ROBOT LOCALIZATION AND MAP CONSTRUCTION USING SENSOR DATA

This work describes the problem of map contraction and a robot localization using sensor data and data from a group of other robots. This methodology is called SLAM or CML, Simultaneous Localization and Mapping or Concurrent Mapping and Localization, respectively. SLAM solves problems connected with building a map of an unknown environment by a mobile robot while at the same time navigating the environment using the map. SLAM comprises of multiple parts: landmark extraction, data association, state estimation, state update and landmark update. Each part can be performed in different ways. As the robot has sensors on one height from the ground, we will get 2D map [1].