1A2-I06 全方位ステレオ視の距離誤差を考慮したICPによるロボットの相対位置姿勢推定(移動ロボットの自己位置推定と地図構築(1))

Abstract

Range-based ego-motion estimation method, which is so-called "scan-matching", has an important role in robotics. However, iterative closest points (ICP), which is basic scan-matching method, assumes that the error of obtained range data is constant. This degrades estimation results when the robot uses sensors whose error is not constant, i.e.stereo vision. In this paper, we propose a ICP-based ego-motion estimation method considering range ambiguity of the stereo vision. The key idea is comparing obtained 3D points in not Euclidean space but disparity space. We implement the method to the robot mounting omnidirectional stereo vision. Simulation experiments are conducted to show the effectiveness of our method.