Kernel Based Cognitive Architecture for Autonomous Agents

TL;DR

This paper proposes an evolutionary, kernel-based cognitive architecture for autonomous agents that enables the development of mental functions without predefined perceptual patterns, using constructivist principles.

Contribution

It introduces a novel kernel-based approach to evolve cognitive functions in autonomous agents, addressing limitations of schematic models.

Findings

Kernel-based architecture supports autonomous evolution of cognitive abilities

The approach enables agents to develop mental functions without predefined patterns

Constructivist theory underpins the evolution of cognition in the model

Abstract

One of the main problems of modern cognitive architectures is an excessively schematic approach to modeling the processes of cognitive activity. It does not allow the creation of a universal architecture that would be capable of reproducing mental functions without using a predetermined set of perceptual patterns. This paper considers an evolutionary approach to creating a cognitive functionality. The basis of our approach is the use of the functional kernel which consistently generates the intellectual functions of an autonomous agent. We consider a cognitive architecture which ensures the evolution of the agent on the basis of Symbol Emergence Problem solution. Evolution of cognitive abilities of the agent is described on the basis of the theory of constructivism.