GMapping is a highly efficient Rao-Blackwellized particle filer to learn
grid maps from laser range data.
Long Description
Recently Rao-Blackwellized particle filters have been
introduced as effective means to solve the simultaneous
localization and mapping (SLAM) problem. This approach uses a
particle filter in which each particle carries an individual
map of the environment. Accordingly, a key question is how to
reduce the number of particles. We present adaptive
techniques to reduce the number of particles in a Rao-
Blackwellized particle filter for learning grid maps. We
propose an approach to compute an accurate proposal
distribution taking into account not only the movement of the
robot but also the most recent observation. This drastically
decrease the uncertainty about the robot's pose in the
prediction step of the filter. Furthermore, we apply an
approach to selectively carry out re-sampling operations
which seriously reduces the problem of particle
depletion.
Example Images
Nice 3d view of the best particle mapping the Intel Reserach Lab
Map of the Freiburg Campus
Map of the MIT Killian Court
Input Data
The approach takes raw laser range data and
odometry. This version is optimized for long-range laser
scanners like SICK LMS or PLS scanner. Short range lasers like
Hokuyo scanner will not work that well with the standard
parameter settings.
Logfile Format
Carmen log format
Type of Map
grid maps
Hardware/Software Requirements
Linux/Unix, GCC 3.3/4.0.x
CARMEN (latest version)
Quick Install-Guide using bash: ./configure; . ./setlibpath; make;
Papers Describing the Approach
Giorgio Grisetti, Cyrill Stachniss, and Wolfram Burgard:
Improved Techniques for Grid Mapping with Rao-Blackwellized Particle Filters,
IEEE Transactions on Robotics, Volume 23, pages 34-46, 2007 (
link)
Giorgio Grisetti, Cyrill Stachniss, and Wolfram Burgard:
Improving Grid-based SLAM with Rao-Blackwellized Particle Filters by Adaptive Proposals and Selective Resampling,
In Proc. of the IEEE International Conference on Robotics and Automation (ICRA), 2005 (
link)
Further Reading
A. Doucet:
On sequential simulation-based methods for bayesian filtering,
Technical report, Signal Processing Group, Dept. of Engeneering, University of Cambridge, 1998
License Information
This software is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
The authors allow the users of OpenSLAM.org to use and modify the source code for their own research. Any commercial application, redistribution, etc has to be arranged between users and authors individually and is not covered by OpenSLAM.org.
GMapping is licenced under
BSD-3-Clause
Further Information
The SLAM approach is available as a library and
can be easily used as a black box. Making changes to the
algorithm itself, however, requires quite some C++ experience.
