Design of evolvable hardware for robotic navigation

TP301.6; This paper presents an integrated on-line learning system toevolve programmabl e logic array (PLA) controllers for navigating an autonomous robot in a two-dime n sional environment. The integrated on-line learning system consists of two lear n ing modules: one is the module of reinforcement...

Full description

Saved in:
Bibliographic Details
Published in:Wuhan University journal of natural sciences 2001-03, Vol.6 (1-2), p.547-554
Main Authors: Liu, Yong, Higuchi, Tetsuya, Iwata, Masaya
Format: Article
Language:English
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:TP301.6; This paper presents an integrated on-line learning system toevolve programmabl e logic array (PLA) controllers for navigating an autonomous robot in a two-dime n sional environment. The integrated on-line learning system consists of two lear n ing modules: one is the module of reinforcement learning based on temporal-diff e rence learning based on genetic algorithms, and the other is the module of evolu tionary learning based on genetic algorithms. The control rules extracted from t he module of reinforcement learning can be used as input to the module of evolut ionary learning, and quickly implemented by the PLA through on-line evolution. T he on-line evolution has shown promise as a method of learning systems in compl e x environment. The evolved PLA controllers can successfully navigate the robot t o a target in the two-dimensional environment while avoiding collisions with ra ndomly positioned obstacles.
ISSN:1007-1202
1993-4998
DOI:10.1007/BF03160300