Samenvatting
The Kalman filter (KF) is a celebrated signal processing algorithm, implementing optimal state estimation of dynamical systems that are well represented by a linear Gaussian statespace model. The KF is model-based, and therefore relies on full and accurate knowledge of the underlying model. We present KalmanNet, a hybrid data-driven/model-based filter that does not require full knowledge of the underlying model parameters. KalmanNet is inspired by the classical KF flow and implemented by integrating a dedicated and compact neural network for the Kalman gain computation. We present an offline training method, and numerically illustrate that KalmanNet can achieve optimal performance without full knowledge of the model parameters. We demonstrate that when facing inaccurate parameters KalmanNet learns to achieve notably improved performance compared to KF.
| Originele taal-2 | Engels |
|---|---|
| Titel | ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Uitgeverij | Institute of Electrical and Electronics Engineers |
| Pagina's | 3905-3909 |
| Aantal pagina's | 5 |
| ISBN van elektronische versie | 978-1-7281-7605-5 |
| DOI's | |
| Status | Gepubliceerd - 2021 |
| Evenement | 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Virtual, Toronto, Canada Duur: 6 jun. 2021 → 11 jun. 2021 https://2021.ieeeicassp.org/ |
Congres
| Congres | 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 |
|---|---|
| Verkorte titel | ICASSP 2021 |
| Land/Regio | Canada |
| Stad | Virtual, Toronto |
| Periode | 6/06/21 → 11/06/21 |
| Internet adres |
Bibliografische nota
Publisher Copyright:©2021 IEEE.
Financiering
This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant no. 646804-ERC-COG-BNYQ, and from the Israel Science Foundation under grant No. 0100101. G. Revach is with the Signal Processing Laboratory (ISI), Department of Information Technology and Electrical Engineering, ETH Zurich, Switzerland (e-mail: [email protected]). N. Shlezinger is with the School of ECE, Ben-Gurion University of the Negev, Beer Sheva, Israel (e-mail: [email protected]). R. J. G. van Sloun is with the EE Dpt., Eindhoven University of Technology, and with Phillips Research, Eindhoven, The Netherlands (e-mail: [email protected]). Y. C. Eldar is with the Faculty of Math and CS, Weizmann Institute of Science, Rehovot, Israel (e-mail: [email protected]).