Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control

A biologically inspired mechanism for robot action selection, based on the vertebrate basal ganglia, has been previously presented (Prescott et al. 2006, Montes Gonzalez et al. 2000). In this model the task confronting the robot is decomposed into distinct behavioural modules that integrate informat...

Full description

Saved in:
Bibliographic Details
Main Authors: F. Montes-Gonzalez, T. J. Prescott, J. Negrete-Martinez
Format: Article
Language:English
Published: Wiley 2007-01-01
Series:Applied Bionics and Biomechanics
Online Access:http://dx.doi.org/10.1080/11762320701492792
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850169893246205952
author F. Montes-Gonzalez
T. J. Prescott
J. Negrete-Martinez
author_facet F. Montes-Gonzalez
T. J. Prescott
J. Negrete-Martinez
author_sort F. Montes-Gonzalez
collection DOAJ
description A biologically inspired mechanism for robot action selection, based on the vertebrate basal ganglia, has been previously presented (Prescott et al. 2006, Montes Gonzalez et al. 2000). In this model the task confronting the robot is decomposed into distinct behavioural modules that integrate information from multiple sensors and internal state to form ‘salience’ signals. These signals are provided as inputs to a computational model of the basal ganglia whose intrinsic processes cause the selection by disinhibition of a winning behaviour. This winner is then allowed access to the motor plant whilst losing behaviours are suppressed. In previous research we have focused on the development of this biomimetic selection architecture, and have therefore used behavioural modules that were hand-coded as algorithmic procedures. In the current article, we demonstrate the use of genetic algorithms and gradient–descent learning to automatically generate/tune some of the modules that generate the model behaviour.
format Article
id doaj-art-a57602a333a74f9991ae5b51b2b3d7e9
institution OA Journals
issn 1176-2322
1754-2103
language English
publishDate 2007-01-01
publisher Wiley
record_format Article
series Applied Bionics and Biomechanics
spelling doaj-art-a57602a333a74f9991ae5b51b2b3d7e92025-08-20T02:20:37ZengWileyApplied Bionics and Biomechanics1176-23221754-21032007-01-014310110910.1080/11762320701492792Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot ControlF. Montes-Gonzalez0T. J. Prescott1J. Negrete-Martinez2Department of Artificial Intelligence, Universidad Veracruzana, Sebastian Camacho 5, Xalapa, Veracruz, MexicoDepartment of Psychology, University of Sheffield, Western Bank, Sheffield S10 2TN, UKDepartment of Artificial Intelligence, Universidad Veracruzana, Sebastian Camacho 5, Xalapa, Veracruz, MexicoA biologically inspired mechanism for robot action selection, based on the vertebrate basal ganglia, has been previously presented (Prescott et al. 2006, Montes Gonzalez et al. 2000). In this model the task confronting the robot is decomposed into distinct behavioural modules that integrate information from multiple sensors and internal state to form ‘salience’ signals. These signals are provided as inputs to a computational model of the basal ganglia whose intrinsic processes cause the selection by disinhibition of a winning behaviour. This winner is then allowed access to the motor plant whilst losing behaviours are suppressed. In previous research we have focused on the development of this biomimetic selection architecture, and have therefore used behavioural modules that were hand-coded as algorithmic procedures. In the current article, we demonstrate the use of genetic algorithms and gradient–descent learning to automatically generate/tune some of the modules that generate the model behaviour.http://dx.doi.org/10.1080/11762320701492792
spellingShingle F. Montes-Gonzalez
T. J. Prescott
J. Negrete-Martinez
Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control
Applied Bionics and Biomechanics
title Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control
title_full Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control
title_fullStr Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control
title_full_unstemmed Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control
title_short Minimizing Human Intervention in the Development of Basal Ganglia-Inspired Robot Control
title_sort minimizing human intervention in the development of basal ganglia inspired robot control
url http://dx.doi.org/10.1080/11762320701492792
work_keys_str_mv AT fmontesgonzalez minimizinghumaninterventioninthedevelopmentofbasalgangliainspiredrobotcontrol
AT tjprescott minimizinghumaninterventioninthedevelopmentofbasalgangliainspiredrobotcontrol
AT jnegretemartinez minimizinghumaninterventioninthedevelopmentofbasalgangliainspiredrobotcontrol