Information driven self-organization of complex robotic behaviors
Georg Martius, Ralf Der, and Nihat Ay
Contact the author: Please use for correspondence this email.
Submission date: 31. Jan. 2013
published in: PLOS ONE, 8 (2013) 5, art-no. e63400
DOI number (of the published article): 10.1371/journal.pone.0063400
MSC-Numbers: 94A15, 68T05, 68T40, 37N35
PACS-Numbers: 89.70.-a, 87.19.lu, 87.85.St, 05.45.-a, 89.75.Fb
Download full preprint: PDF (1816 kB)
Information theory is a powerful tool to express principles to drive autonomous systems because it is domain invariant and allows for an intuitive interpretation. This paper studies the use of the predictive information (PI), also called excess entropy or effective measure complexity, of the sensorimotor process as a driving force to generate behavior. We study nonlinear and nonstationary systems and introduce the time-local predicting information (TiPI) which allows us to derive exact results together with explicit update rules for the parameters of the controller in the dynamical systems framework. In this way the information principle, formulated at the level of behavior, is translated to the dynamics of the synapses. We underpin our results with a number of case studies with high-dimensional robotic systems. We show the spontaneous cooperativity in a complex physical system with decentralized control. Moreover, a jointly controlled humanoid robot develops a high behavioral variety depending on its physics and the environment it is dynamically embedded into. The behavior can be decomposed into a succession of low-dimensional modes that increasingly explore the behavior space. This is a promising way to avoid the curse of dimensionality which hinders learning systems to scale well.