2015/05/23 by Fredrik Lindsten, Pete Bunch, Simo Särkkä +3 · 34 citations
Computer Science · Engineering · Mathematics · #Algorithm #Applied mathematics #Artificial intelligence #Computer science #Conditional independence #Distributed Sensor Networks and Detection Algorithms #Fault Detection and Control Systems #Gaussian #Kalman filter #Mathematical optimization #Mathematics #Particle filter #Physics #Smoothing #State space #Statistical physics #Statistics #Target Tracking and Data Fusion in Sensor Networks #stat.CO
paper · pdf · doi:10.1109/jstsp.2015.2506543
published in IEEE Journal of Selected Topics in Signal Processing 10(2), 353-365 (Institute of Electrical and Electronics Engineers)
arxiv created 2015/05/23 · openalex publication_date 2015/12/09 · arxiv updated 2016/04/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Sequential Monte Carlo (SMC) methods, such as the particle filter, are by now one of the standard computational techniques for addressing the filtering problem in general state-space models. However, many applications require post-processing of data offline. In such scenarios the smoothing problem-in which all the available data is used to compute state estimates-is of central interest. We consider the smoothing problem for a class of conditionally linear Gaussian models. We present a forward-backward-type Rao-Blackwellized particle smoother (RBPS) that is able to exploit the tractable substructure present in these models. Akin to the well known Rao-Blackwellized particle filter, the proposed RBPS marginalizes out a conditionally tractable subset of state variables, effectively making use of SMC only for the “intractable part” of the model. Compared to existing RBPS, two key features of the proposed method are: 1) it does not require structural approximations of the model, and 2) the aforementioned marginalization is done both in the forward direction and in the backward direction.