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.
引文
[1]Se S,Brady M.Vision-based detection of staircases[C]∥Proceedings of the Fourth Asian Conference on Computer Vision,Taipei:Springer,2000:535-540.
[2]Lu X,Manduchi R.Detection and localization of curbs and stairways using stereo vision[C]∥Proceedings of the 2005 IEEE International Conference on Robotics and Automation,Barcelona,Spain:IEEE,2005:4648-4654.
[3]朱万彬,钟俊,莫仁芸.激光位移传感器在角度测量中的应用[J].传感器与微系统,2010,29(6)131-133.
[4]曹鹏,尹文庆,吴林华,等.基于激光传感器的稻种轮廓形状测量方法研究[J].传感器与微系统,2017,36(3):29-32.
[5]Theeravithayangkura C,Takubo T,Mae Y,et al.Stair recognition of with laser range scanning by limb mechanism robot‘ASTERISK’[C]∥Proceedings of IEEE International Conference on Robotics and biomimetics,Bangkok,Thailand:IEEE,2009:915-920.
[6]OBwald S,Gutmann J S,Hornung A,et al.From 3D point clouds to climbing stairs:A comparision of plane segmentation approaches for humanoids[C]∥The 11th IEEE/RAS International Conference on Humanoid Robots,Bled,Slovenia:IEEE,2011:93-98.