The Borg Lab

incremental SAM

iSAM, or Incremental Smoothing and Mapping, is a novel incremental optimization technique for mapping and localization in robotics. In its latest incarnation, iSAM2 , we represent what we know about the robot’s environment as a large tree data structure called the Bayes tree, which we iteratively update as more measurements come in via the robot’s sensors. Please refer to the publications below, but you can also watch a movie here.

People

Related Papers

Kaess M, Johannsson H, Roberts R, Ila V, Leonard J, Dellaert F
International Journal of Robotics Research (IJRR)
2012
iSAM2: Incremental Smoothing and Mapping Using the Bayes Tree, Kaess, Michael, Johannsson Hordur, Roberts Richard, Ila Viorela, Leonard John, and Dellaert Frank , International Journal of Robotics Research (IJRR), (2012)
Kaess M, Johannsson H, Roberts R, Ila V, Leonard J, Dellaert F
ICRA
2011
iSAM2: Incremental Smoothing and Mapping with Fluid Relinearization and Incremental Variable Reordering, Kaess, Michael, Johannsson Hordur, Roberts Richard, Ila Viorela, Leonard John, and Dellaert Frank , ICRA, (2011)
Kaess M, Ila V, Roberts R, Dellaert F
2010
The Bayes Tree: Enabling Incremental Reordering and Fluid Relinearization for Online Mapping, Kaess, Michael, Ila Viorela, Roberts Richard, and Dellaert Frank , Jan, Number MIT-CSAIL-TR-2010-021, (2010)
Kaess M, Ila V, Roberts R, Dellaert F
WAFR
2010
The Bayes Tree: An Algorithmic Foundation for Probabilistic Robot Mapping, Kaess, Michael, Ila Viorela, Roberts Richard, and Dellaert Frank , WAFR, Dec, (2010)
Kaess M, Ranganathan A, Dellaert F
Transactions on Robotics (TRO)
2008
iSAM: Incremental Smoothing and Mapping, Kaess, Michael, Ranganathan Ananth, and Dellaert Frank , Transactions on Robotics (TRO), (2008)
Kaess M, Ranganathan A, Dellaert F
ICRA
2007
iSAM: Fast Incremental Smoothing and Mapping with Efficient Data Association, Kaess, Michael, Ranganathan Ananth, and Dellaert Frank , ICRA, April, Rome; Italy, (2007)