RTAB-Map

RTAB-Map (Real-Time Appearance-Based Mapping) is a RGB-D, Stereo, and Lidar Graph-Based SLAM approach. It uses an incremental appearance-based loop closure detector to determine if a new image comes from a previous location or a new location. When a loop closure hypothesis is accepted, a new constraint is added to the map’s graph, and a graph optimizer minimizes the errors in the map. It can be used for 6DoF mapping with a handheld Kinect, stereo camera, or 3D lidar, or for 3DoF mapping on a robot equipped with a laser rangefinder.

Installation instructions are provided on the RTAB-Map website. There are also tutorials and tools available. For ROS users, you can find a package overview on the ROS wiki page for rtabmap. Additionally, there is a SetupOnYourRobot page to help integrate RTAB-Map on your robot.

If OpenCV is built without the nonfree module, RTAB-Map can be used under the permissive BSD License. However, if OpenCV is built with the nonfree module, RTAB-Map is free for research only because it depends on SURF features, which are not free for commercial use. SIFT can be a good free equivalent of SURF since its patent has expired.

The RTAB-Map app on Google Play Store or Apple Store requires access to the camera to record images for creating the map. A database containing these images is saved locally on the device. While location permission is required to install RTAB-Map Tango, GPS coordinates are not saved by default unless the user enables the 'Save GPS' option in the settings. RTAB-Map only accesses the RTAB-Map folder for saving, exporting, and opening maps and does not share information over the internet unless the user explicitly exports a map to Sketchfab or another location.

Yes, there are several tutorials and examples available. These include a Multi-session mapping tutorial, a demo for car mapping and localization with CitySim simulator and CAT Vehicle, and an indoor drone visual navigation example using move_base, PX4, and mavros. There are also examples for exporting data to MeshLab and speeding up RTAB-Map’s odometry.

You can visit the RTAB-Map wiki for detailed information. For standalone use, you can ask a question on the RTAB-Map Forum or post an issue on GitHub. For ROS users, you can ask questions on answers.ros.org or robotics.stackexchange.com with the rtabmap or rtabmap-ros tag.