计算机与现代化 ›› 2012, Vol. 1 ›› Issue (11): 43-46.doi: 10.3969/j.issn.1006-2475.2012.11.012

• 人工智能 • 上一篇    下一篇

三种基于偏好的区间多目标进化算法及应用

殷昭宁1,孙 靖2   

  1. 1.连云港润众制药有限公司,江苏 连云港 222069;2.淮海工学院理学院,江苏 连云港 222005
  • 收稿日期:2012-07-23 修回日期:1900-01-01 出版日期:2012-11-10 发布日期:2012-11-10

Three Preference-based Interval Multi-objective Evolutionary Algorithms and Their Application

YIN Zhao-ning1, SUN Jing2   

  1. 1. Lianyungang Runzhong Pharmaceutical Co., Ltd., Lianyungang 222069, China;2. School of Science, Huaihai Institute of Technology, Lianyungang 222005, China
  • Received:2012-07-23 Revised:1900-01-01 Online:2012-11-10 Published:2012-11-10

摘要: 区间参数多目标优化问题是普遍存在且非常重要的。目前直接求解该类问题的进化优化方法非常少,且已有方法的目的是找到收敛性好且分布均匀的Pareto最优解集。为得到符合决策者偏好的最满意解,本文综述3种基于偏好的区间多目标进化算法,并将其应用于特定环境下机器人路径规划问题,比较3种算法的性能。研究结果可丰富特定环境下机器人路径规划的求解方法,提高机器人路径优化效果。

关键词: 进化算法, 多目标优化, 区间, 偏好, 机器人, 路径规划

Abstract: Interval multi-objective optimization problems are very popular and important. There exist few evolutionary optimization methods for directly solving them, and these existing methods aim at finding a set of well-converged and evenly-distributed Pareto-optimal solutions. Three preference-based interval multi-objective evolutionary algorithms are surveyed to obtain the most preferred solution fitted the decision maker’s preferences. Additionally, the above algorithms are applied in robot path planning problems under a special environment, and are compared about their performance. The research enriches the methods of solving robot path planning problems under a special environment, and improves the optimization performance of the problems.

Key words: evolutionary algorithm, multi-objective optimization, interval, preference, robot, path planning

中图分类号: