Automatic Navigation of Mobile Robots in Unknown Environments

Online navigation with known target and unknown obstacles is an interesting problem in mobile robotics. This article presents a technique based on utilization of neural networks and reinforcement learning to enable a mobile robot to learn constructed environments on its own. The robot learns to gene...

Full description

Saved in:
Bibliographic Details
Main Authors: motlagh, o, nakhaeinia, n, tang, s.h.
Format: Article
Language:en
Published: 2013
Subjects:
Online Access:http://eprints.utem.edu.my/id/eprint/7577/1/nca.pdf
http://eprints.utem.edu.my/id/eprint/7577/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832716269988610048
author motlagh, o
nakhaeinia, n
tang, s.h.
author_facet motlagh, o
nakhaeinia, n
tang, s.h.
author_sort motlagh, o
building UTEM Library
collection Institutional Repository
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
continent Asia
country Malaysia
description Online navigation with known target and unknown obstacles is an interesting problem in mobile robotics. This article presents a technique based on utilization of neural networks and reinforcement learning to enable a mobile robot to learn constructed environments on its own. The robot learns to generate efficient navigation rules automatically without initial settings of rules by experts. This is regarded as the main contribution of this work compared to traditional fuzzy models based on notion of artificial potential fields. The ability for generalization of rules has also been examined. The initial results qualitatively confirmed the efficiency of the model. More experiments showed at least 32% of improvement in path panning from the first till the third path planning trial in a sample environment. Analysis of the results, limitations and recommendations are included for future work.
format Article
id my.utem.eprints-7577
institution Universiti Teknikal Malaysia Melaka
language en
publishDate 2013
record_format eprints
spelling my.utem.eprints-75772015-05-28T03:50:28Z http://eprints.utem.edu.my/id/eprint/7577/ Automatic Navigation of Mobile Robots in Unknown Environments motlagh, o nakhaeinia, n tang, s.h. QA75 Electronic computers. Computer science Online navigation with known target and unknown obstacles is an interesting problem in mobile robotics. This article presents a technique based on utilization of neural networks and reinforcement learning to enable a mobile robot to learn constructed environments on its own. The robot learns to generate efficient navigation rules automatically without initial settings of rules by experts. This is regarded as the main contribution of this work compared to traditional fuzzy models based on notion of artificial potential fields. The ability for generalization of rules has also been examined. The initial results qualitatively confirmed the efficiency of the model. More experiments showed at least 32% of improvement in path panning from the first till the third path planning trial in a sample environment. Analysis of the results, limitations and recommendations are included for future work. 2013 Article PeerReviewed application/pdf en http://eprints.utem.edu.my/id/eprint/7577/1/nca.pdf motlagh, o and nakhaeinia, n and tang, s.h. (2013) Automatic Navigation of Mobile Robots in Unknown Environments. Neural Computing and Applications. xxxx-xxxx. ISSN xxxx-xxxx
spellingShingle QA75 Electronic computers. Computer science
motlagh, o
nakhaeinia, n
tang, s.h.
Automatic Navigation of Mobile Robots in Unknown Environments
title Automatic Navigation of Mobile Robots in Unknown Environments
title_full Automatic Navigation of Mobile Robots in Unknown Environments
title_fullStr Automatic Navigation of Mobile Robots in Unknown Environments
title_full_unstemmed Automatic Navigation of Mobile Robots in Unknown Environments
title_short Automatic Navigation of Mobile Robots in Unknown Environments
title_sort automatic navigation of mobile robots in unknown environments
topic QA75 Electronic computers. Computer science
url http://eprints.utem.edu.my/id/eprint/7577/1/nca.pdf
http://eprints.utem.edu.my/id/eprint/7577/
url_provider http://eprints.utem.edu.my/