Difference between revisions of "RTAB-Map"

From IntRoLab
Line 57: Line 57:
 
* Standalone application and libraries : [http://rtabmap.googlecode.com rtabmap]
 
* Standalone application and libraries : [http://rtabmap.googlecode.com rtabmap]
 
* ROS packages : [http://rtabmap-ros-pkg.googlecode.com rtabmap-ros-pkg]
 
* ROS packages : [http://rtabmap-ros-pkg.googlecode.com rtabmap-ros-pkg]
 +
<div style="text-align: center;">
 +
[[File:RTAB-Map_Interface.png|800px|Images acquired in Need For Speed Most Wanted]]
 +
</div>
 
</english>
 
</english>
 
<french>
 
<french>
Line 63: Line 66:
 
* Logiciel "stand-alone" et les bibliothèques logicielles : [http://rtabmap.googlecode.com rtabmap]
 
* Logiciel "stand-alone" et les bibliothèques logicielles : [http://rtabmap.googlecode.com rtabmap]
 
* Noeuds ROS : [http://rtabmap-ros-pkg.googlecode.com rtabmap-ros-pkg]
 
* Noeuds ROS : [http://rtabmap-ros-pkg.googlecode.com rtabmap-ros-pkg]
</french>
 
 
<div style="text-align: center;">
 
<div style="text-align: center;">
[[File:RTAB-Map_Interface.png|800px]]
+
[[File:RTAB-Map_Interface.png|800px|Images provenant de Need For Speed Most Wanted]]
 
</div>
 
</div>
 +
</french>
 
<english>
 
<english>
 
== Data sets ==
 
== Data sets ==

Revision as of 20:51, 12 April 2011

RTAB-Map : Real-Time Appearance-Based Mapping

Description[edit]

Loop closure detection is the process involved when trying to find a match between the current and a previously visited locations in SLAM (Simultaneous Localization And Mapping). Over time, the amount of time required to process new observations increases with the size of the internal map, which may affect real-time processing. RTAB-Map is a novel real-time loop closure detection approach for large-scale and long-term SLAM. Our approach is based on efficient memory management to keep computation time for each new observation under a fixed time limit, thus respecting real-time limit for long-term operation. Results demonstrate the approach's adaptability and scalability using one custom data set and four standard data sets.

Results[edit]

Note that these results (more recent) may differ from those in the video...

Figure 1: Summary of the loop closures detected on UdeS1Hz data set :

  • Green : Loop closures detected
  • Yellow : Loop closures rejected
  • Red : Unable to detect a loop closure because old places could not be retrieved

Figure 2: Processing time for each image acquired (real-time limit fixed to 700 ms for an image rate of 1 Hz)

Figure 3: Precision-Recall (43% recall at 100% precision)

RTAB-Map LoopClosureMapResults.png RTAB-Map LoopClosureTimeResults.png RTAB-Map RecallResults.png



Source code[edit]

The code was tested on Windows (Xp, 7), Mac OS X 10.6 and Ubuntu 10.4LTS.

Images acquired in Need For Speed Most Wanted

Data sets[edit]

UdeS1Hz samples[edit]

Downloads[edit]

Community data sets from other loop closure detection approaches :


Publications

Labbé, M., Michaud, F. (2011), “Memory management approach for real-time appearance-based loop closure detection”, To appear in IEEE Transactions on Robotics.