Vertigo: Versatile Extensions for Robust Inference using Graph Optimization

Vertigo is a C++ extension for g2o and gtam. It provides an implementation of switchable constraints and enables g2o and gtsam to solve pose graph SLAM problems despite the presence of false positive loop closure constraints.
Further information

Authors
Niko Suenderhauf;

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

Long Description
Vertigo is an extension library for g2o [1] and gtsam 2.0 [5].

It provides a C++ implementation of the switchable constraints described in [2,3]. This extension enables g2o or gtsam to solve pose graph SLAM problems in 2D and 3D despite a large number of false positive loop closure constraints. In addition, a re-implementation of the max-mixture model described in [4] for g2o is also contained.

Furthermore, Vertigo contains a number of standard pose graph SLAM datasets and a script to spoil them with false positive loop closure constraints. These datasets have been used in the evaluations [2] and [3]. They can serve as a set of benchmark datasets for future developments in robust pose graph SLAM. Have fun, I hope this is useful. Hopefully, more stuff will be added to Vertigo in the future. Any comments, thoughts and patches are welcome and largely appreciated.




Input Data
nodes and edges of a pose graph

Type of Map
pose graphs

Hardware/Software Requirements
Linux/Unix, cmake, gcc
g2o, gtsam (either one or both of them) Vertigo has been tested with gtsam 2.0 and g2o rev.19 (SVN on openslam.org)
Quick Install-Guide using cmake: mkdir build; cd build; cmake ..; make;

Papers Describing the Approach
Niko Suenderhauf, and Peter Protzel: Switchable Constraints for Robust Pose Graph SLAM, In Proc. of IEEE International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Portugal., 2012 (link)

Niko Suenderhauf: Robust Optimization for Simultaneous Localization and Mapping, PhD Thesis, Chemnitz University of Technology, 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.

Vertigo is licenced under GPL Version 3.

Further Information
[1] Rainer Kuemmerle, Giorgio Grisetti, Hauke Strasdat, Kurt Konolige, and Wolfram Burgard: g2o: A General Framework for Graph Optimization, IEEE International Conference on Robotics and Automation (ICRA), 2011 Available online: http://openslam.org/g2o.html

[2] Suenderhauf, N., Protzel, P. (2012). Switchable Constraints for Robust Pose Graph SLAM. Proc. of IEEE International Conference on Intelligent Robots and Systems (IROS), Vilamoura, Portugal.

[3] Suenderhauf, N. (2012). Robust Optimization for Simultaneous Localization and Mapping. PhD Thesis, Chemnitz University of Technology.

[4] Olson, E. and Agarwal, P. (2012). Inference on networks of mixtures for robust robot mapping. Proc. of Robotics: Science and Systems (RSS), Sydney, Australia.

[5] GTSAM2.0 https://collab.cc.gatech.edu/borg/gtsam/


*** OpenSLAM.org is not responsible for the content of this webpage ***
*** Copyright and V.i.S.d.P.: Niko Suenderhauf; ***