Cargando…

Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method

This paper proposes an improved ant colony algorithm to achieve efficient searching capabilities of path planning in complicated maps for mobile robot. The improved ant colony algorithm uses the characteristics of A(*) algorithm and MAX-MIN Ant system. Firstly, the grid environment model is construc...

Descripción completa

Detalles Bibliográficos
Autores principales: Dai, Xiaolin, Long, Shuai, Zhang, Zhiwen, Gong, Dawei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6477093/
https://www.ncbi.nlm.nih.gov/pubmed/31057388
http://dx.doi.org/10.3389/fnbot.2019.00015
_version_ 1783412998297092096
author Dai, Xiaolin
Long, Shuai
Zhang, Zhiwen
Gong, Dawei
author_facet Dai, Xiaolin
Long, Shuai
Zhang, Zhiwen
Gong, Dawei
author_sort Dai, Xiaolin
collection PubMed
description This paper proposes an improved ant colony algorithm to achieve efficient searching capabilities of path planning in complicated maps for mobile robot. The improved ant colony algorithm uses the characteristics of A(*) algorithm and MAX-MIN Ant system. Firstly, the grid environment model is constructed. The evaluation function of A(*) algorithm and the bending suppression operator are introduced to improve the heuristic information of the Ant colony algorithm, which can accelerate the convergence speed and increase the smoothness of the global path. Secondly, the retraction mechanism is introduced to solve the deadlock problem. Then the MAX-MIN ant system is transformed into local diffusion pheromone and only the best solution from iteration trials can be added to pheromone update. And, strengths of the pheromone trails are effectively limited for avoiding premature convergence of search. This gives an effective improvement and high performance to ACO in complex tunnel, trough and baffle maps and gives a better result as compare to traditional versions of ACO. The simulation results show that the improved ant colony algorithm is more effective and faster.
format Online
Article
Text
id pubmed-6477093
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-64770932019-05-03 Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method Dai, Xiaolin Long, Shuai Zhang, Zhiwen Gong, Dawei Front Neurorobot Neuroscience This paper proposes an improved ant colony algorithm to achieve efficient searching capabilities of path planning in complicated maps for mobile robot. The improved ant colony algorithm uses the characteristics of A(*) algorithm and MAX-MIN Ant system. Firstly, the grid environment model is constructed. The evaluation function of A(*) algorithm and the bending suppression operator are introduced to improve the heuristic information of the Ant colony algorithm, which can accelerate the convergence speed and increase the smoothness of the global path. Secondly, the retraction mechanism is introduced to solve the deadlock problem. Then the MAX-MIN ant system is transformed into local diffusion pheromone and only the best solution from iteration trials can be added to pheromone update. And, strengths of the pheromone trails are effectively limited for avoiding premature convergence of search. This gives an effective improvement and high performance to ACO in complex tunnel, trough and baffle maps and gives a better result as compare to traditional versions of ACO. The simulation results show that the improved ant colony algorithm is more effective and faster. Frontiers Media S.A. 2019-04-16 /pmc/articles/PMC6477093/ /pubmed/31057388 http://dx.doi.org/10.3389/fnbot.2019.00015 Text en Copyright © 2019 Dai, Long, Zhang and Gong. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Neuroscience
Dai, Xiaolin
Long, Shuai
Zhang, Zhiwen
Gong, Dawei
Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method
title Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method
title_full Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method
title_fullStr Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method
title_full_unstemmed Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method
title_short Mobile Robot Path Planning Based on Ant Colony Algorithm With A(*) Heuristic Method
title_sort mobile robot path planning based on ant colony algorithm with a(*) heuristic method
topic Neuroscience
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6477093/
https://www.ncbi.nlm.nih.gov/pubmed/31057388
http://dx.doi.org/10.3389/fnbot.2019.00015
work_keys_str_mv AT daixiaolin mobilerobotpathplanningbasedonantcolonyalgorithmwithaheuristicmethod
AT longshuai mobilerobotpathplanningbasedonantcolonyalgorithmwithaheuristicmethod
AT zhangzhiwen mobilerobotpathplanningbasedonantcolonyalgorithmwithaheuristicmethod
AT gongdawei mobilerobotpathplanningbasedonantcolonyalgorithmwithaheuristicmethod