Information driven self-organization of complex robotic behaviors

TL;DR

This paper explores how predictive information can drive autonomous robotic behaviors, enabling complex, adaptive, and scalable actions through information-theoretic principles applied to sensorimotor dynamics.

Contribution

It introduces the time-local predicting information (TiPI) for deriving explicit control update rules in nonlinear, nonstationary systems, linking information principles to system dynamics.

Findings

Robots exhibit spontaneous cooperation with decentralized control.

Humanoid robots develop diverse behaviors based on physics and environment.

Behavior decomposes into low-dimensional modes exploring the behavior space.

Abstract

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.