Better be reactive at the beginning. Implications of the first seconds of an encounter for the tutoring style in human-robot-interaction

The paper investigates the effects of a robot's “on-line” feedback during a tutoring situation with a human tutor. Analysis is based on a study conducted with an iCub robot that autonomously generates its feedback (gaze, pointing gesture) based on the system's perception of the tutor's actions using the idea of reciprocity of actions. Sequential micro-analysis of two opposite cases reveals how the robot's behavior (responsive vs. non-responsive) pro-actively shapes the tutor's conduct and thus co-produces the way in which it is being tutored. A dialogic and a monologic tutoring style are distinguished. The first 20 seconds of an encounter are found to shape the user's perception and expectations of the system's competences and lead to a relatively stable tutoring style even if the robot's reactivity and appropriateness of feedback changes.

[1]  Franz Kummert,et al.  “Can you answer questions, Flobi?”: Interactionally defining a robot's competence as a fitness instructor , 2012, 2012 IEEE RO-MAN: The 21st IEEE International Symposium on Robot and Human Interactive Communication.

[2]  Karola Pitsch,et al.  How infants perceive the toy robot Pleo. An exploratory case study on infant-robot-interaction , 2010, HRI 2010.

[3]  Emanuel A. Schegloff.  Opening sequencing , 2002 .

[4]  A. Alissandrakis,et al.  Human to Robot Demonstrations of Routine Home Tasks:Acknowledgment and Response to the Robot’s Feedback , 2009 .

[5]  Mark Aakhus,et al.  Perpetual Contact: Mobile Communication, Private Talk, Public Performance , 2002 .

[6]  Hideaki Kuzuoka,et al.  “The first five seconds”: Contingent stepwise entry into an interaction as a means to secure sustained engagement in HRI , 2009, RO-MAN 2009 - The 18th IEEE International Symposium on Robot and Human Interactive Communication.

[7]  Kerstin Fischer,et al.  Tutor Spotter: Proposing a Feature Set and Evaluating It in a Robotic System , 2011, International Journal of Social Robotics.

[8]  Patricia Zukow-Goldring,et al.  Assisted imitation: first steps in the seed model of language development , 2012 .

[9]  E. Schegloff.  Sequencing in Conversational Openings , 1968 .

[10]  Katharina J. Rohlfing,et al.  Towards Learning by Interacting , 2009, Creating Brain-Like Intelligence.

[11]  Katharina J. Rohlfing,et al.  Developing feedback: How children of different age contribute to a tutoring interaction with adults , 2010, 2010 IEEE 9th International Conference on Development and Learning.

[12]  K. Rohlfing,et al.  On the loop of action modification and the recipient's gaze in adult-child interaction , 2009 .