RTSNet: Learning to Smooth in Partially Known State-Space Models
- 17 November 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 71 (1053587X) , 4441-4456
Abstract
The smoothing task is core to many signal-processing applications. A widely popular smoother is the Rauch-Tung-Striebel (RTS) algorithm, which achieves minimal mean-squared error recovery with low complexity for linear Gaussian state-space (SS) models, yet is limited in systems that are only partially known, as well as nonlinear and non-Gaussian. In this work, we propose RTSNet, a highly efficient model-based and data-driven smoothing algorithm suitable for partially known SS models. RTSNet integrates dedicated trainable models into the flow of the classical RTS smoother, while iteratively refining its sequence estimate via deep unfolding methodology. As a result, RTSNet learns from data to reliably smooth when operating under model mismatch and nonlinearities while retaining the efficiency and interpretability of the traditional RTS smoothing algorithm. Our empirical study demonstrates that RTSNet overcomes nonlinearities and model mismatch, outperforming classic smoothers operating with both mismatched and accurate domain knowledge. Moreover, while RTSNet is based on compact neural networks, which leads to faster training and inference times, it demonstrates improved performance over previously proposed deep smoothers in nonlinear settings.Keywords
Funding Information
- IEEE International Conference on Acoustics, Speech, and Signal Processing
This publication has 47 references indexed in Scilit:
- Optimization Viewpoint on Kalman Smoothing with Applications to Robust and Sparse Estimation2013
- Vision meets robotics: The KITTI datasetThe International Journal of Robotics Research, 2013
- A Fresh Look at the Kalman FilterSIAM Review, 2012
- An $\ell _{1}$-Laplace Robust Kalman SmootherIEEE Transactions on Automatic Control, 2011
- Applying the unscented Kalman filter for nonlinear state estimationJournal of Process Control, 2008
- Monte Carlo Smoothing for Nonlinear Time SeriesJournal of the American Statistical Association, 2004
- Novel approach to nonlinear/non-Gaussian Bayesian state estimationIEE Proceedings F Radar and Signal Processing, 1993
- Fixed interval smoothing with discrete measurementsInternational Journal of Control, 1973
- Maximum likelihood estimates of linear dynamic systemsAIAA Journal, 1965
- A New Approach to Linear Filtering and Prediction ProblemsJournal of Basic Engineering, 1960