Memory-based navigation using data sequence of laser range finder

Abstract

In this paper we propose a novel navigation method for a mobile robot using a laser range finder based on the memory-based approach. A robot memorizes sequential scanning data of the laser range finder in the recording run. Then the localization of the robot is achieved based on the matching between the current scan and memorized scan sequence in the autonomous run. The matching process utilizes histogram-based method proposed by Weiss et al. Experimental results of the recording run and the autonomous navigation is presented to show the feasibility of the proposed method.