An experimental comparison of imitation paradigms used in social robotics

We study and contrast particular issues arising in two social learning paradigms that are widely used in robotics research: (i) following or matched-dependent behaviour and (ii) static observational learning. Experiments are carried out with physical Khepera robots whose controllers include motor schemas and the new neural network based methods for model agent-centred perception of angle and distance. The robots are trained to perceive the dynamic movement of a human or robot demonstrator carrying a light source. The robots learn the behaviour either through the perception from a static location or while following. The differences and implications of the results of both the following and observation mechanisms are compared and contrasted.

[1]  Chrystopher L. Nehaniv,et al.  Like Me?- Measures of Correspondence and Imitation , 2001, Cybern. Syst..

[2]  Sorin Moga,et al.  From Perception-Action Loops to Imitation Processes: A Bottom-Up Approach of Learning by Imitation , 1998, Appl. Artif. Intell..

[3]  Phillip J. McKerrow,et al.  Introduction to robotics , 1991 .

[4]  L. Steels.  The Biology and Technology of Intelligent Autonomous Agents , 1995, NATO ASI Series.

[5]  Masayuki Inaba,et al.  Learning by watching: extracting reusable task knowledge from visual observation of human performance , 1994, IEEE Trans. Robotics Autom..

[6]  Gillian M. Hayes,et al.  A Robot Controller Using Learning by Imitation , 1994 .

[7]  Chrystopher L. Nehaniv,et al.  Synchrony and perception in robotic imitation across embodiments , 2003, Proceedings 2003 IEEE International Symposium on Computational Intelligence in Robotics and Automation. Computational Intelligence in Robotics and Automation for the New Millennium (Cat. No.03EX694).

[8]  E. Thorndike.  “Animal Intelligence” , 1898, Nature.

[9]  Ulrich Nehmzow.  Animal and Robot Navigation , 1995 .

[10]  K. Dautenhahn,et al.  Imitation in Animals and Artifacts , 2002 .

[11]  Robin R. Murphy,et al.  Introduction to AI Robotics , 2000 .

[12]  Dearborn.  Animal Intelligence: An Experimental Study of the Associative Processes in Animals , 1900 .

[13]  John Cohen.  Social Learning and Imitation , 1945, Nature.

[14]  Thomas R. Zentall,et al.  IMITATION IN ANIMALS: EVIDENCE, FUNCTION, AND MECHANISMS , 2001, Cybern. Syst..

[15]  Maja J. Mataric,et al.  Movement control methods for complex, dynamically simulated agents: Adonis dances the Macarena , 1998, AGENTS '98.

[16]  Robert Hecht-Nielsen,et al.  Applications of counterpropagation networks , 1988, Neural Networks.

[17]  K. Dautenhahn,et al.  Trying to imitate-a step towards releasing robots from social isolation , 1994, Proceedings of PerAc '94. From Perception to Action.

[18]  B. Scassellati.  Imitation and mechanisms of joint attention: a developmental structure for building social skills on a humanoid robot , 1999 .

[19]  Aude Billard,et al.  Grounding communication in situated, social robots , 1997 .

[20]  R. W. Mitchell,et al.  A Comparative-Developmental Approach to Understanding Imitation , 1987 .

[21]  E. Thorndike.  Review of Animal Intelligence: An Experimental Study of the Associative Processes in Animals. , 1898 .

[22]  Robin I. M. Dunbar.  The thinking ape: Evolutionary origins of intelligence , 1995 .

[23]  Ronald C. Arkin,et al.  An Behavior-based Robotics , 1998 .

[24]  Jason Noble,et al.  Imitation or something simpler? modeling simple mechanisms for social information processing , 2002 .

[25]  C. Heyes,et al.  Social learning in animals : the roots of culture , 1996 .