标题:On Global Smooth Path Planning for Mobile Robots using a Novel Multimodal Delayed PSO Algorithm
作者:Song, Baoye; Wang, Zidong; Zou, Lei
作者机构:[Song, Baoye; Wang, Zidong; Zou, Lei] Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China.; [Wang, Zidong] Brune 更多
通讯作者:Wang, Zidong
通讯作者地址:[Wang, ZD]Shandong Univ Sci & Technol, Coll Elect Engn & Automat, Qingdao 266590, Peoples R China;[Wang, ZD]Brunel Univ London, Dept Comp Sci, Uxbridg 更多
来源:COGNITIVE COMPUTATION
出版年:2017
卷:9
期:1
页码:5-17
DOI:10.1007/s12559-016-9442-4
关键词:Particle swarm optimization; Mobile robot; Multimodal delayed; information; Smooth path planning; Bezier curve
摘要:The planning problem for smooth paths for mobile robots has attracted particular research attention, but the strategy combining the heuristic intelligent optimization algorithm (e.g., particle swarm optimization) with smooth parameter curve (e.g., Bezier curve) for global yet smooth path planning for mobile robots has not been thoroughly discussed because of several difficulties such as the local trapping phenomenon in the searching process. In this paper, a novel multimodal delayed particle swarm optimization (MDPSO) algorithm is developed for the global smooth path planning for mobile robots. By evaluating the evolutionary factor in each iteration, the evolutionary state is classified by equal interval division for the swarm of the particles. Then, the velocity updating model would switch from one mode to another according to the evolutionary state. Furthermore, in order to reduce the occurrence of local trapping phenomenon and expand the search space in the searching process, the so-called multimodal delayed information (which is composed of the local and global delayed best particles selected randomly from the corresponding values in previous iterations) is added into the velocity updating model. A series of simulation experiments are implemented on a standard collection of benchmark functions. The experiment results verify that the comprehensive performance of the developed MDPSO algorithm is superior to other well-known PSO algorithms. Finally, the presented MDPSO algorithm is utilized in the global smooth path planning problem for mobile robots, which further confirms the advantages of the MDPSO algorithm over the traditional genetic algorithm (GA) investigated in previous studies. The multimodal delayed information in the MDPSO reduces the occurrence of local trapping phenomenon and the convergence rate is satisfied at the same time. Based on the testing results on a selection of benchmark functions, the MDPSO's performance has been shown to be superior to other five well-known PSO algorithms. Successful application of the MDPSO for planning the global smooth path for mobile robots further confirms its excellent performance compared with the some typical existing algorithms.
收录类别:EI;SCIE
WOS核心被引频次:7
资源类型:期刊论文
TOP