rtab-map feature

edit

RTAB-Map is a SLAM approach. When navigation is mentioned, move_base is always used under the hood. RTAB-Map can do planning in its graph (i.e., topological planning) but still rely on move_base (i.e., metrical planning) to make the robot move and avoid dynamic obstacles. The SLAM+planning capability is described in this paper:

M. Labbé and F. Michaud, “Long-term online multi-session graph-based SPLAM with memory management,” in Autonomous Robots, vol. 42, no. 6, pp. 1133-1150, 2018.

For SLAM alone, rtabmap can do visual and lidar SLAM. See this paper focusing only on the SLAM part:

M. Labbé and F. Michaud, “RTAB-Map as an Open-Source Lidar and Visual SLAM Library for Large-Scale and Long-Term Online Operation,” in Journal of Field Robotics, vol. 36, no. 2, pp. 416–446, 2019.

EDIT: A list of ros nodes are described on rtabmap_ros page, along with some demos including rosbags. Some ROS tutorials are here. For tools, the DatabaseViewer may be the most useful tool to analyse the map.