Kalmannet: Data-Driven Kalman Filtering


METADATA ONLY
Loading...

Date

2021

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

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 state-space 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.

Publication status

published

Editor

Book title

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Journal / series

Volume

Pages / Article No.

3905 - 3909

Publisher

IEEE

Event

2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Kalman filter; deep learning; model-based

Organisational unit

03568 - Loeliger, Hans-Andrea / Loeliger, Hans-Andrea check_circle

Notes

Funding

Related publications and datasets