a sensor-based learning algorithm for the self-organization of robot behavior一个基于传感器的自组织学习算法的机器人的行为.pdfVIP

Algorithms 2009, 2, 398-409; DOI: 10.3390/a2010398 OPEN ACCESS algorithms ISSN 1999-4893 /journal/algorithms Article A Sensor-Based Learning Algorithm for the Self-Organization of Robot Behavior Frank Hesse , Georg Martius , Ralf Der and J. Michael Herrmann ¨ Max Planck Institute for Dynamics and Self-Organization, Bunsenstrasse 10, 37073 Gottingen, Germany; ¨ ¨ Bernstein Center for Computational Neuroscience Gottingen, Bunsenstrasse 10, 37073 Gottingen, Germany ¨ Institute for Nonlinear Dynamics, Georg-August-University Gottingen, Bunsenstrasse 10, 37073 ¨ Gottingen, Germany Max Planck Institute for Mathematics in the Sciences, Inselstrasse 22, 04103 Leipzig, Germany University of Edinburgh, School of Informatics, IPAB, 10 Crichton Street, Edinburgh, EH8 9AB, U.K. E-Mail: frank@nld.ds.mpg.de, georg@nld.ds.mpg.de, ralfder@mis.mpg.de, mherrman@inf.ed.ac.uk Author to whom correspondence should be addressed. Received: 30 November 2008 / Accepted: 26 February 2009 / Published: 4 March 2009 Abstract: Ideally, sensory information forms the only source of information to a robot. We consider an algorithm for the self-organization of a controller. At short time scales the con- troller is merely reactive but the parameter dynamics and the acquisition of knowledge by an internal model lead to seemingly purposeful behavior on l