From unknown sensors and actuators to actions grounded in sensorimotor perceptions

This article describes a developmental system based on information theory implemented on a real robot that learns a model of its own sensory and actuator apparatus. There is no innate knowledge regarding the modalities or representation of the sensory input and the actuators, and the system relies on generic properties of the robot’s world, such as piecewise smooth effects of movement on sensory changes. The robot develops the model of its sensorimotor system by first performing random movements to create an informational map of the sensors. Using this map, the robot then learns what effects the different possible actions have on the sensors. After this developmental process, the robot can perform basic visually guided movement.

[1]  J. B. Uexküll,et al.  Streifzüge durch die Umwelten von Tieren und Menschen : ein Bilderbuch unsichtbarer Welten , 1934 .

[2]  R. Held,et al.  MOVEMENT-PRODUCED STIMULATION IN THE DEVELOPMENT OF VISUALLY GUIDED BEHAVIOR. , 1963, Journal of comparative and physiological psychology.

[3]  S. Laughlin.  A Simple Coding Procedure Enhances a Neuron's Information Capacity , 1981, Zeitschrift fur Naturforschung. Section C, Biosciences.

[4]  E. Newman,et al.  Integration of visual and infrared information in bimodal neurons in the rattlesnake optic tectum. , 1981, Science.

[5]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[6]  T. Wiesel.  The postnatal development of the visual cortex and the influence of environment. , 1982, Bioscience reports.

[7]  T. Wiesel.  Postnatal development of the visual cortex and the influence of environment , 1982, Nature.

[8]  S. Parker,et al.  Origins of Intelligence , 1983, Springer US.

[9]  M Kuperstein,et al.  Neural model of adaptive hand-eye coordination for single postures. , 1988, Science.

[10]  J. Crutchfield.  Information and Its Metric , 1990 .

[11]  Thomas M. Cover,et al.  Elements of Information Theory , 2005 .

[12]  Jianhua Lin,et al.  Divergence measures based on the Shannon entropy , 1991, IEEE Trans. Inf. Theory.

[13]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[14]  S. Balachandar,et al.  Three-Dimensional Instabilities of Mantle Convection with Multiple Phase Transitions , 1993, Science.

[15]  D. Ruderman.  The statistics of natural images , 1994 .

[16]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[17]  L. Steels.  The origins of intelligence , 1996 .

[18]  William Bialek,et al.  Spikes: Exploring the Neural Code , 1996 .

[19]  T. Sejnowski,et al.  Quantifying neighbourhood preservation in topographic mappings , 1996 .

[20]  A. Basu,et al.  2 Minimum distance estimation: The approach using density-based distances , 1997 .

[21]  Benjamin Kuipers,et al.  Map Learning with Uninterpreted Sensors and Effectors , 1995, Artif. Intell..

[22]  A. Meltzoff,et al.  Explaining Facial Imitation: A Theoretical Model. , 1997, Early development & parenting.

[23]  P. Rochat.  Self-perception and action in infancy , 1998, Experimental Brain Research.

[24]  Stewart W. Wilson,et al.  Dynamic Categorization of Explorative Behaviors for Emergence of Stable Sensorimotor Configurations , 1998 .

[25]  D Purves,et al.  The distribution of oriented contours in the real world. , 1998, Proceedings of the National Academy of Sciences of the United States of America.

[26]  William Bialek,et al.  Adaptive Rescaling Maximizes Information Transmission , 2000, Neuron.

[27]  H. Sebastian Seung,et al.  Algorithms for Non-negative Matrix Factorization , 2000, NIPS.

[28]  D. Polani.  Measures for the organization of self-organizing maps , 2001 .

[29]  James L. McClelland,et al.  Autonomous Mental Development by Robots and Animals , 2001, Science.

[30]  Lakhmi C. Jain,et al.  Self-Organizing neural networks: recent advances and applications , 2001 .

[31]  A. Noë,et al.  Acting out our sensory experience , 2001 .

[32]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[33]  A. Noë,et al.  A sensorimotor account of vision and visual consciousness. , 2001, The Behavioral and brain sciences.

[34]  Carsten O. Daub,et al.  The mutual information: Detecting and evaluating dependencies between variables , 2002, ECCB.

[35]  James R. Schott,et al.  Principles of Multivariate Analysis: A User's Perspective , 2002 .

[36]  Terrence J Sejnowski,et al.  Communication in Neuronal Networks , 2003, Science.

[37]  J. Kevin O'Regan,et al.  Is There Something Out There? Inferring Space from Sensorimotor Dependencies , 2003, Neural Computation.

[38]  Masayuki Inaba,et al.  From visuo-motor self learning to early imitation-a neural architecture for humanoid learning , 2003, 2003 IEEE International Conference on Robotics and Automation (Cat. No.03CH37422).

[39]  J. Kevin O'Regan,et al.  Perception of the Structure of the Physical World Using Unknown Multimodal Sensors and Effectors , 2003, NIPS.

[40]  Giulio Sandini,et al.  Developmental robotics: a survey , 2003, Connect. Sci..

[41]  Chrystopher L. Nehaniv,et al.  Sensory channel grouping and structure from uninterpreted sensor data , 2004, Proceedings. 2004 NASA/DoD Conference on Evolvable Hardware, 2004..

[42]  Yasuo Kuniyoshi,et al.  Emergence and Categorization of Coordinated Visual Behavior Through Embodied Interaction , 1998, Machine Learning.

[43]  Philippe Gaussier,et al.  Learning Invariant Sensorimotor Behaviors: A Developmental Approach to Imitation Mechanisms , 2004, Adapt. Behav..

[44]  Chrystopher L. Nehaniv,et al.  The Effects on Visual Information in a Robot in Environments with Oriented Contours , 2004 .

[45]  Chrystopher L. Nehaniv,et al.  Discovering Motion Flow by Temporal-Informational Correlations in Sensors , 2005 .

[46]  C.L. Nehaniv,et al.  From Unknown Sensors and Actuators to Visually Guided Movement , 2005, Proceedings. The 4nd International Conference on Development and Learning, 2005..

[47]  Deepak Kumar,et al.  BRINGING UP ROBOT: FUNDAMENTAL MECHANISMS FOR CREATING A SELF-MOTIVATED, SELF-ORGANIZING ARCHITECTURE , 2005, Cybern. Syst..

[48]  Chrystopher L. Nehaniv,et al.  Sensor adaptation and development in robots by entropy maximization of sensory data , 2005, 2005 International Symposium on Computational Intelligence in Robotics and Automation.

[49]  Chrystopher L. Nehaniv,et al.  Measuring Informational Distances Between Sensors and Sensor Integration , 2006 .

[50]  Benjamin Kuipers,et al.  Bootstrap learning of foundational representations , 2006, Connect. Sci..

[51]  Peter Stone,et al.  Towards autonomous sensor and actuator model induction on a mobile robot , 2006, Connect. Sci..

[52]  Olaf Sporns,et al.  Methods for quantifying the informational structure of sensory and motor data , 2007, Neuroinformatics.