From Perception-Action Loops to Imitation Processes: A Bottom-Up Approach of Learning by Imitation

This paper proposes a neural architecture for a robot in order to learn how to imitate a sequence of movements performed by another robot or by a human. The main idea is that the imitation process does not need to be given to the system but can emerge from a misinterpretation of the perceived situation at the level of a simple sensory-motor system. The robot controller is based on a Perception-Action (PerAc) architecture. This architecture allows an autonomous robot to learn by itself sensory-motor associations with a delayed reward. Here, we show how the same architecture can also be used by a “student” robot to learn to imitate another robot, allowing the student robot to discover by itself solutions to a particular problem or to learn from another robot what to do. We discuss the difficulty linked to the segmentation of the actions to imitate. This imitation problem is demonstrated by a task of learning a sequence of movements and their precise timing. Another interesting aspect of this work is that th...

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

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

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

[4]  J. Piaget,et al.  LA NAISSANCE DE L'INTELLIGENCE CHEZ L'INFANT , 1939 .

[5]  S Ullman,et al.  Shifts in selective visual attention: towards the underlying neural circuitry. , 1985, Human neurobiology.

[6]  Rodney A. Brooks,et al.  A Robust Layered Control Syste For A Mobile Robot , 2022 .

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

[8]  R. Hecht-Nielsen.  Counterpropagation networks. , 1987, Applied optics.

[9]  D. Wood.  Social interaction as tutoring , 1989 .

[10]  David E. Rumelhart,et al.  Product Units: A Computationally Powerful and Biologically Plausible Extension to Backpropagation Networks , 1989, Neural Computation.

[11]  M. Tomasello.  Cultural transmission in the tool use and communicatory signaling of chimpanzees , 1990 .

[12]  James S. Albus,et al.  Outline for a theory of intelligence , 1991, IEEE Trans. Syst. Man Cybern..

[13]  Jean-Louis Deneubourg,et al.  The dynamics of collective sorting robot-like ants and ant-like robots , 1991 .

[14]  S. Grossberg,et al.  A neural network model of adaptively timed reinforcement learning and hippocampal dynamics. , 1992, Brain research. Cognitive brain research.

[15]  A. Whiten,et al.  On the Nature and Evolution of Imitation in the Animal Kingdom: Reappraisal of a Century of Research , 1992 .

[16]  C. Heyes,et al.  Imitation in Rats: Initial Responding and Transfer Evidence , 1992 .

[17]  Y. Kuniyoshi.  The Science of Imitation - Towards Physically and Socially Grounded Intelligence , 1994 .

[18]  Philippe Gaussier,et al.  Avoiding the world model trap: An acting robot does not need to be so smart! , 1994 .

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

[20]  Stephen Grossberg,et al.  A neural model of timed response learning in the cerebellum , 1994, Neural Networks.

[21]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

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

[23]  Philippe Gaussier,et al.  PerAc: A neural architecture to control artificial animals , 1995, Robotics Auton. Syst..

[24]  Maja J. Mataric,et al.  Issues and approaches in the design of collective autonomous agents , 1995, Robotics Auton. Syst..

[25]  C. Joulain,et al.  Are shaping techniques the correct answer the control of visually guided autonomous robots , 1996 .

[26]  P. Bakker,et al.  Robot See, Robot Do : An Overview of Robot Imitation , 1996 .

[27]  Gillian M. Hayes,et al.  Imitative Learning Mechanisms in Robots and Humans , 1996 .

[28]  Yasuo Kuniyoshi,et al.  Learning of oculo-motor control: a prelude to robotic imitation , 1996, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems. IROS '96.

[29]  A. Whiten,et al.  Imitative learning of artificial fruit processing in children (Homo sapiens) and chimpanzees (Pan troglodytes). , 1996, Journal of comparative psychology.

[30]  Philippe Gaussier,et al.  Living in a partially structured environment: How to bypass the limitations of classical reinforcement techniques , 1997, Robotics Auton. Syst..

[31]  Philippe Gaussier,et al.  Learning to build visual categories from perception-action associations , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.

[32]  Sorin Moga,et al.  Autonomous robot learning: what can we take for free? , 1997, ISIE '97 Proceeding of the IEEE International Symposium on Industrial Electronics.

[33]  L. Matthews.  Cognitive science perspectives on personality and emotion , 1997 .

[34]  Lucas Salvador.  Assimilation, Imitation and the Elementary Social Fact. Towards a Definition of Social Interactions , 1997 .

[35]  J. Banquet,et al.  Chapter 4 Space-time, order, and hierarchy in fronto-hippocampal system: A neural basis of personality , 1997 .

[36]  A. Berthoz,et al.  Le sens du mouvement , 1997 .

[37]  Philippe Gaussier,et al.  Visual navigation in an open environment without map , 1997, Proceedings of the 1997 IEEE/RSJ International Conference on Intelligent Robot and Systems. Innovative Robotics for Real-World Applications. IROS '97.

[38]  Philippe Gaussier,et al.  Planification versus sensory-motor conditioning: what are the issues? , 1998 .

[39]  Sorin Moga,et al.  From Perception-Action loops to imitation processes , 1998 .