基于激光雷达的舞蹈机器人室内行人跟踪方法  

Indoor Pedestrian Tracking Method of Dancing Robot Based on Laser Radar

作　　者：刘召 宋立滨[1,2] 耿美晓 于涛 王增喜 郭凯 

机构地区：[1]清研华宇智能机器人(天津)有限责任公司,天津300304 [2]清华大学机械工程系,北京100084

出　　处：《计算机工程》2017年第6期247-252,258,共7页Computer Engineering

基　　金：国家自然科学基金(51005126)

摘　　要：为使舞蹈机器人根据行人的运动轨迹进行路径的动态规划,增强与人共处的能力,提出一种基于激光雷达的室内行人跟踪方法。获取激光原始数据并进行预处理,根据激光数据的分布特点对DBSCAN算法进行优化,实现激光数据的快速聚类,完成环境分割,给出基于类簇到激光雷达的距离及行人身体宽度的行人识别方法,并将行人簇的位置作为初始跟踪位置,将激光数据图形化显示,激光数据转换成视频数据,利用粒子滤波算法实现行人跟踪并实时绘制轨迹。实验结果表明,该方法能获得较好的行人识别以及跟踪效果,且实时性较强。To make the dancing robot plan a dynamic path based getting along with people, an indoor pedestrian tracking method on the motion of pedestrians and enhance its ability of based on laser radar is proposed. The source data collected by the laser is gotten and preprocessed. According to the distribution characteristics of laser data, the DBSCAN algorithm is optimized to cluster the data rapidly to realize the segmentation of the environmental information. A pedestrian recognition method is proposed based on the distance from cluster to laser radar and the pedestrian width. The position of the pedestrian cluster is used as the initial tracking position. The laser data is displayed graphically and converted into video data. The particle filtering algorithm is applied to track the pedestrian, and the trajectory is drawn at the same time. Experimental results show that the proposed method has good effect on pedestrian recognition and tracking. It also has a good real-time performance.

关 键 词：激光雷达 舞蹈机器人 DBSCAN算法 行人识别 粒子滤波 行人跟踪 

分 类 号：TP242.6[自动化与计算机技术—检测技术与自动化装置]