Multimodal Child-Robot Interaction: Building Social Bonds

Tony Belpaeme,Rachel Wood,Robin Read,Giacomo Sommavilla,Raquel Ros-Espinoza,Valentin Enescu,Piero Cosi,Heriberto Cuayáhuitl,Stefania Racioppa,Lola Cañamero,Fabio Tesser,Aryel Beck,Giulio Paci,Yiannis Demiris,Antione Hiolle,Bernd Kiefer,Matthew Lewis,Rosemarijn Looije,Ilaria Baroni,Marco Nalin,Paul Baxter ,Mark A Neerincx ,George Athanasopoulos ,Ivana Kruijff‐Korbayová ,Rémi Humbert

doi:10.5898/jhri.1.2.belpaeme

Abstract

For robots to interact effectively with human users they must be capable of coordinated, timely behavior in response to social context. The Adaptive Strategies for Sustainable Long-Term Social Interaction (ALIZ-E) project focuses on the design of long-term, adaptive social interaction between robots and child users in real-world settings. In this paper, we report on the iterative approach taken to scientific and technical developments toward this goal: advancing individual technical competencies and integrating them to form an autonomous robotic system for evaluation "in the wild." The first evaluation iterations have shown the potential of this methodology in terms of adaptation of the robot to the interactant and the resulting influences on engagement. This sets the foundation for an ongoing research program that seeks to develop technologies for social robot companions.

Highlights

The ultimate goal of Human-Robot Interaction (HRI) is to have robots working in real-time with real people
The technical difficulties associated with coordinating the functioning of multiple action systems to provide coherent, flexible, and timely behavior are enough to ensure that projects attempting HRI ‘in the wild’ are rare
We previously found that adults were able to interpret body poses displayed by the robot as conveying certain emotions, which is relevant for the Nao robot used in ALIZ-E since it does not have facial articulation and as such is very limited in communicating emotion when not moving its body

Summary

Introduction

The ultimate goal of Human-Robot Interaction (HRI) is to have robots working in real-time with real people. The technical difficulties associated with coordinating the functioning of multiple action systems to provide coherent, flexible, and timely behavior are enough to ensure that projects attempting HRI ‘in the wild’ (i.e. real robots interacting with real people in real time) are rare. Rarer yet are those HRI projects aiming to go beyond the level of moment-by-moment interchange to achieve long-term social coherence. While the interaction between children and robots has been studied (e.g. Draper & Clayton, 1992; Kanda, Hirano, Eaton, & Ishiguro, 2004; Tanaka, Cicourel, & Movellan, 2007), the Adaptive Strategies for Sustainable Long-Term Social Interaction (ALIZ-E) project differs in its ambition as a multi-partner initiative focused on long-term adaptive social interaction between robots and child users built up through multiple sessions extended over a period of days

Objectives

Results

Conclusion