Indoor autonomous mobile robot localization using natural landmark

Abstract

In this paper we present a method which can solve simultaneous localization and mapping (SLAM) problem using natural landmarks when mobile robot is in a long corridor or a roomy space. Generally, for an EKF-SLAM procedure, it is difficult to estimate the robot position before getting a complete landmark measurement. In this paper, the method we have proposed not only can reduce the complicated merging identical landmark process, but also can utilize pieces information of observed landmark to improve the localization performance in the EKF-SLAM. We have demonstrated our estimation method to SLAM process, it can make the overall framework effectively to adapt more natural landmarks for a common indoor environment.