Introduction:
A related initiative is OpenSLAM, a collection of open-source SLAM packages available at the OpenSLAM web-site since January 2007. Its goal is to provide a platform for SLAM researchers which give them the possibility to publish their algorithms. OpenSLAM provides to every interested SLAM researcher a subversion (svn) repository and a small webpage in order to publish and promote their work. In the repository, only the authors have full access to the files; other users are restricted to read-only access. OpenSLAM does not really aim to provide a repository for the daily development process of early SLAM implementations. Published algorithm should have a certain degree of robustness. OpenSLAM does not force the authors to give away the copyright for their code, but only require that the algorithms are provided as source code and that the authors allow the users 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.
- CAS Robot Navigation Toolbox. It's a GNU GPL licensed Matlab toolbox for robot localization and mapping. It is made for research and education and independent on the type(s) of feature and type(s) of sensors.
- DP-SLAM aims to achieve truly simultaneous localization and mapping without landmarks, it is compatible with techniques that correct maps when a loop is closed, and is accurate enough that no special loop closing techniques are required in most cases.
- GMapping is a highly efficient Rao-Blackwellized particle filer to learn grid maps from laser range data.
- GridSLAM is an easy to use and understand Rao-Blackwellized particle filer to learn grid maps from laser range data.
- SLAM Package of Tim Bailey. This package is a collection of implemented SLAM approaches by Tim Bailey. The code is written in MatLab and performs EFK, UKF, FastSLAM 1, and FastSLAM2.
- CEKF-SLAM is a Compressed Extended Kalman Filter-based SLAM simulator written under Matlab.
- Thin Junction Tree Filters for SLAM. This is a software package that implements a filtering technique that maintains a tractable approximation of the belief state as a thin junction tree.
- TORO (Tree-based netwORk Optimizer) is an optimization approach for constraint-network. It provides a highly efficient, gradient descent-based error minimization procedure. There is a 2D and a 3D version of TORO available.
Further information:
More information can be found at the official website.