病房巡视机器人复杂环境下的避障技术研究  

Research on obstacles avoidance for ward inspection robot in complex environment

作　　者：田国会[1] 王家超[1] 段朋[1] 

机构地区：[1]山东大学控制科学与工程学院,山东济南250061

出　　处：《华中科技大学学报（自然科学版）》2013年第S1期312-315,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61075092);山东省自然科学基金资助项目(ZR2011FM011);山东大学自主创新基金资助项目(2011JC01)

摘　　要：针对医院病房巡视机器人的工作环境复杂多变、障碍物形状各异的特点,提出了一种基于视觉-激光传感器的障碍物检测方法.通过视觉获得障碍物的大小、远近信息.结合激光传感器对环境的感知能力,构建虚拟障碍物,并形成避障策略关键字.通过查询避障策略表,实现病房巡视机器人在复杂环境下的安全避障功能.实验结果验证了该方法的有效性.Considering of the working environment of ward inspection robot is complex and the obstacles have different kinds of shapes,a new method based on the vision-laser sensors to detect the obstacles was proposed.Firstly,a camera installed on the ward inspection robot was used to obtain the information of obstacles,such as the size of obstacles and the distance between the robot and obstacles. Then,a virtual obstacle was constructed using the information which was collected by laser radar and the camera.Obstacle avoidance strategies were built based on the position of the virtual obstacles.Finally,the ward inspection robot could realize obstacle avoidance safely and easily by querying the obstacle avoidance strategies.Experimental results verify the effectiveness of the proposed method.

关 键 词：移动机器人 避障 病房巡视 激光雷达 视觉测距 虚拟障碍 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]