Parallel Iterated Extended and Sigma-point Kalman Smoothers
| Autor: | Simo Särkkä, Fatemeh Yaghoobi, Sakira Hassan, Adrien Corenflos |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Signal processing Computer science Graphics processing unit Kalman filter Statistics - Computation symbols.namesake Nonlinear system Computer Science - Distributed Parallel and Cluster Computing Iterated function Taylor series symbols Time domain Distributed Parallel and Cluster Computing (cs.DC) Algorithm Smoothing Computation (stat.CO) |
| Zdroj: | ICASSP |
| DOI: | 10.48550/arxiv.2102.00514 |
| Popis: | The problem of Bayesian filtering and smoothing in nonlinear models with additive noise is an active area of research. Classical Taylor series as well as more recent sigma-point based methods are two well-known strategies to deal with these problems. However, these methods are inherently sequential and do not in their standard formulation allow for parallelization in the time domain. In this paper, we present a set of parallel formulas that replace the existing sequential ones in order to achieve lower time (span) complexity. Our experimental results done with a graphics processing unit (GPU) illustrate the efficiency of the proposed methods over their sequential counterparts. Comment: Accepted to be published in IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2021 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|