Diverse, complex, and adaptive animal behaviors are achieved by organizing
hierarchically structured controllers in motor systems. The levels
of control progress from simple spinal reflexes and central pattern
generators through to executive cognitive control in the frontal
cortex. Various types of hierarchical control structures have been
introduced and shown to be effective in past artificial agent models,
but few studies have shown how such structures can self-organize.
This study describes how such hierarchical control may evolve in
a simple recurrent neural network model implemented in a mobile robot.
Topological constraints on information flow are found to improve
system performance by decreasing interference between different parts
of the network. One part becomes responsible for generating lower
behavior primitives while another part evolves top-down sequencing
of the primitives for achieving global goals. Fast and slow neuronal
response dynamics are automatically generated in specific neurons
of the lower and the higher levels, respectively. A hierarchical
neural network is shown to outperform a comparable single-level network
in controlling a mobile robot.
%0 Journal Article
%1 Paine:2005
%A Paine, R. W.
%A Tani, J.
%D 2005
%J Adaptive Behavior
%K Algorithm, Evolutionary Genetic Hierarchy, Initial Network, Neural Robotics Self-organization, Sensitivity,
%P 211-225
%T How Hierarchical Control Self-organizes in Artificial Adaptive Systems
%V 13,
%X Diverse, complex, and adaptive animal behaviors are achieved by organizing
hierarchically structured controllers in motor systems. The levels
of control progress from simple spinal reflexes and central pattern
generators through to executive cognitive control in the frontal
cortex. Various types of hierarchical control structures have been
introduced and shown to be effective in past artificial agent models,
but few studies have shown how such structures can self-organize.
This study describes how such hierarchical control may evolve in
a simple recurrent neural network model implemented in a mobile robot.
Topological constraints on information flow are found to improve
system performance by decreasing interference between different parts
of the network. One part becomes responsible for generating lower
behavior primitives while another part evolves top-down sequencing
of the primitives for achieving global goals. Fast and slow neuronal
response dynamics are automatically generated in specific neurons
of the lower and the higher levels, respectively. A hierarchical
neural network is shown to outperform a comparable single-level network
in controlling a mobile robot.
@article{Paine:2005,
abstract = {Diverse, complex, and adaptive animal behaviors are achieved by organizing
hierarchically structured controllers in motor systems. The levels
of control progress from simple spinal reflexes and central pattern
generators through to executive cognitive control in the frontal
cortex. Various types of hierarchical control structures have been
introduced and shown to be effective in past artificial agent models,
but few studies have shown how such structures can self-organize.
This study describes how such hierarchical control may evolve in
a simple recurrent neural network model implemented in a mobile robot.
Topological constraints on information flow are found to improve
system performance by decreasing interference between different parts
of the network. One part becomes responsible for generating lower
behavior primitives while another part evolves top-down sequencing
of the primitives for achieving global goals. Fast and slow neuronal
response dynamics are automatically generated in specific neurons
of the lower and the higher levels, respectively. A hierarchical
neural network is shown to outperform a comparable single-level network
in controlling a mobile robot.},
added-at = {2009-06-26T15:25:19.000+0200},
author = {Paine, R. W. and Tani, J.},
biburl = {https://www.bibsonomy.org/bibtex/273d1a1ce06e03ceceaa876e7007e3570/butz},
description = {diverse cognitive systems bib},
interhash = {e93c99cb0352cdc3d75ddd3120acc714},
intrahash = {73d1a1ce06e03ceceaa876e7007e3570},
journal = {Adaptive Behavior},
keywords = {Algorithm, Evolutionary Genetic Hierarchy, Initial Network, Neural Robotics Self-organization, Sensitivity,},
owner = {butz},
pages = {211-225},
timestamp = {2009-06-26T15:25:49.000+0200},
title = {How Hierarchical Control Self-organizes in Artificial Adaptive Systems},
volume = {13,},
year = 2005
}