Mapping and Navigation for Indoor Robots under ROS: An Experimental Analysis

Abstract

Since it was proposed, the Robot Operating System (ROS) has fostered solutions for various problems in robotics in the form of ROS packages. One of these problems is Simultaneous Localization and Mapping (SLAM), a problem solved by computing the robot pose and a map of its environment of operation at the same time. The increasingly availability of robot kits ready to be programmed and also of RGB-D sensors often pose the question of which SLAM package should be used given the application requirements. When the SLAM subsystem must deliver estimates for robot navigation, as is the case of applications involving autonomous navigation, this question is even more relevant. This work introduces an experimental analysis of GMapping and RTAB-Map, two ROS compatible SLAM packages, regarding their SLAM accuracy, quality of produced maps and use of produced maps in navigation tasks. Our analysis aims ground robots equipped with RGB-D sensors for indoor environments and is supported by experiments conducted on datasets from simulation, benchmarks and from our own robot.

Mobile Robot Simulation and Navigation in ROS and Gazebo

“…These two packages are part of the packages in the ROS and can be used ready-made. The Mapping package is used to create and retrieve map information [9]. The AMCL package provides self-localization algorithms [10].…”

RPLiDAR-Based Mapping in Development of a Health Service Assisting Robot in COVID-19 Pandemic

“…The application of LiDAR in robotic navigation systems has a huge impact in predicting environmental conditions in real-time because LiDAR has very high accuracy, particularly for short-range measurements in room mapping [28]- [30]. Robot Operating System (ROS) is used to perform mapping using LiDAR sensors, considering that in recent years the use of ROS has become increasingly widespread in the development of robots [31].…”