GMapping Giorgio Grisetti http://www.informatik.uni-freiburg.de/~grisetti Cyrill Stachniss http://www.informatik.uni-freiburg.de/~stachnis Wolfram Burgard http://www.informatik.uni-freiburg.de/~burgard http://www.informatik.uni-freiburg.de/~stachnis/research/rbpfmapper/ GMapping is a highly efficient Rao-Blackwellized particle filer to learn grid maps from laser range data. 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. Linux/Unix, GCC 3.3/4.0.x CARMEN (latest version) Quick Install-Guide using bash: ./configure; . ./setlibpath; make; 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. Carmen log format http://www.informatik.uni-freiburg.de/~stachnis/pictures/intel3d.avi http://www.informatik.uni-freiburg.de/~stachnis/pictures/intel3d.jpg Nice 3d view of the best particle mapping the Intel Reserach Lab http://www.informatik.uni-freiburg.de/~stachnis/research/rbpfmapper/gmapper-web/freiburg-campus/fr-campus-20040714.carmen.gfs.png http://www.informatik.uni-freiburg.de/~stachnis/research/rbpfmapper/gmapper-web/freiburg-campus/sfr-campus-20040714.carmen.gfs.png Map of the Freiburg Campus http://www.informatik.uni-freiburg.de/~stachnis/research/rbpfmapper/gmapper-web/MIT/MIT_Infinite_Corridor_2002_09_11_same_floor.gfs.png http://www.informatik.uni-freiburg.de/~stachnis/research/rbpfmapper/gmapper-web/MIT/sMIT_Infinite_Corridor_2002_09_11_same_floor.gfs.png Map of the MIT Killian Court Giorgio Grisetti, Cyrill Stachniss, and Wolfram Burgard IEEE Transactions on Robotics 2006 http://www.informatik.uni-freiburg.de/~stachnis/pdf/grisetti06tro.pdf Giorgio Grisetti, Cyrill Stachniss, and Wolfram Burgard In Proc. of the IEEE International Conference on Robotics and Automation (ICRA) 2005 http://www.informatik.uni-freiburg.de/~stachnis/pdf/grisetti05icra.pdf A. Doucet Technical report, Signal Processing Group, Dept. of Engeneering, University of Cambridge 1998 GMapping is licenced under the Creative Commons (Attribution-NonCommercial-ShareAlike). 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. http://webhostingrating.com/libs/openslam-gmapping-be