Comparing algorithms for point cloud registration for accurately locating rod intersections for robot action

In this paper we test 15 point-cloud registration algorithms (including four iterative closest point (ICP) and three coherent point drift (CPD) variants) to find which ones give least registration error and are fastest for our use case: detecting the intersection point between two rods for an industrial robot application. The algorithms are all in common use. The data comprises both real and simulation-adjusted images of approximately perpendicular metal rods taken from different angles.