Home Alone: Social Robots for Digital Ethnography of Toddler Behavior

We describe the results of a field study in which the social robot RUBI-5, was left alone for a 28 day period to interact autonomously with 16 toddlers at an Early Childhood Education Center. The study is part of the RUBI project, which started in 2004 with the goal of exploring the potential of social robotics for research and enrichment of early childhood education environments. As part of the 28 day field study RUBI-5 collected data about the facial expressions, activities, and spatio-temporal proximity of the toddlers. We found that RUBI-5 could use the facial expression data to accurately predict the children's preference for different activities: on average robot agreed with human judges as much (Pearson Correlation =0.67) as human judges agreed with each other (Pearson Correlation = 0.68). In addition RUBI discovered some useful aspects of the social structure of the toddler's group. The study is an important milestone in social robotics, both for the length of time the robot could interact autonomously with children, and for the richness of the data that it provided. The results indicate that social robots have the potential to act as low cost, autonomous "digital ethnographers" in a manner that may revolutionize the science and technology of early childhood education.

[1]  Javier R. Movellan,et al.  Design and early evaluation of the RUBI-5 sociable robots , 2012, 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL).

[2]  Stanley Wasserman,et al.  Social Network Analysis: Methods and Applications , 1994, Structural analysis in the social sciences.

[3]  J. Movellan,et al.  Ruby: A Robotic Platform for Real-time Social Interaction , 2004 .

[4]  J.R. Movellan,et al.  The RUBI/QRIO Project: Origins, Principles, and First Steps , 2005, Proceedings. The 4nd International Conference on Development and Learning, 2005..

[5]  J. Movellan,et al.  Automatic cry detection in early childhood education settings , 2008, 2008 7th IEEE International Conference on Development and Learning.

[6]  Ian R. Fasel,et al.  The RUBI project: A progress report , 2007, 2007 2nd ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[7]  M. Virnes,et al.  Building a more effective teaching robot using apprenticeship learning , 2008, 2008 7th IEEE International Conference on Development and Learning.

[8]  Fumihide Tanaka,et al.  Socialization between toddlers and robots at an early childhood education center , 2007, Proceedings of the National Academy of Sciences.

[9]  Javier R. Movellan,et al.  Sociable robot improves toddler vocabulary skills , 2009, 2009 4th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[10]  Vincent Lepetit,et al.  DAISY: An Efficient Dense Descriptor Applied to Wide-Baseline Stereo , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[11]  Gwen Littlewort,et al.  The computer expression recognition toolbox (CERT) , 2011, Face and Gesture 2011.

[12]  Linton C. Freeman,et al.  Carnegie Mellon: Journal of Social Structure: Visualizing Social Networks Visualizing Social Networks , 2022 .