A Synchrony-Based Perspective for Partner Selection and Attentional Mechanism in Human-Robot Interaction

Abstract

Future robots must co-exist and directly interact with human beings. Designing these agents imply solving hard problems linked to human-robot interaction tasks. For instance, how a robot can choose an interacting partner among various agents and how a robot locates regions of interest in its visual field. Studies of neurobiology and psychology collectively named synchrony as an indispensable parameter for social interaction. We assumed that Human-Robot interaction could be initiated by synchrony detection. In this paper, we present a developmental approach for analyzing unintentional synchronization in human-robot interaction. Using our neural network model, the robot learns from a babbling step its inner dynamics by associating its own motor activities (oscillators) with the visual stimulus induced by its own motion. After learning the robot is capable of choosing an interacting agent and of localizing the spatial position of its preferred partner by synchrony detection.

Influence of stimulus velocity profile on rhythmic visuomotor coordination.

“…Finally, the present findings can be also of importance to improve our interactions with virtual agents and humanoid robots (Chaminade et al, 2005;Hasnain, Mostafaoui, & Gaussier, 2013;Kopp, 2010;Kupferberg et al, 2011). Several previous studies have tried to improve the interaction of these agents by enhancing the human nature of their appearance despite there is no demonstrated influence at our knowledge of such manipulations on our movement coordination (Coey et al, 2011a).…”

Building brains that communicate like machines

“…This kind of model allows future machines to better generalize their learning and to acquire new social skills. In other recent examples, using a very simple neural network providing minimal sensorimotor adaptation capabilities to the robot, unintentional motor coordination could emerge during an imitation game (of a simple gesture) with a human (Hasnain et al 2012;. An extension of this work demonstrated that a robot could quickly and "online" learn more complex gestures and synchronize its behavior to the human partner based on the same sensorimotor approach (Ansermin et al 2016).…”

Simulating the Emergence of Early Physical and Social Interactions : A Developmental Route through Low Level Visuomotor Learning

“…Our short-term future works are aiming to use this model on an hydraulic robot in order to obtain a realistic force controlled arm leading to more "natural" movements. In order to maintain the interaction and to give the robot capabilities to learn new and more complex movements, we are also planing to introduce the notion of synchrony detection between the oscillators controlling the arm and the visual stimuli as proposed in our previous work on simple oscillatory movements [24]. Thus, a refined interaction can be obtained during immediate and differed imitation games.…”