Mobile Robot Self-Localization and Local Map Alignment with a Dempster Shafer Sensor Fusion Algorithm

Abstract

An important and challenging research issue associated with mobile robots is simultaneous localization and map building (SLAM), which refers to the mobile robot's capability of estimating its poses in the environment without external information, and simultaneous alignment of the local maps. To solve these kinds of research problems, researchers have proposed various methods such as odometry measurement, landmark matching, laser range image matching and a scale-invariant feature transform (SIFT)–based algorithm, all of which suffer from inevitable drawbacks such as a local minimum problem and a lack of SIFT features. Our solution for these problems is a sensor fusion method that uses a Dempster Shafer algorithm to fuse both the laser range information and the SIFT features information for the SLAM. Through a series of experiments, we tested and evaluated the proposed method. By real experiments, we analyzed the parameters of the ICP and SIFT features and we checked the robustness of our algorithm.