基于视觉和激光传感器信息融合的楼梯结构参数估计  

Staircase structure parameter estimation based on vision and laser sensor information fusion

作　　者：李艳杰[1,2] 刘宸 眭晋 LI Yan-jie;LIU Chen;SUI Jin(School of Mechanical Engineering, Shenyang Ligong University, Shenyang 110159, China;Taizhou Xiangda Fire Service Implement Co Ltd, Shenyang 110159, China;State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China)

机构地区：[1]沈阳理工大学机械工程学院,辽宁沈阳110159 [2]泰州市翔达消防器材有限公司,辽宁沈阳110159 [3]中国科学院沈阳自动化研究所机器人学国家重点实验室,辽宁沈阳110016

出　　处：《传感器与微系统》2018年第6期40-42,47,共4页Transducer and Microsystem Technologies

基　　金：国家重点研发计划资助项目(2016YFE0206200)

摘　　要：针对在室内楼梯环境下履腿复合机器人的自主攀爬过程中的楼梯结构参数确定问题,提出了一种基于视觉和激光传感器信息融合的楼梯目标识别与结构参数确定方法。将三维点云数据处理为二值图像,利用霍夫变换提取的特征直线确定台阶深度和宽度,通过点云直线间距离与台阶边缘直线距离比确定台阶高度。验证试验结果表明:所提方法能够快速、有效地获取足够精度的楼梯结构参数,为楼梯攀爬控制提供任务环境反馈信息。Aiming at problem of determining the parameters of staircase structure in the process of autonomous crawling of compound robots in indoor staircase environment,a method of stair target identification and structure parameter identification based on information fusion of vision and laser sensors is proposed. The method processes the 3D point cloud data into a binary image,and determines the step depth and width by using the feature straight line extracted by the Hough transform. The step height is determined by the ratio of the distance between the point cloud straight line and the straight line of the step edge. The verification test shows that this method can quickly and efficiently obtain the parameters of stair structure with sufficient precision and provide the feedback information of task environment for stair climbing control.

关 键 词：履腿复合机器人 相机与三维激光雷达信息融合 楼梯结构参数 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]