基于激光雷达的移动机器人运动目标检测与跟踪

运动目标的检测与跟踪是移动机器人研究的难点问题之一.基于2维激光雷达的性能分析与滤波设计的基础上,提出一种自主运动目标检测与跟踪的方法.通过k-近邻对激光雷达扫描的障碍进行聚类分析;基于栅格地图匹配的方法评估障碍的运动参数;检测出运动目标后,通过对机器人进行运动补偿,提出一种改进的粒子滤波算法对目标的运动状态进行评估.最后,利用自行研制的移动机器人进行算法评估,实验结果验证了所提方法的有效性.

Detection and Tracking of Moving Object with a Mobile Robot Using Laser Scanner

Detection and tracking of moving object is a difficult problem in mobile robot research. On the basis of the performance analysis and filter design with a 2D laser scanner, an autonomous approach for detection and tracking of moving object is presented. The k-nearest neighbor method is adopted to realize the spatial clustering of obstacles according to the ranging data of laser scanner. Then, the movement parameter of clustering obstacles is computed by grid map matching. After obtaining the moving object, an improved particle filter is used for mobile robot to estimate the movement condition of object with the movement compensation of mobile robot. At last, experiments with the mobile robot designed by us are implemented and the validity of this approach is verified.