Topo-geometric modeling and localization in indoor environments

In this paper a new SLAM (simultaneous localization and mapping) algorithm in an unknown indoor environment is presented. SLAM is one of the fundamental problems in mobile robots. The proposed approach uses a topo-geometric map obtained from the local Voronoi diagram (LVD) using the measurements of a laser telemeter. According to estimate the robot position, the map´s topological and geometrical characteristics are used. The proposed algorithm introduces a backward step, which revises all previous poses. This step is fundamental to obtain good results in large and cyclic indoor environments. Genetic algorithms are used to improve the estimated approach. In order to maintain the continuity in the global topo-geometric map, a virtual Voronoi diagram is built.