计算机应用 ›› 2015, Vol. 35 ›› Issue (10): 2828-2832.DOI: 10.11772/j.issn.1001-9081.2015.10.2828

• 第十五届中国机器学习会议(CCML2015)论文 • 上一篇    下一篇

不确定生命强度的微粒群救援路径规划求解

耿娜, 巩敦卫, 张勇   

  1. 中国矿业大学 信息与电气工程学院, 江苏 徐州 221008
  • 收稿日期:2015-06-01 修回日期:2015-06-18 出版日期:2015-10-10 发布日期:2015-10-14
  • 通讯作者: 耿娜(1985-),女,江苏徐州人,博士研究生,主要研究方向:微粒群优化算法,gengna@126.com
  • 作者简介:巩敦卫(1970-),男,江苏徐州人,教授,博士生导师,博士,CCF会员,主要研究方向:智能优化与控制、基于搜索的软件工程;张勇(1979-),男,山东莱芜人,副教授,博士,CCF会员,主要研究方向:群体智能、数据挖掘
  • 基金资助:
    中国博士后科学基金资助项目(2014T70557);江苏省博士后科研资助计划项目(1301009B);江苏普通高校研究生科研创新计划项目(CXZZ12-0931)。

Uncertain life strength rescue path planning based on particle swarm optimization

GENG Na, GONG Dunwei, ZHANG Yong   

  1. School of Information and Electrical Engineering, China University of Mining and Technology, Xuzhou Jiangsu 221008, China
  • Received:2015-06-01 Revised:2015-06-18 Online:2015-10-10 Published:2015-10-14

摘要: 针对灾难发生后,如何在有限的时间内救援最多被困者的问题,研究灾难发生后,由机器人代替救援人员,在被困人员生命强度不确定的情况下,规划救援路径,以期在有限的时间内救援最多的被困人员(目标点)。首先,考虑到灾难发生之前,每个目标点都有生命强度,且每个人由于不同因素的影响,生命强度的大小不同,不失一般性,将其设为一个区间;然后,考虑生命强度约束,救援人数作为目标函数,将其建立为一个与生命强度有关的区间函数;接着,采用改进的整数微粒群算法对上述目标函数进行求解,介绍了微粒的编码、解码方法和全局极值更新策略;最后,通过对不同场景下的仿真,验证所提算法的有效性。

关键词: 机器人, 灾难救援, 微粒群, 生命强度

Abstract: In order to solve the problem of rescuing the maximum number of trapped men in limited time after disaster, the robots were used to take place of rescue workers to rescue the survivors after disaster, and the robots rescue path planning method was studied by considering the situation that the trapped men's life strengths were uncertain. Firstly, considering that each target has life strength and the values of life strengths were different due to different factors, the value of life strength was set as interval number in general. Secondly, taking life strength constraint into account, the rescued worker number was treated as the objective function, which is an interval function related to life strength. Then the modified Particle Swarm Optimization (PSO) algorithm was used to solve the established objective function, the particle's code and decode method and the global best solution update strategy were introduced. Finally, the effectiveness of the proposed method was verified by simulations of different scenarios.

Key words: robot, disaster rescue, Particle Swarm Optimization (PSO), life strength

中图分类号: