Integration of intelligent technologies for simultaneous localization and mapping

Abstract

This paper proposes a simultaneous localization and mapping method for a mobile robot in unknown environments. According to the measured distance by laser range finder, a topological environmental map is updated sequentially by using growing neural gas. When the difference between the measured distance and its corresponding map data is large, the robot must update the self-location. In this paper, we apply a particle filter and steady-state genetic algorithm, and compare their performance. Finally, we discuss the effectiveness of the proposed methods through several experimental results.