| Multi-path planning algorithm based on fitness sharing and species evolution |
| |
| 作者姓名： | ZHANGJing-juan LIXue-lian HAOYan-ling |
| |
| 作者单位： | CollegeofAutomation,HarbinEngineeringUniversity,Harbin150001,China |
| |
| 摘 要： | A new algorithm is proposed for underwater vehicles multi-path planning. This algorithm is based on fitness sharing genetic algorithm, clustering and evolution of multiple populations, which can keep the diversity of the solution path, and decrease the operating time because of the independent evolution of each subpopulation. The multi-path planning algorithm is demonstrated by a number of two-dimensional path planning problems. The results show that the multi-path planning algorithm has the following characteristics: high searching capability, rapid convergence and high reliability.
|
| 关 键 词： | 多路径 运算法则 计划编制 遗传算法 水下交通工具 |
Multi-path planning algorithm based on fitness sharing and species evolution |
| |
| ZHANGJing-juan LIXue-lian HAOYan-ling.Multi-path planning algorithm based on fitness sharing and species evolution[J].Journal of Marine Science and Application,2003,2(1):60-65. |
| |
| Authors: | Zhang Jing-juan Li Xue-lian Hao Yan-ling |
| |
| Institution: | (1) College of Automation, Harbin Engineering University, 150001 Harbin, China |
| |
| Abstract: | A new algorithm is proposed for underwater vehicles multi-path planning. This algorithm is based on fitness sharing genetic algorithm, clustering and evolution of multiple populations, which can keep the diversity of the solution path, and decrease the operating time because of the independent evolution of each subpopulation. The multi-path planning algorithm is demonstrated by a number of two-dimensional path planning problems. The results show that the multi-path planning algorithm has the following characteristics: high searching capability, rapid convergence and high reliability. |
| |
| Keywords: | genetic algorithm subpopulation evolution fitness sharing multi-path planning |
| 本文献已被 CNKI 维普 万方数据 SpringerLink 等数据库收录！ |
