Invited Speakers

Michael Kaess
Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology

iSAM and the Bayes Tree

I present a graphical model perspective of incremental smoothing and mapping (iSAM) that is based on our recent work called the Bayes tree. Similar to a junction tree, a Bayes tree encodes a factored probability density, but unlike the junction tree it is directed and maps more naturally to the square root information matrix of the simultaneous localization and mapping (SLAM) problem. The original iSAM algorithm incrementally maintains the square root information matrix by applying matrix factorization updates. These fairly abstract matrix updates translate to a simple editing of the Bayes tree and its conditional densities. The Bayes tree formulation allows us to derive a fully incremental iSAM algorithm called iSAM2, that performs incremental variable reordering and fluid relinearization.