Information driven self-organization of complex robotic behaviors

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.

arXiv comment29 pages, 12 figures

References in corpus (2)

• Self-organized chaos through polyhomeostatic optimization
• Intrinsic adaptation in autonomous recurrent neural networks

Cited by in corpus (23)

• Warmth and Competence to Predict Human Preference of Robot Behavior in Physical Human-Robot Interaction
• Informational and Causal Architecture of Discrete-Time Renewal Processes
• Computational Theories of Curiosity-Driven Learning
• A novel plasticity rule can explain the development of sensorimotor intelligence
• Evolving Modular Soft Robots without Explicit Inter-Module Communication using Local Self-Attention
• Information Anatomy of Stochastic Equilibria
• Specialization in Hierarchical Learning Systems
• Measuring information transfer in a soft robotic arm
• The sensorimotor loop as a dynamical system: How regular motion primitives may emerge from self-organized limit cycles
• Closed-loop robots driven by short-term synaptic plasticity: Emergent explorative vs. limit-cycle locomotion
• Causal Influence Detection for Improving Efficiency in Reinforcement Learning
• From Biological Synapses to Intelligent Robots
• Kick control: using the attracting states arising within the sensorimotor loop of self-organized robots as motor primitives
• Intrinsically Motivated Autonomy in Human-Robot Interaction: Human Perception of Predictive Information in Robots
• Human Perception of Intrinsically Motivated Autonomy in Human-Robot Interaction
• An Information-theoretic On-line Learning Principle for Specialization in Hierarchical Decision-Making Systems
• Quantifying Emergent Behavior of Autonomous Robots
• Hierarchical Expert Networks for Meta-Learning
• Self-organized control for musculoskeletal robots
• Why collective behaviours self-organise to criticality: A primer on information-theoretic and thermodynamic utility measures
• When the goal is to generate a series of activities: A self-organized simulated robot arm
• Universal Memory Architectures for Autonomous Machines
• Autonomous learning of multiple, context-dependent tasks