Simultaneous localization and Mapping(SLAM) in indoor environment based on characters recognition

SLAM enables a robot to construct a map of an unknown environment while using the same map to bound or nullify positioning errors. This paper presents a new method for mobile robot simultaneous localization and mapping in indoor office-like environment. Topological map is set up based on the environment characters recognition and Voronoi graph, which allows the robot to classify and localize in distinguished places. In order to minimize the odometry errors, simple wheel-slippage calibration is presented. After the characteristic patterns recording topologies had been previously generated at various positions, the robot can identify its position when traveling in an indoor environment. The experiments demonstrate the proposed SLAM algorithm to be an effective approach to localize the mobile robot in an unknown environment from sensor measurements and build map concurrently.