Details

Autor(en) / Beteiligte

• Petersen, Eike
• Hoffmann, Christian
• Rostalski, Philipp

Titel

On Approximate Nonlinear Gaussian Message Passing on Factor Graphs

Ist Teil von

• 2018 IEEE Statistical Signal Processing Workshop (SSP), 2018, p.513-517

Ort / Verlag

IEEE

Erscheinungsjahr

2018

Link zum Volltext

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• Factor graphs have recently gained increasing attention as a unified framework for representing and constructing algorithms for signal processing, estimation, and control. One capability that does not seem to be well explored within the factor graph tool kit is the ability to handle deterministic nonlinear transformations, such as those occuring in nonlinear filtering and smoothing problems, using tabulated message passing rules. In this contribution, we provide general forward (filtering) and backward (smoothing) approximate Gaussian message passing rules for deterministic nonlinear transformation nodes in arbitrary factor graphs fulfilling a Markov property, based on numerical quadrature procedures for the forward pass and a Rauch-Tung-Striebel-type approximation of the backward pass. These message passing rules can be employed for deriving many algorithms for solving nonlinear problems using factor graphs, as is illustrated by the proposition of a nonlinear modified Bryson-Frazier (MBF) smoother based on the presented message passing rules.