An Entropy-Based Approach to the Hierarchical Acquisition of Perception-Action Capabilities

Authors:
David Windridge;Mikhail Shevchenko;Josef Kittler
Affiliations:
Centre for Vision, Speech and Signal Processing, School of Electronics and Physical Sciences, University of Surrey, Guildford, UK;Centre for Vision, Speech and Signal Processing, School of Electronics and Physical Sciences, University of Surrey, Guildford, UK;Centre for Vision, Speech and Signal Processing, School of Electronics and Physical Sciences, University of Surrey, Guildford, UK
Venue:
Cognitive Vision
Year:
2009

Citing 7
Cited 0

The symbol grounding problem

CNLS '89 Proceedings of the ninth annual international conference of the Center for Nonlinear Studies on Self-organizing, Collective, and Cooperative Phenomena in Natural and Artificial Computing Networks on Emergent computation
Intelligence without representation

Artificial Intelligence
Knowledge Extraction from Transducer Neural Networks

Applied Intelligence
Application of Neurosymbolic Integration for Environment Modelling in Mobile Robots

Hybrid Neural Systems, revised papers from a workshop
Introduction to Stochastic Search and Optimization

Introduction to Stochastic Search and Optimization
A neuro-fuzzy network to generate human-understandable knowledge from data

Cognitive Systems Research
Mechanistic versus phenomenal embodiment: Can robot embodiment lead to strong AI?

Cognitive Systems Research

Quantified Score

Hi-index	0.02

Visualization

Abstract

We detail an approach to the autonomous acquisition of hierarchical perception-action competences in which capabilities are bootstrapped using an information-based saliency measure. Our principle aim is hence to accelerate learning in embodied autonomous agents by aggregating novel motor capabilities and their corresponding perceptual representations using a subsumption-based strategy. The method seeks to allocate affordance parameterizations according to the current (possibly autonomously-determined) learning goal in a manner that eliminates redundant percept-motor context, thereby obtaining maximal parametric efficiency. Experimental results within a simulated environment indicate that doing so reduces the complexity of a multistage perception-action learning problem by several orders of magnitude.