Through the Looking-Glass with ALICE - Trying to Imitate using Correspondences

Interactive behavior of biological agents represents an important area in life as we know it. Behavior matching and imitation may serve as fundamental mechanisms for the development of societies and individuals. Imitation and observational learning as means for acquiring new behaviors also represent a largely untapped resource for robotics and artificial life — both in the study of life as it could be and for applications of biological tricks to synthetic worlds. This paper describes a new general imitating mechanism called ALICE (Action Learning for Imitation via Correspondences between Embodiments) that addresses the important correspondence problem in imitation. The mechanism is implemented and illustrated on the chessworld test-bed that was used in previous work to address the effects of agent embodiment, metrics and granularity when learning how to imitate another. The performance of the imitating agent is shown to improve when ALICE is complementing its imitation behavior generating mechanism.

[1]  S. Walker.  Social Learning: Psychological and Biological Perspectives, Thomas R. Zentall, Bennet G. Galef Jr. (Eds.). Lawrence Erlbaum, Hillsdale, New Jersey (1988), xi , 1988 .

[2]  Masayuki Inaba,et al.  Design and implementation of a system that generates assembly programs from visual recognition of human action sequences , 1990, EEE International Workshop on Intelligent Robots and Systems, Towards a New Frontier of Applications.

[3]  Henry Lieberman,et al.  Watch what I do: programming by demonstration , 1993 .

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

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

[6]  Kerstin Dautenhahn,et al.  Getting to know each other - Artificial social intelligence for autonomous robots , 1995, Robotics Auton. Syst..

[7]  G. Rizzolatti,et al.  Action recognition in the premotor cortex. , 1996, Brain : a journal of neurology.

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

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

[10]  M. Arbib,et al.  Language within our grasp , 1998, Trends in Neurosciences.

[11]  Aude Billard,et al.  Grounding communication in autonomous robots: An experimental study , 1998, Robotics Auton. Syst..

[12]  R. Byrne.  Imitation without intentionality. Using string parsing to copy the organization of behaviour , 1999, Animal Cognition.

[13]  K. Dautenhahn,et al.  The Mirror System, Imitation, and the Evolution of Language , 1999 .

[14]  C. Heyes,et al.  What Is the Significance of Imitation in Animals , 2000 .

[15]  Kerstin Dautenhahn,et al.  Of hummingbirds and helicopters: An algebraic framework for interdisciplinary studies of imitation a , 2000 .

[16]  Kerstin Dautenhahn,et al.  Learning how to do things with imitation , 2000 .

[17]  Joshua G. Hale,et al.  Using Humanoid Robots to Study Human Behavior , 2000, IEEE Intell. Syst..

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

[19]  K. Dautenhahn,et al.  Imitation of Sequential and Hierarchical Structure in Action: Experimental Studies with Children and Chimpanzees , 2002 .

[20]  Aude Billard,et al.  Imitation: a Means to Enhance Learning of a Synthetic Proto-language in an Autonomous Robot , 1999 .

[21]  L. Herman.  Vocal, social, and self-imitation by bottlenosed dolphins , 2002 .

[22]  K. Dautenhahn,et al.  The agent-based perspective on imitation , 2002 .

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