机器人辅助的三维点云自动配准  

Robot-Assisted Automatic Registration of Three Dimensional Point Clouds

作　　者：孙威[1] 黄惠[1] 

机构地区：[1]中国科学院深圳先进技术研究院,深圳518055

出　　处：《集成技术》2015年第6期37-45,共9页Journal of Integration Technology

基　　金：国家自然科学基金(61379091);科技部863项目(2015AA016401);深圳市可视计算与可视分析重点实验室(CXB201104220029A);深圳市基础研究项目(JCYJ20140901003939034;JCYJ20140901003938994)

摘　　要：针对三维扫描时不同扫描仪坐标系下三维点云配准困难且耗时过多的难题,提出一种利用机器人转换扫描仪坐标来进行点云配准的算法。该算法主要有两步:第一步为粗配准,将三维扫描仪固定在服务机器人的机械臂末端,在三维扫描过程中实时记录扫描仪的姿势,并利用此信息将不同扫描仪坐标系的点云转换到机器人基底坐标系;第二步为精细配准,以第一步的结果作为改进的迭代最近点算法的初始值,再利用加权的稀疏迭代最近点算法对机器人基底坐标系下不同帧的点云进行精细配准。实验证明,相比其他基于仪器的配准方法和直接利用迭代最近点算法进行配准的方法,该方法能有效提高配准成功率、减少配准时间、提高配准精度。Automatic registration of point clouds is a challenging task especially when the overlap between them is too small to initialize the traditional iterative closest point algorithm directly. A method for registering 3D point clouds in different coordinates was proposed by using the scanner＇s pose information, recorded by a robot. This method consisted of two steps： firstly, 3D scanner was set on the end effector of the robot, which recorded the 6D pose of the scanner when an object was scanned in real time. Using this recorded pose information, the captured point clouds from different scanner coordinates were transformed to robot base coordinate. Secondly, the weighted sparse iterative closest point was used to align the point clouds in robot base coordinate which refines the result of the first step. This method was tested on various data and situations. The experiment results show that the proposed method could align point clouds with lower overlapping ratio, and is more accurate, faster and more robust to outliers than existing methods.

关 键 词：点云配准 迭代最近点算法 坐标变换 三维扫描 机器人 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]