A Tree-Type Memory Formation by Sensorimotor Feedback: A Possible Approach to the Development of Robotic Cognition - Intelligent Control and Automation

ICA > Vol.4 No.2, May 2013

A Tree-Type Memory Formation by Sensorimotor Feedback: A Possible Approach to the Development of Robotic Cognition ()

HTML XML

Download as PDF (Size: 561KB) PP. 154-165

DOI: 10.4236/ica.2013.42020 3,599 Downloads 5,126 Views

Author(s)

Fady Alnajjar, Indra M. Zin, Abdl R. Hafiz, Kazuyuki Murase

Affiliation(s)

Brain Science Institute, RIKEN, Nagoya, Japan.
Department of Human and Artificial Intelligence Systems, Fukui, Japan.

ABSTRACT

Based on indications from neuroscience and psychology, both perception and action can be internally simulated in or- ganisms by activating sensory and/or motor areas in the brain without actual external sensory input and/or without any resulting behavior (a phenomenon called Thinking). This phenomenon is usually used by the organisms to cope with missing external inputs. Applying such phenomenon in a real robot recently has taken the attention of many researchers. Although some work has been reported on this issue, none of this work has so far considered the potential of the robot’s vision at the sensorimotor abstraction level, where extracting data from the environment takes place. In this study, a novel visiomotor abstraction is presented into a physical robot through a memory-based learning algorithm. Experi- mental results indicate that our robot with its vision could develop a kind of simple anticipation mechanism into its tree-type memory structure through interacting with the environment which would guide its behavior in the absence of external inputs.

KEYWORDS

Visiomotor Abstraction; Memory Based Learning; Artificial Cognition; Internal Representation

Share and Cite:

Alnajjar, F. , Zin, I. , Hafiz, A. and Murase, K. (2013) A Tree-Type Memory Formation by Sensorimotor Feedback: A Possible Approach to the Development of Robotic Cognition. Intelligent Control and Automation, 4, 154-165. doi: 10.4236/ica.2013.42020.

Journals Menu

Follow SCIRP

	+1 323-425-8868
	customer@scirp.org
	+86 18163351462(WhatsApp)
	1655362766

	Paper Publishing WeChat

Journals Menu

Home

About SCIRP

Service

Policies