A tool that provides real-time appearance-based mapping
The loop closure detection approach is fully incremental, starting with an empty
memory. The robot builds his own representation of the environment by linking new acquired images with previous ones (e.g., detecting loop closures).
Furthermore, the method implemented here may be considered as a Topological SLAM (Simultaneous Localization And Mapping) approach. Memory management makes it possible to process each new image under a fixed real-time limit, thus ideal for long-term operation and systems with limited resources.
Detailed instructions on how to install and use the RTAB-Map utility on your Mac are available HERE.
RTAB-Map is cross-platform and it works on Mac OS X and Windows. Binaries for the Windows platform are available on the project's homepage.
In a hurry? Add it to your Download Basket!
What's New in This Release:
- Moved all sensorimotor stuff to the new project SeMoLearning. Now RTAB-Map contains only things about loop closure detection using a Bayesian bag-of-words approach, as in the RTAB-Map related papers. This also simplified the interface. Personal note: it became a little too much time consuming to continue to support the classic RTAB-Map while developing a sensorimotor approach in the same project (to not break old stuff). Thus, I will no longer maintain this project (though I can still answer questions if you have ones).
- Added a new option from the menu to print the detected loop closure IDs in the application console (in MATLAB matrix format, for fast copy/paste in MATLAB).
- Also, when generating the map using the menu action, a tip is printed in the application console to know how print a pdf from the ".dot" file with Graphiz: