动态环境下基于SVR-PSO的多机器人气味源定位方法  

Method of multi-robot odor source localization based on SVR-PSO in dynamic environments

作　　者：张建化[1,2] 巩敦卫[1] 张勇[1] 

机构地区：[1]中国矿业大学信息与电气工程学院,江苏徐州221008 [2]徐州工程学院机电学院,江苏徐州221111

出　　处：《中国科技论文》2014年第1期122-129,共8页China Sciencepaper

基　　金：高等学校博士学科点专项科研基金资助项目(20100095110006;20100095120016);国家自然科学基金资助项目(61005089);江苏省博士后科研资助计划(1301009B)

摘　　要：研究具有风速变化的动态环境下气味源定位问题,提出一种基于支持向量回归和微粒群优化的多机器人气味源定位方法。以当前时刻机器人的位置为输入,以机器人所测的气味浓度值为输出,利用支持向量回归,建立机器人所在位置气味浓度的预测模型;采用改进微粒群优化方法定位气味源时,以气味浓度最大的机器人所在的观测窗内,基于预测模型得到的气味浓度最大值的所在位置作为微粒的全局极值,以当前机器人的位置作为微粒的个体极值,完成微粒的更新;根据机器人所测的气味浓度值,定位气味源。将所提方法应用于2个气味源定位场景,实验结果表明所提方法能够在短时间内成功定位气味源。Aiming at the problem of odor source localization in dynamic environments with changing wind,a method of localizing odor source using multiple robots based on particle swarm optimization and support vector regression is proposed.In this method, a model predicting concentration of an odor at a location based on support vector regression is developed,which takes a robot’s current position as its input,and the corresponding concentration value measured by the robot as its output.Then,an improved particle swarm optimization is used to localize odor source,and the position corresponding to the maximal concentration value ob-tained by the prediction model is taken as the particle’s global optimum in the observation window of the robot with the maximal concentration value.In addition,the current position of a robot is taken as the particle’s local optimum.The velocity and position of a particle is updated based on the above global and local optima.Finally,the position of an odor source is localized based on the concentration value measured by a robot.The proposed method is applied to localize odor sources in two scenarios,and the exper-imental results confirm that the proposed method can successfully localize odor source in a short time.

关 键 词：气味源定位 动态环境 多机器人 支持向量回归 微粒群优化 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]