一种适用于移动机器人的障碍物快速检测算法及其实现  

A Fast Obstacle Detection Algorithm for Mobile Robots and Its Application

作　　者：赵小川[1,2] 刘培志[1,2] 张敏 杨立辉 施建昌 

机构地区：[1]中国兵器工业计算机应用技术研究所,北京100089 [2]北京理工大学,北京100081 [3]总装工程兵科研二所,北京100093

出　　处：《机器人》2011年第2期198-201,214,共5页Robot

基　　金：国家部委预研基金资助项目(6140528).

摘　　要：针对传统的用于机器人检测障碍物的算法存在的不足,提出了一种基于视觉传感器与超声波传感器信息融合的快速障碍物检测算法.该算法通过位于机器人头部的超声波传感器获取机器人到障碍物(本算法采用矩形障碍物)的距离信息,通过改进型快速直线检测方法和约束条件确定障碍物在视觉传感器所采集的图像中的直线边缘,根据成像过程中三角形相似的原理,融合障碍物的距离信息和图像中障碍物的边缘信息,从而得到矩形障碍物的实际高度和宽度,为机器人遇到障碍物时进行局部路径规划提供决策依据.以六足移动机器人为实验平台,验证了所提出的障碍物检测算法的有效性和实用性.In order to overcome the shortcomings of traditional obstacle detection algorithms,a fast obstacle detection algorithm for mobile robots based on the vision sensor and ultrasonic sensor information fusion is proposed.The distance between the robot and the obstacle（the obstacle employed in this algorithm is rectangular） is obtained by the ultrasonic sensor located on the head of the robot.An improved fast line detection method and restriction terms are proposed to extract the straight line edge of the obstacle in the image（obtained by the vision sensor）.According to the mechanism of the triangle similarity in process of imaging,the real height and width of the obstacle is calculated by fusing the distance and the height and width of the obstacle in the image,which supports the local path planning decision.The validity and practicability of the obstacle detection algorithm is tested by the experiments conducted on the hexapod robot.

关 键 词：机器人 模式识别 信息处理 障碍物检测 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]