By Topic

An analysis of neural models for walking control

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$33 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
R. Reeve ; Sch. of Informatics, Univ. of Edinburgh, UK ; J. Hallam

A large space of different neural models exists from simple mathematical abstractions to detailed biophysical representations with strongly differing levels of complexity and biological relevance. Previous comparisons between models have looked at biological realism or mathematical tractability rather than expressive power. This paper, however, investigates whether more sophisticated models are better suited to a complex sensorimotor control task than simpler ones, or whether the more general nature of groups of the simpler neurons allows them to collectively solve complex tasks better despite their individual simplicity. Many models have been proposed or used for sensorimotor control tasks such as the control of locomotion. Four such neural models with varying levels of complexity were chosen. Controllers made of networks of each neural type were evolved to generate locomotion in a simulated dynamically stable four-legged robot using a genetic algorithm. The problem domain was chosen as one for which no simple solution could be hand crafted and which, with its tight sensorimotor coupling, had strongly time-dependent properties as is common in many biological control tasks. Analysis of the results shows that the most complex and biologically based model is significantly better at walking control, even producing recognizable gaits.

Published in:

IEEE Transactions on Neural Networks  (Volume:16 ,  Issue: 3 )