SPLGMLJun 13, 2025

Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantification

arXiv:2506.11639v16 citationsh-index: 2Has CodeEUSIPCO
Originality Incremental advance
AI Analysis

This addresses state estimation for systems with non-Gaussian noise, offering improved accuracy and uncertainty quantification, but it is incremental as it builds on existing Kalman filter and deep learning approaches.

The paper tackled state estimation in stochastic dynamical systems with non-Gaussian noise by introducing Recursive KalmanNet, a deep learning-augmented Kalman filter, which outperformed conventional and existing deep learning methods in experiments.

State estimation in stochastic dynamical systems with noisy measurements is a challenge. While the Kalman filter is optimal for linear systems with independent Gaussian white noise, real-world conditions often deviate from these assumptions, prompting the rise of data-driven filtering techniques. This paper introduces Recursive KalmanNet, a Kalman-filter-informed recurrent neural network designed for accurate state estimation with consistent error covariance quantification. Our approach propagates error covariance using the recursive Joseph's formula and optimizes the Gaussian negative log-likelihood. Experiments with non-Gaussian measurement white noise demonstrate that our model outperforms both the conventional Kalman filter and an existing state-of-the-art deep learning based estimator.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes