On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem
The Kalman filter requires knowledge of the noise statistics; however, the noise covariances are generally unknown. Although this problem has a long history, reliable algorithms for their estimation are scant, and necessary and sufficient conditions for identifiability of the covariances are in disp...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9044358/ |
| _version_ | 1819159299118596096 |
|---|---|
| author | Lingyi Zhang David Sidoti Adam Bienkowski Krishna R. Pattipati Yaakov Bar-Shalom David L. Kleinman |
| author_facet | Lingyi Zhang David Sidoti Adam Bienkowski Krishna R. Pattipati Yaakov Bar-Shalom David L. Kleinman |
| author_sort | Lingyi Zhang |
| collection | DOAJ |
| description | The Kalman filter requires knowledge of the noise statistics; however, the noise covariances are generally unknown. Although this problem has a long history, reliable algorithms for their estimation are scant, and necessary and sufficient conditions for identifiability of the covariances are in dispute. We address both of these issues in this paper. We first present the necessary and sufficient condition for unknown noise covariance estimation; these conditions are related to the rank of a matrix involving the auto and cross-covariances of a weighted sum of innovations, where the weights are the coefficients of the minimal polynomial of the closed-loop system transition matrix of a stable, but not necessarily optimal, Kalman filter. We present an optimization criterion and a novel six-step approach based on a successive approximation, coupled with a gradient algorithm with adaptive step sizes, to estimate the steady-state Kalman filter gain, the unknown noise covariance matrices, as well as the state prediction (and updated) error covariance matrix. Our approach enforces the structural assumptions on unknown noise covariances and ensures symmetry and positive definiteness of the estimated covariance matrices. We provide several approaches to estimate the unknown measurement noise covariance $R$ via post-fit residuals, an approach not yet exploited in the literature. The validation of the proposed method on five different test cases from the literature demonstrates that the proposed method significantly outperforms previous state-of-the-art methods. It also offers a number of novel machine learning motivated approaches, such as sequential (one sample at a time) and mini-batch-based methods, to speed up the computations. |
| first_indexed | 2024-12-22T16:38:21Z |
| format | Article |
| id | doaj.art-eb4a58f788ec438f9895e0541d18f839 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-22T16:38:21Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-eb4a58f788ec438f9895e0541d18f8392022-12-21T18:19:54ZengIEEEIEEE Access2169-35362020-01-018593625938810.1109/ACCESS.2020.29824079044358On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old ProblemLingyi Zhang0https://orcid.org/0000-0003-4556-6668David Sidoti1Adam Bienkowski2Krishna R. Pattipati3https://orcid.org/0000-0002-0565-181XYaakov Bar-Shalom4David L. Kleinman5Department of Electrical and Computer Engineering, University of Connecticut, Storrs, CT, USAMarine Meteorology Division, U.S. Naval Research Laboratory, Monterey, CA, USADepartment of Electrical and Computer Engineering, University of Connecticut, Storrs, CT, USADepartment of Electrical and Computer Engineering, University of Connecticut, Storrs, CT, USADepartment of Electrical and Computer Engineering, University of Connecticut, Storrs, CT, USADepartment of Electrical and Computer Engineering, University of Connecticut, Storrs, CT, USAThe Kalman filter requires knowledge of the noise statistics; however, the noise covariances are generally unknown. Although this problem has a long history, reliable algorithms for their estimation are scant, and necessary and sufficient conditions for identifiability of the covariances are in dispute. We address both of these issues in this paper. We first present the necessary and sufficient condition for unknown noise covariance estimation; these conditions are related to the rank of a matrix involving the auto and cross-covariances of a weighted sum of innovations, where the weights are the coefficients of the minimal polynomial of the closed-loop system transition matrix of a stable, but not necessarily optimal, Kalman filter. We present an optimization criterion and a novel six-step approach based on a successive approximation, coupled with a gradient algorithm with adaptive step sizes, to estimate the steady-state Kalman filter gain, the unknown noise covariance matrices, as well as the state prediction (and updated) error covariance matrix. Our approach enforces the structural assumptions on unknown noise covariances and ensures symmetry and positive definiteness of the estimated covariance matrices. We provide several approaches to estimate the unknown measurement noise covariance $R$ via post-fit residuals, an approach not yet exploited in the literature. The validation of the proposed method on five different test cases from the literature demonstrates that the proposed method significantly outperforms previous state-of-the-art methods. It also offers a number of novel machine learning motivated approaches, such as sequential (one sample at a time) and mini-batch-based methods, to speed up the computations.https://ieeexplore.ieee.org/document/9044358/Adaptive filteringKalman filterminimal polynomialnoise covariance estimationadaptive gradient descent |
| spellingShingle | Lingyi Zhang David Sidoti Adam Bienkowski Krishna R. Pattipati Yaakov Bar-Shalom David L. Kleinman On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem IEEE Access Adaptive filtering Kalman filter minimal polynomial noise covariance estimation adaptive gradient descent |
| title | On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem |
| title_full | On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem |
| title_fullStr | On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem |
| title_full_unstemmed | On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem |
| title_short | On the Identification of Noise Covariances and Adaptive Kalman Filtering: A New Look at a 50 Year-Old Problem |
| title_sort | on the identification of noise covariances and adaptive kalman filtering a new look at a 50 year old problem |
| topic | Adaptive filtering Kalman filter minimal polynomial noise covariance estimation adaptive gradient descent |
| url | https://ieeexplore.ieee.org/document/9044358/ |
| work_keys_str_mv | AT lingyizhang ontheidentificationofnoisecovariancesandadaptivekalmanfilteringanewlookata50yearoldproblem AT davidsidoti ontheidentificationofnoisecovariancesandadaptivekalmanfilteringanewlookata50yearoldproblem AT adambienkowski ontheidentificationofnoisecovariancesandadaptivekalmanfilteringanewlookata50yearoldproblem AT krishnarpattipati ontheidentificationofnoisecovariancesandadaptivekalmanfilteringanewlookata50yearoldproblem AT yaakovbarshalom ontheidentificationofnoisecovariancesandadaptivekalmanfilteringanewlookata50yearoldproblem AT davidlkleinman ontheidentificationofnoisecovariancesandadaptivekalmanfilteringanewlookata50yearoldproblem |