A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization

To overcome the limitations of particle swarm optimization (PSO) in mobile robot path planning, including issues such as premature convergence and sensitivity to local optima, this study proposes a novel approach, dynamic multipopulation particle swarm optimization (DMPSO). First, the multipopulatio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunjie Zhang, Ning Li, Yadong Chen, Zhenjian Yang, Yue Liu
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Journal of Robotics
Online Access:http://dx.doi.org/10.1155/joro/5018491
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850059734456991744
author Yunjie Zhang
Ning Li
Yadong Chen
Zhenjian Yang
Yue Liu
author_facet Yunjie Zhang
Ning Li
Yadong Chen
Zhenjian Yang
Yue Liu
author_sort Yunjie Zhang
collection DOAJ
description To overcome the limitations of particle swarm optimization (PSO) in mobile robot path planning, including issues such as premature convergence and sensitivity to local optima, this study proposes a novel approach, dynamic multipopulation particle swarm optimization (DMPSO). First, the multipopulation particle swarm optimization (MPSO) framework is extended by introducing a dynamic multipopulation strategy that adjusts the number of subpopulations in real-time. This strategy is designed to enhance the algorithm’s local search capabilities and accelerate its convergence. Second, the inertia weights and learning factors within the algorithm are refined to achieve a balance between global exploration and local exploitation. Furthermore, an initialization strategy based on fitness variance is developed to improve population diversity, mitigate premature convergence, and enhance the algorithm’s ability to locate global optima. Lastly, a positive feedback acceleration factor is introduced to optimize particle positions, thereby improving local search capabilities and accelerating convergence. Simulation experiments have validated that DMPSO offers improved exploration capabilities, enhanced search precision, and a more rapid convergence rate. In comparison to PSO, DMPSO reduces the path length by 3% and decreases the number of convergence iterations by 17%.
format Article
id doaj-art-ca26aa80245a4962926457940ea8d922
institution DOAJ
issn 1687-9619
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Journal of Robotics
spelling doaj-art-ca26aa80245a4962926457940ea8d9222025-08-20T02:50:48ZengWileyJournal of Robotics1687-96192024-01-01202410.1155/joro/5018491A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm OptimizationYunjie Zhang0Ning Li1Yadong Chen2Zhenjian Yang3Yue Liu4School of Computer and Information EngineeringSchool of Information and Electromechanical EngineeringSchool of Computer and Information EngineeringSchool of Computer and Information EngineeringSchool of Computer and Information EngineeringTo overcome the limitations of particle swarm optimization (PSO) in mobile robot path planning, including issues such as premature convergence and sensitivity to local optima, this study proposes a novel approach, dynamic multipopulation particle swarm optimization (DMPSO). First, the multipopulation particle swarm optimization (MPSO) framework is extended by introducing a dynamic multipopulation strategy that adjusts the number of subpopulations in real-time. This strategy is designed to enhance the algorithm’s local search capabilities and accelerate its convergence. Second, the inertia weights and learning factors within the algorithm are refined to achieve a balance between global exploration and local exploitation. Furthermore, an initialization strategy based on fitness variance is developed to improve population diversity, mitigate premature convergence, and enhance the algorithm’s ability to locate global optima. Lastly, a positive feedback acceleration factor is introduced to optimize particle positions, thereby improving local search capabilities and accelerating convergence. Simulation experiments have validated that DMPSO offers improved exploration capabilities, enhanced search precision, and a more rapid convergence rate. In comparison to PSO, DMPSO reduces the path length by 3% and decreases the number of convergence iterations by 17%.http://dx.doi.org/10.1155/joro/5018491
spellingShingle Yunjie Zhang
Ning Li
Yadong Chen
Zhenjian Yang
Yue Liu
A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization
Journal of Robotics
title A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization
title_full A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization
title_fullStr A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization
title_full_unstemmed A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization
title_short A Mobile Robot Path Planning Method Based on Dynamic Multipopulation Particle Swarm Optimization
title_sort mobile robot path planning method based on dynamic multipopulation particle swarm optimization
url http://dx.doi.org/10.1155/joro/5018491
work_keys_str_mv AT yunjiezhang amobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT ningli amobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT yadongchen amobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT zhenjianyang amobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT yueliu amobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT yunjiezhang mobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT ningli mobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT yadongchen mobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT zhenjianyang mobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization
AT yueliu mobilerobotpathplanningmethodbasedondynamicmultipopulationparticleswarmoptimization