A Topological SPLAM Approach for Robust Exploration

Abstract

This paper describes a simultaneous planning localization and mapping (SPLAM) approach, where a mobile robot explores the environment efficiently and also considers the requisites of the simultaneous localization and mapping algorithm. The method is based on the randomized incremental generation of a data structure called the Random Exploration Graph (REG), which represents a roadmap of the explored area with an associated safe region. The REG approach includes a frontier control to carry a registry over the nodes that have not been fully explored. A continuous localization procedure based on B-Splines features of the safe region is integrated in the scheme. Simulations and experiments on the Pioneer P3DX robot show the performance of this approach.