, we focus on ML methodologies, as well as other computational approaches for nonverbal behaviour understanding and multi-modal data analysis. It brings together ten selected papers that reflect some of the current computational approaches applied to HHI and HRI.Bartlett et al. focus on movement analysis based on internal states identification. Video clips of social interactions as either the original scene or in the form of 2D body pose data were shown to the participants who later accessed internal state perception. This data was analysed to determine whether the full scene clips were more informative than 2D body pose. Results showed that participants were able to identify interaction imbalance, valence and engagement independent to the types of the videos. ML achieved similar performances as well, which can be interpreted as it can successfully decode and classify internal states using low-dimensional data.Kory-Westlund and Breazeal investigate whether a social robot could increase children's rapport, positive emotion, acceptance, engagement, closeness, and learning. The robot is entrained its speech and behaviour to individual children and provided an appropriate backstory about its abilities. The data analysis performed showed that robot's entrainment led children to show more positive emotions; it affected children's emulation of the robot's words in their own stories. Additionally, children who heard robot's backstory were more accepting it, find it more human-like and agreed more to its requests.Bloch et al. study the relevance of interpersonal synchrony (IS) for Autism Spectrum Disorder (ASD). IS is related to empathy, rapport, thus enables successful HHI while individuals with ASD have difficulties to IS. Authors present a comprehensive review on IS in ASD, and then propose a theoretic concept based on temporal processing of sensory input of interactions. Georgescu et al. present an ML method to study IS difficulties in ASD. IS between the head and upper body was quantified using Motion Energy Analysis, whose results were used to train a Support Vector Machine to classify individuals with ASD and typically developed individuals.Biancardi et al. propose a computational model that allow to change the impression of warmth and competences of an embodied conversational agent that can interact with a human. The impression of warmth and competence are changed in real-time to adapt to the human in order to maximise engagement. The system is tested as a museum guide and show that the hypothesis of warmth primacy may be valid.Niewiadomski et al. focus on the analysis of social activities related to food and eating, as well as computational and technological approaches addressing such activities. The paper describes the ap