iSAM - Incremental Smoothing and Mapping

iSAM is a general optimization library for incremental sparse nonlinear problems as encountered in simultaneous localization and mapping (SLAM).
Further information

Michael Kaess; Hordur Johannsson; John Leonard;
No link to code anymore

Long Description
The iSAM library provides efficient algorithms for batch and incremental optimization, recovering the exact least-squares solution. The library can easily be extended to new problems, and functionality for often encountered 2D and 3D SLAM problems is already provided. The iSAM algorithm was originally developed by Michael Kaess and Frank Dellaert at Georgia Tech.

Input Data
Factor graph: Nodes (variables) and factors (measurements)

Type of Map
Feature-based or pose graph

Hardware/Software Requirements
Linux/Unix/Mac, requires SuiteSparse.

Installation instructions and source code documentation

Papers Describing the Approach
Michael Kaess, Ananth Ranganathan and Frank Dellaert: iSAM: Incremental Smoothing and Mapping, IEEE Transactions on Robotics (TRO), vol. 24, no. 6, pp. 1365-1378, 2008 (link)

Michael Kaess and Frank Dellaert: Covariance Recovery from a Square Root Information Matrix for Data Association, Journal of Robotics and Autonomous Systems (RAS), vol. 57, pp. 1198-1210, 2009 (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 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

iSAM is licenced under GNU LGPL version 2.1.

Further Information
Compact and efficient C++ library code. Also includes an iSAM application with integrated 3D viewer and several demo programs.

*** is not responsible for the content of this webpage ***
*** Copyright and V.i.S.d.P.: Michael Kaess; Hordur Johannsson; John Leonard; ***