NEURAL ROBOT PATH PLANNING - THE MAZE PROBLEM

Authors
DRACOPOULOS DC
Citation
Dc. Dracopoulos, NEURAL ROBOT PATH PLANNING - THE MAZE PROBLEM, NEURAL COMPUTING & APPLICATIONS, 7(2), 1998, pp. 115-120
Citations number
8
Categorie Soggetti
Computer Science Artificial Intelligence","Computer Science Artificial Intelligence
Journal title
NEURAL COMPUTING & APPLICATIONS → ACNP
ISSN journal
09410643
Volume
7
Issue
2
Year of publication
1998
Pages
115 - 120
Database
ISI
SICI code
0941-0643(1998)7:2<115:NRPP-T>2.0.ZU;2-T
Abstract
The importance of path planning is very significant in the field of ro botics. This paper presents the application of multilayer perceptrons to the robot path planning problem, and in particular to the task of m aze navigation. Previous published results implied that the training o f feedforward multilayered networks failed, because of the non-smoothn ess of data. Here the path planning problem is reconsidered, and it is shown that multilayer perceptrons are able to learn the task successf ully.