Memory-based cognitive framework: a low-level association approach to cognitive architectures

Authors:
Paul Baxter;Will Browne
Affiliations:
Cybernetics Intelligence Research Group, School of Systems Engineering, University of Reading, Reading, U.K.;Cybernetics Intelligence Research Group, School of Systems Engineering, University of Reading, Reading, U.K.
Venue:
ECAL'09 Proceedings of the 10th European conference on Advances in artificial life: Darwin meets von Neumann - Volume Part I
Year:
2009

Citing 4
Cited 1

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
A Large-scale Neurocomputational Model of Task-oriented Behavior Selection and Working Memory in Prefrontal Cortex

Journal of Cognitive Neuroscience
The animat contribution to cognitive systems research

Cognitive Systems Research
Editorial: Epigenetic robotics: modelling cognitive development in robotic systems

Cognitive Systems Research

A review of long-term memory in natural and synthetic systems

Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

At its most fundamental, cognition as displayed by biological agents (such as humans) may be described as being the manipulation and utilisation of memory. A low-level approach to the associative sensory-motor development of cognition is then appropriate, rather than the more common higher-level functional approach. A novel theoretical framework - the memory-based cognitive framework (MBCF) - is proposed based upon these considerations. A computational architecture based on the MBCF is implemented on a mobile robot platform, and experimental results are presented to demonstrate the functionality of the architecture. It is shown that this low-level, bottom-up, approach can produce adaptive behaviours, which may ultimately form the foundation of cognitively flexible agents.