KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics

By Guy Revach, Nir Shlezinger, Xiaoyong Ni, Adrià López Escoriza, Ruud J. G. van Sloun, Yonina C. Eldar. IEEE Transactions on Signal Processing, 2021

576 citations recorded by the source corpus.

State estimation of dynamical systems in real-time is a fundamental task in signal processing. For systems that are well-represented by a fully known linear Gaussian state space (SS) model, the celebrated Kalman filter (KF) is a low complexity optimal solution. However, both linearity of the underlying SS model and accurate knowledge of it are often not encountered in practice. Here, we present KalmanNet, a real-time state estimator that learns from data to carry out Kalman filtering under non-linear dynamics with partial information. By incorporating the structural SS model with a dedicated recurrent neural network module in the flow of the KF, we retain data efficiency and interpretability of the classic algorithm while implicitly learning complex dynamics from data. We demonstrate numerically that KalmanNet overcomes non-linearities and model mismatch, outperforming classic filtering methods operating with both mismatched and accurate domain knowledge.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/29c62e80e1ec86a26f96cee8b8fe9124beeb8f2c

Citations in the corpus

• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, unknown): “3) We enlarge and relabeled two river ice datasets, the NWPU_YRCC_EX and NWPU_YRCC2.”