Cargando…

Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners

Robot navigation is a fundamental problem in robotics and various approaches have been developed to cope with this problem. Despite the great success of previous approaches, learning-based methods are receiving growing interest in the research community. They have shown great efficiency in solving n...

Descripción completa

Detalles Bibliográficos
Autores principales: Zhou, Xiaomao, Gao, Yanbin, Guan, Lianwu
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6339171/
https://www.ncbi.nlm.nih.gov/pubmed/30621314
http://dx.doi.org/10.3390/s19010176
_version_ 1783388576838320128
author Zhou, Xiaomao
Gao, Yanbin
Guan, Lianwu
author_facet Zhou, Xiaomao
Gao, Yanbin
Guan, Lianwu
author_sort Zhou, Xiaomao
collection PubMed
description Robot navigation is a fundamental problem in robotics and various approaches have been developed to cope with this problem. Despite the great success of previous approaches, learning-based methods are receiving growing interest in the research community. They have shown great efficiency in solving navigation tasks and offer considerable promise to build intelligent navigation systems. This paper presents a goal-directed robot navigation system that integrates global planning based on goal-directed end-to-end learning and local planning based on reinforcement learning (RL). The proposed system aims to navigate the robot to desired goal positions while also being adaptive to changes in the environment. The global planner is trained to imitate an expert’s navigation between different positions by goal-directed end-to-end learning, where both the goal representations and local observations are incorporated to generate actions. However, it is trained in a supervised fashion and is weak in dealing with changes in the environment. To solve this problem, a local planner based on deep reinforcement learning (DRL) is designed. The local planner is first implemented in a simulator and then transferred to the real world. It works complementarily to deal with situations that have not been met during training the global planner and is able to generalize over different situations. The experimental results on a robot platform demonstrate the effectiveness of the proposed navigation system.
format Online
Article
Text
id pubmed-6339171
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-63391712019-01-23 Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners Zhou, Xiaomao Gao, Yanbin Guan, Lianwu Sensors (Basel) Article Robot navigation is a fundamental problem in robotics and various approaches have been developed to cope with this problem. Despite the great success of previous approaches, learning-based methods are receiving growing interest in the research community. They have shown great efficiency in solving navigation tasks and offer considerable promise to build intelligent navigation systems. This paper presents a goal-directed robot navigation system that integrates global planning based on goal-directed end-to-end learning and local planning based on reinforcement learning (RL). The proposed system aims to navigate the robot to desired goal positions while also being adaptive to changes in the environment. The global planner is trained to imitate an expert’s navigation between different positions by goal-directed end-to-end learning, where both the goal representations and local observations are incorporated to generate actions. However, it is trained in a supervised fashion and is weak in dealing with changes in the environment. To solve this problem, a local planner based on deep reinforcement learning (DRL) is designed. The local planner is first implemented in a simulator and then transferred to the real world. It works complementarily to deal with situations that have not been met during training the global planner and is able to generalize over different situations. The experimental results on a robot platform demonstrate the effectiveness of the proposed navigation system. MDPI 2019-01-05 /pmc/articles/PMC6339171/ /pubmed/30621314 http://dx.doi.org/10.3390/s19010176 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Zhou, Xiaomao
Gao, Yanbin
Guan, Lianwu
Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners
title Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners
title_full Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners
title_fullStr Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners
title_full_unstemmed Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners
title_short Towards Goal-Directed Navigation Through Combining Learning Based Global and Local Planners
title_sort towards goal-directed navigation through combining learning based global and local planners
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6339171/
https://www.ncbi.nlm.nih.gov/pubmed/30621314
http://dx.doi.org/10.3390/s19010176
work_keys_str_mv AT zhouxiaomao towardsgoaldirectednavigationthroughcombininglearningbasedglobalandlocalplanners
AT gaoyanbin towardsgoaldirectednavigationthroughcombininglearningbasedglobalandlocalplanners
AT guanlianwu towardsgoaldirectednavigationthroughcombininglearningbasedglobalandlocalplanners