Ghiles Mostafaoui

Synchrony as a tool to establish focus of attention for autonomous robots

With technology and artificial intelligence advancements, the notion of professional service robots has emerged. Consequently, robots must share their physical and social space with human beings. How can robots select a partner among many interactants and how can they focus their attention on regions of interest? As psychologists consider synchrony as an important parameter for social interaction, we hypothesize that in the case of social interaction, people focus their attention on regions of interest where the visual stimuli are synchronized with their inner dynamics. Then, we assume that a mechanism able to detect synchrony between internal dynamics of a robot and external visual stimuli (optical flow) can be used as a starting point for human robot interaction. This kind of mechanism can also be involved in more complex tasks of interaction such as partner selection. Inspired by human psychological and neurobiological data, we propose a synchrony-based neural network architecture capable of selecting the robot partner and of locating focus of attention.

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

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.

“Synchrony” as a way to choose an interacting partner

Robots are poised to fill a growing number of roles in todays society. In future, we could have robots expected to behave as companion in our home, offices etc. Moving to social robotics imply to address several issues related to human-robot interactions for instance, how the robot can develop an attentional mechanism and select an interacting agent among several interactants. We took our inspiration from neurobiological and psychological studies suggesting that synchrony is an essential parameter for social interaction. We assumed that synchrony detection could be used for intitiating human robot interaction. We present a neural network architecture able to focus the attention of the robot and to select an interacting partner on the basis of synchrony detection.

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

In this paper, we propose a bio-inspired and developmental neural model that allows a robot, after learning its own dynamics during a babbling phase, to gain imitative and shape recognition abilities leading to early attempts for physical and social interactions. We use a motor controller based on oscillators. During the babbling step, the robot learns to associate its motor primitives (oscillators) to the visual optical flow induced by its own arm. It also statically learn to recognize its arm by selecting moving local view (feature points) in the visual field. In real indoor experiments we demonstrate that, using the same model, early physical (reaching objects) and social (immediate imitation) interactions can emerge through visual ambiguities induced by the external visual stimuli.

Unintentional entrainment effect in a context of Human Robot Interaction: An experimental study

Modelling nonverbal communication in robotics is a crucial issue to improve Human Robot interactions (HRI). Among several nonverbal behaviours we focus in this article on unintentional rhythmic entrainment and synchronization which has been proven to be highly important in intuitive and natural Human Human communication. Hence, the rising question is whether or no this phenomenon can be reproduced in a context of HRI and what are the prerequisites to ensure its emergence. In this paper, we study rhythmical interactions during imitation games between a NAO robot and naive subjects. We analysed two main types of interactions, a first where NAO performs movements at a fixed rhythm (unidirectional) and a second one where the robot is able to adopt the human motion dynamic (bidirectional) using a neural modelling of the entrainment effect based on dynamical systems. We show that using such model allows us to reach synchronization during the interactions and that both partners (robot and human) adapt their frequency as observed in natural HHI. This puts forward the importance of bidirectionality for HRI. Moreover, the participants shifted their motion dynamics during the interaction without noticing it, proving the presence of such unintentional rhythmic entrainment in HRI.