Three dimensional recognition of environments for a mobile robot using laser range finder

In this paper we propose a method for estimating the position and the orientation of a mobile robot from the Hough parameters of several flat surfaces in the environment. The 3D data in the environment are acquired from a laser range finder with vertical scanning and simultaneously the robot is rotating and the horizontal scanning can be achieved. After the measured 3D data by the LRF are projected on to a 2D plane, the 2D or 3D Hough parameters can be calculated and the position and the orientation of the robot can be determined. We have performed experimental examinations, and evaluated their accuracies and calculation time, and verified that this proposed method would be feasible for an autonomous vehicle.