Options
Information driven self-organization of complex robotic behaviors
Publikationstyp
Journal Article
Date Issued
2013-05-13
Sprache
English
Author(s)
Herausgeber*innen
Journal
Volume
8
Issue
5
Article Number
e63400
Citation
PLoS ONE 8(5): e63400 (2013)
Publisher DOI
Scopus ID
PubMed ID
23723979
ArXiv ID
Publisher
PLOS
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.
Subjects
Computer Science - Robotics
Computer Science - Robotics
Computer Science - Information Theory
Computer Science - Learning
Mathematics - Information Theory
94A15, 94A17, 37N35, 68T05, 68T40
I.2.9; H.1.1; I.2.6
DDC Class
004: Informatik
530: Physik