COP-SLAM

COP-SLAM is a highly efficient closed-form 3-D SLAM approach, It optimizes pose-chains on-line and it is compatible with g2o. The COP-SLAM demo program comes with 60 kilometers of pose-chain datasets, which are obtained with visual odometry and appearance-based loop detection.
Further information

Authors
Gijs Dubbelman; Brett Browning;

Get the Source Code via SVN
svn co https://svn.openslam.org/data/svn/copslam

Long Description
Closed-form Online Pose-chain SLAM (COP-SLAM), efficiently and accurately optimizes pose-chains, in closed-form by exploiting their Lie group structure. Pose-chains are a specific type of extremely sparse pose-graphs and are a product of contemporary SLAM front-ends, which perform accurate visual odometry and reliable appearance-based loop detection. They are relevant for challenging robotic applications in large-scale 3-D environments for which frequent loop detection is not desired or not possible. It has been shown that the accuracy obtained by Closed-form Online Pose-chain SLAM is comparable to that of state-of-the-art iterative methods, while the time it needs to compute its solution is orders of magnitudes lower. This novel SLAM technique thereby is relevant to a broad range of robotic applications and computational platforms. The COP-SLAM demo program has no external dependencies and comes with 60 kilometers of ready-to-use pose-chain datasets. The process of building and running COP-SLAM on these datasets is therefore extremely straightforward.

Example Images

Nice 3-D view of results of COP-SLAM together with GPS ground truth, input from visual odometer, and result from g2o.

Input Data
COP-SLAM takes as input g2o pose graph files, which specify nodes and edges of a pose graph. Example data sets with a total length of 60 kilometers are provided with the demo program.

Logfile Format
The g2o file format with vertices and edges in an on-line timely order. For more information, we refer to the README that comes with the COP-SLAM demo program.

Type of Map
Pose-chains (i.e. timely ordered extremely sparse pose-graphs).

Hardware/Software Requirements
Linux/Unix, GCC (tested on Debian and Ubuntu)
Quick Install-Guide using CMAKE
Visualization with Octave, Matlab, or g2o_viewer.

Papers Describing the Approach
G. Dubbelman and B. Browning: Closed-form Online Pose-chain SLAM, IEEE International Conference on Robotics and Automation, Karlsruhe, Germany, May 6-10, 2012 (link)

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.

COP-SLAM is licensed under GPL v3.

Further Information
The COP-SLAM demo program is a stand-alone application. It should however be straightforward to integrate COP-SLAM with other software, e.g. with ROS. For help with this, please feel free to contact Gijs Dubbelman (gijsdubbelman@gmail.com).


*** OpenSLAM.org is not responsible for the content of this webpage ***
*** Copyright and V.i.S.d.P.: Gijs Dubbelman; Brett Browning; ***