ROS based SLAM for a Gazebo Simulated Fetch Robot in Unknown Indoor Environment

Abstract

Mapping and Navigation are the basic need in many autonomous robot applications like Search and Rescue, Mining, surveillance and Ware house management etc., The ability of the robot to make simultaneously map of its surroundings and localize itself in relation to that environment is the most important element of mobile robots. To solve Simultaneous Localization and Mapping (SLAM) many algorithms could be utilized to build up the SLAM process and SLAM is a developing area in Robotics research. This paper describes Gazebo simulation approach to SLAM based on Robot Operating System (ROS) using Fetch robot. The mapping process is done by making use of the open-source Gmapping method. The Gmapping method applies Rao-Blackwellized particle filters and laser scanner data to find the Fetch robot in unknown Indoor environment and build a map. Data visualization is done using Rviz and a robot simulation is done in Gazebo. From our research, it is shown that for indoor environments Gmapping algorithm is employed to generate 2D maps with SICK Laser scanner and RGBD sensor placed on mobile robot. The algorithm has been evaluated and maps are constructed by the Fetch robot in static unknown indoor environment.