Difference between revisions of "RTAB-Map"
Line 82: | Line 82: | ||
* Walking the same loop of ~2 km two times. | * Walking the same loop of ~2 km two times. | ||
* The data set contains indoor and outdoor environments. | * The data set contains indoor and outdoor environments. | ||
+ | <div style="text-align: center;"> | ||
+ | [[File:UdeS_1Hz_map.png|250px]] | ||
+ | </div> | ||
+ | ([http://maps.google.ca/maps?q=Universit%C3%A9+de+sherbrooke&hl=en&ie=UTF8&ll=45.377714,-71.927383&spn=0.011546,0.016158&sll=49.891235,-97.15369&sspn=43.664668,66.181641&t=h&z=16|Google maps]) | ||
<gallery perrow=5> | <gallery perrow=5> | ||
File:UdeS_1Hz_sample1.jpg | File:UdeS_1Hz_sample1.jpg | ||
Line 108: | Line 112: | ||
* 2 areas visited hundred times each (100 traversals in area 1 then moved to area 2 for another 102 traversals). | * 2 areas visited hundred times each (100 traversals in area 1 then moved to area 2 for another 102 traversals). | ||
* 25098 images at 1 Hz (7 hours). | * 25098 images at 1 Hz (7 hours). | ||
+ | <div style="text-align: center;"> | ||
+ | [[File:NFSMW_1Hz_map.png|250px]] | ||
+ | </div> | ||
<gallery perrow=5> | <gallery perrow=5> | ||
File:NFSMW_1Hz_sample1.jpg | File:NFSMW_1Hz_sample1.jpg |
Revision as of 19:20, 25 July 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.
Example of sensorimotor learning using directly this loop closure detection approach (new in RTAB-Map 0.3) :
Results[edit]
Note that these results (more recent) may differ from those in the video...
Figure 1: Summary of the loop closures detected on UdeS 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)
Source code[edit]
The code was tested on Windows (Xp, 7), Mac OS X 10.6 and Ubuntu 10.4LTS.
- Standalone application, libraries and ROS packages : rtabmap.googlecode.com
Data sets[edit]
UdeS
- 5395 images at 1 Hz (1.5 hours).
- Walking the same loop of ~2 km two times.
- The data set contains indoor and outdoor environments.
(maps)
UdeS_1Hz.part1.rar UdeS_1Hz.part2.rar UdeS_1Hz.part3.rar UdeS_1Hz GroundTruth
NFSMW
- Images taken from the racing video game Need For Speed: Most Wanted.
- 2 areas visited hundred times each (100 traversals in area 1 then moved to area 2 for another 102 traversals).
- 25098 images at 1 Hz (7 hours).
NFSMW_1Hz.part01.rar NFSMW_1Hz.part02.rar NFSMW_1Hz.part03.rar NFSMW_1Hz.part04.rar NFSMW_1Hz.part05.rar NFSMW_1Hz.part06.rar NFSMW_1Hz.part07.rar NFSMW_1Hz.part08.rar
Community Community data sets from other loop closure detection approaches :
- Angeli et al. : Lip6Indoor et Lip6Outdoor
- Cummins et al. (FAB-MAP) : NewCollege et CityCentre
Ground truths (readable by RTAB-Map) :
- NewCollege.rar 1073 images at ~0.5 Hz (left and right images merged)
- CityCentre.rar 1237 images at ~0.5 Hz (left and right images merged)
- Lip6Indoor.rar 388 images at 1 Hz
- Lip6Outdoor.rar 531 images at 0.5 Hz
Publications
M. Labbé and F. Michaud, “Memory management for real-time appearance-based loop closure detection,” in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, 2011. (Accepted)