From Babies to Robots: The Contribution of Developmental Robotics to Developmental Psychology

Abstract

The latest developments in artificial intelligence (AI) and machine learning, and the parallel advances in robotics, have contributed recently to a shift in the scientific approach to modeling human intelligence. These innovations, accompanied by the new emphasis on embodied and grounded cognition in AI and psychology, have led to the establishment of the field of developmental robotics. This field features an interdisciplinary approach, built on collaboration between cognitive robotics and child psychology, to the autonomous design of behavioral and cognitive capabilities in artificial cognitive agents, such as robots, which is inspired by developmental principles and mechanisms observed in children. In this article, we illustrate the benefits of this approach by presenting a case study of a baby robot with a focus on the role of embodiment during early word learning, as well as an overview of several developmental robotics model of perceptual, social, and language development.

From social brains to social robots: applying neurocognitive insights to human–robot interaction

“…The contributions in this section are at the core of developmental robotics [13], thereby bridging cognitive robotics and social robotics, and work towards achieving autonomous behaviour in robots by embracing a bottom-up embodied cognition and internal learning approach. As the contributions show, these biology-and psychology-inspired social robotics systems can lead to an impressive range of socially engaging behaviours, such as attention-grabbing emotional facial expressions [14], and even trust and theory-of-mind [13]. Crucially, these perspectives directly provide new insights for developmental psychology, for example into developmental mechanisms of social behaviour as well as clinical insights into autism spectrum condition [15,16].…”

Shall I Trust You? From Child–Robot Interaction to Trusting Relationships

“…With children, the factors underpinning child human-robot interaction have not been systematically explored. There are several studies that inform about ways in which children interact, play, and learn from a robotic agent in school and educational contexts (Kanda et al, 2004;Okumura et al, 2013a,b;Breazeal et al, 2016;Baxter et al, 2017;Belpaeme et al, 2018;Cangelosi and Schlesinger, 2018;Di Dio et al, 2019). These studies have shown that children tend to interact with robot partners in a humanlike manner, proving to be sensitive to verbal and non-verbal signals, such as eye gaze (Okumura et al, 2013a,b), and often attributing mentalistic competencies to the robot (for a review, see Marchetti et al, 2018).…”

Transferring Adaptive Theory of Mind to Social Robots: Insights from Developmental Psychology to Robotics

“…In fact, on the one hand, developing architectures for robots inspired by developmental mechanisms resulted in more sophisticated robots with increasingly complex abilities and behavior [41]. On the other hand, robots have been useful in the modelling of human developmental processes within an embodied agent and the prediction of developmental phenomena which were successively validated by infants studies [2]. Therefore, developing robot architectures based on ToM can result in increasingly complex adaptive social robots as well as in a new tool for investigating models from developmental psychology and provide insights into human capabilities which are yet to be fully understood, including the mentalizing ability itself.…”

“…For example, humans' positive attitude towards non-human agents has increased with the humanoid aspect of robots, however, this drops when a mismatch of agent features is noticed [1] due to the robots' still limited (non-human-like) social capabilities (uncanny valley effect). Currently, robots' architectures generally rely on association and simulation principles to learn about the social world, which enable them to recognize and predict actions from observing other agents performing such actions [2,3]. However, robots' recognition of complex mental states is still limited, as is their understanding of the humans they interact with.…”