%0 Journal Article
%T 基于雷达信息的室内移动机器人的方位估计<br>Orientation estimate of indoor mobile robot using laser scans
%A 刘华平
%A 郑向梅
%A 孙富春
%J 清华大学学报（自然科学版）
%D 2018
%R 10.16511/j.cnki.qhdxxb.2018.25.031
%X 移动机器人的室内定位是机器人领域中的一个热点问题，移动机器人的定位包括位置与方位两方面。为对移动机器人方位进行有效的估计，该文提出了基于支持向量机（support vector machine，SVM）的机器人方位回归模型，选定激光雷达信息作为模型的输入量、机器人的方位作为输出量；并与基于极限学习机（extreme learning machine，ELM）的机器人方位回归模型进行对比。实验结果表明：基于极限学习机回归模型的均方误差为0.320 rad，训练时间为0.936 s；基于支持向量回归模型的均方误差为0.113 rad，训练时间为9 273 s。该回归模型可为机器人方位估计提供一定的应用价值。<br>Abstract：The positioning of mobile robots indoors is very important with the controller needed to know both the location and the orientation. This paper presents a robot orientation regression model based on a support vector machine (SVM) to estimate the robot orientation. A laser radar signal is used as the model input with the orientation as the output. Tests show that the mean square error using an extreme learning machine model is 0.320 rad with a training time of 0.936 s while the mean square error based on the current support vector regression model is 0.113 rad with a training time of 9 273 s. Thus, the regression models can provide accurate robot position estimates.
%K 支持向量回归
%K 方向估计
%K 移动机器人
%K &lt
%K br&gt
%K support vector regression
%K orientation estimation
%K mobile robot
%U http://jst.tsinghuajournals.com/CN/Y2018/V58/I7/609