arXiv 2110.090052021-10-18eess.SPcs.LG

Unsupervised Learned Kalman Filtering

ETH Zürich（苏黎世联邦理工学院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Eindhoven University of Technology（埃因霍温理工大学）；Phillips Research（飞利浦研究院）；Weizmann Institute of Science（魏茨曼科学研究学院）

Guy Revach, Nir Shlezinger, Timur Locher, Xiaoyong Ni, Ruud J. G. van Sloun, Yonina C. Eldar

备注：: 5 Pages, 5 Figures, Submitted to ICASSP 2022

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

In this paper we adapt KalmanNet, which is a recently pro-posed deep neural network (DNN)-aided system whose architecture follows the operation of the model-based Kalman filter (KF), to learn its mapping in an unsupervised manner, i.e., without requiring ground-truth states. The unsupervised adaptation is achieved by exploiting the hybrid model-based/data-driven architecture of KalmanNet, which internally predicts the next observation as the KF does. These internal features are then used to compute the loss rather than the state estimate at the output of the system. With the capability of unsupervised learning, one can use KalmanNet not only to track the hidden state, but also to adapt to variations in the state space (SS) model. We numerically demonstrate that when the noise statistics are unknown, unsupervised KalmanNet achieves a similar performance to KalmanNet with supervised learning. We also show that we can adapt a pre-trained KalmanNet to changing SS models without providing additional data thanks to the unsupervised capabilities.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Nonlinear Kalman Filtering with Reparametrization Gradients

Yahoo! Inc.（雅虎公司）；Columbia University（哥伦比亚大学）

We introduce a novel nonlinear Kalman filter that utilizes reparametrization gradients. The widely used parametric approximation is based on a jointly Gaussian assumption of the state-space model, which is in turn equivalent to minimizing an approximation to the Kullback-Leibler divergence. It is possible to obtain better approximations using the alpha divergence, but the resulting problem is substantially more complex. In this paper, we introduce an alternate formulation based on an energy function, which can be optimized instead of the alpha divergence. The optimization can be carried out us…

2023-03-08cs.LGeess.SP

Recursive KalmanNet：用于具有一致不确定性量化的状态估计的深度学习增强卡尔曼滤波

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

Exail

本文提出Recursive KalmanNet，一种结合卡尔曼滤波与循环神经网络的深度学习滤波器，通过递归Joseph公式和高斯负对数似然优化实现一致误差协方差量化，在非高斯噪声下优于传统方法。

2025-06-13cs.LGeess.SPstat.ML

KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics

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 r…

2022-03-11cs.LGeess.SPstat.ML

Exactly Decoupled Kalman Filtering for Multitarget State Estimation with Sensor Bias

The problem of multisensor multitarget state estimation in the presence of constant but unknown sensor biases is investigated. The classical approach to this problem is to augment the state vector to include the states of all the targets and the sensor biases, and then implement an augmented state Kalman filter (ASKF). In this paper, we propose a novel decoupled Kalman filtering algorithm. The decoupled Kalman filtering first processes each target in a separate branch, namely the single-target Kalman filtering branch, where the single-target states and the sensor biases are estimated. Then the…

2019-10-15eess.SP

Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Models

University of Haifa（海法大学）；ETH Zürich（苏黎世联邦理工学院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Eindhoven University of Technology（埃因霍温理工大学）；Phillips Research（飞利浦研究院）；Weizmann Institute of Science（魏茨曼科学研究所）

Providing a metric of uncertainty alongside a state estimate is often crucial when tracking a dynamical system. Classic state estimators, such as the Kalman filter (KF), provide a time-dependent uncertainty measure from knowledge of the underlying statistics, however, deep learning based tracking systems struggle to reliably characterize uncertainty. In this paper, we investigate the ability of KalmanNet, a recently proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure. By exploiting the interpretable nature of KalmanNet, we show that the error covarianc…

2022-02-09cs.LGeess.SP

基于最优传输的可微分自适应 Kalman 滤波

Differentiable Adaptive Kalman Filtering via Optimal Transport

Shanghai Research Institute for Intelligent Autonomous Systems（上海智能自主系统研究所）；Tongji University（同济大学）；School of Computer Science and Technology（计算机科学与技术学院）；Shanghai Jiaotong University（上海交通大学）；Shanghai Zhangjiang Institute of Mathematics（上海张江数学研究所）；East China Normal University（华东师范大学）

提出 OTAKNet，通过最优传输与单步预测测量似然建立联系，解决基于学习的自适应 Kalman 滤波中噪声统计漂移问题，实现无需标签的完全在线自适应。

2025-08-09cs.LGeess.SP

更多相关论文收起更多论文

平稳图信号的卡尔曼滤波

Kalman Filtering of Stationary Graph Signals

本文提出基于对称图位移的平稳图信号新定义，并证明多项式图信道传输白噪声可生成平稳图信号，同时证明针对多项式状态与观测矩阵动态系统的卡尔曼滤波能保持信号平稳性，提供比静态逆滤波和零信号策略更准确、自适应的估计。

2025-09-16eess.SP

优化还是架构：如何破解卡尔曼滤波问题

Optimization or Architecture: How to Hack Kalman Filtering

Technion（以色列理工学院）；ELTA Systems（埃尔塔系统公司）；Nvidia Research（英伟达研究院）

针对非线性滤波研究中非线性模型与未优化的标准卡尔曼滤波器对比的不合理性，提出优化卡尔曼滤波器OKF，经优化的KF可媲美神经模型，且仅需更新参数即可替换现有系统中的KF。

2023-10-01cs.LGeess.SP

离群值不敏感的卡尔曼滤波：理论与应用

Outlier-Insensitive Kalman Filtering: Theory and Applications

University of Haifa（海法大学）；ETH Zürich（苏黎世联邦理工学院）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）

针对含噪观测中离群值导致线性卡尔曼滤波性能下降的问题，提出一种无参数算法，通过将离群值建模为未知方差正态过程并结合期望最大化或交替最大化进行在线估计，仅需简短迭代即可有效减轻离群值影响，鲁棒性强。

2024-08-25cs.LGeess.SP

Numerical Gaussian process Kalman filtering

KU Leuven（荷语鲁汶大学）

In this manuscript we introduce numerical Gaussian process Kalman filtering (GPKF). Numerical Gaussian processes have recently been developed to simulate spatiotemporal models. The contribution of this paper is to embed numerical Gaussian processes into the recursive Kalman filter equations. This embedding enables us to do Kalman filtering on infinite-dimensional systems using Gaussian processes. This is possible because i) we are obtaining a linear model from numerical Gaussian processes, and ii) the states of this model are by definition Gaussian distributed random variables. Convenient prop…

2020-05-11cs.LGeess.SPstat.CO

Kalman Filtering With Censored Measurements

This paper concerns Kalman filtering when the measurements of the process are censored. The censored measurements are addressed by the Tobit model of Type I and are one-dimensional with two censoring limits, while the (hidden) state vectors are multidimensional. For this model, Bayesian estimates for the state vectors are provided through a recursive algorithm of Kalman filtering type. Experiments are presented to illustrate the effectiveness and applicability of the algorithm. The experiments show that the proposed method outperforms other filtering methodologies in minimizing the computation…

2020-02-20eess.SPstat.ME

GSP-KalmanNet：通过神经辅助卡尔曼滤波跟踪图信号

GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filtering

Ben-Gurion University of the Negev（内盖夫本-古里安大学）

本文提出GSP-KalmanNet，将图信号处理与深度学习结合，通过图频域滤波和可学习卡尔曼增益实现高维图信号跟踪，在精度、速度及模型失配鲁棒性上优于现有基准。

2023-11-28cs.AIcs.LGeess.SP

面向未知动力学的神经卡尔曼滤波：基于Koopman主干的任务感知学习

Neural Kalman Filtering for Unknown Dynamics: Task-Aware Learning with a Koopman Backbone

Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；Yonsei University（延世大学）；Ben-Gurion University of the Negev（内盖夫本-古里安大学）；Weizmann Institute of Science（魏茨曼科学研究所）；Northeastern University（东北大学）

针对未知动力学下的卡尔曼滤波问题，提出基于Koopman算子的任务感知神经框架，通过双头架构联合学习线性替代与增益，实现高精度跟踪。

2026-09-22eess.SP

Observation of Periodic Systems: Bridge Centralized Kalman Filtering and Consensus-Based Distributed Filtering

Compared with linear time invariant systems, linear periodic system can describe the periodic processes arising from nature and engineering more precisely. However, the time-varying system parameters increase the difficulty of the research on periodic system, such as stabilization and observation. This paper aims to consider the observation problem of periodic systems by bridging two fundamental filtering algorithms for periodic systems with a sensor network: consensus-on-measurement-based distributed filtering (CMDF) and centralized Kalman filtering (CKF). Firstly, one mild convergence condit…

2023-03-15eess.SP

Some New Results on l1-Minimizing Nullspace Kalman Filtering for Remote Sensing Applications

This paper describes some new results on recursive l_1-minimizing by Kalman filtering. We consider the l_1-norm as an explicit constraint, formulated as a nonlinear observation of the state to be estimated. Interpretiing a sparse vector to be estimated as a state which is observed from erroneous (undersampled) measurements we can address time- and space-variant sparsity, any kind of a priori information and also easily address nonstationary error influences in the measurements available. Inherently in our approach we move slightly away from the classical RIP-based approaches to a more intuitiv…

2018-08-16eess.SP

CKFNet：神经网络辅助的容积卡尔曼滤波

CKFNet: Neural Network Aided Cubature Kalman filtering

针对容积卡尔曼滤波因模型不匹配导致性能下降的问题，提出混合架构CKFNet，在预测阶段嵌入RNN以适应不确定性并减少误差传播，同时保持可解释性，实验证明其准确性与鲁棒性优于现有方法。

2025-08-13eess.SP

由递推最小二乘遗忘算法发展而来的自适应卡尔曼滤波

Adaptive Kalman Filtering Developed from Recursive Least Squares Forgetting Algorithms

本研究提出KFLS代价函数并证明RLS扩展是卡尔曼滤波特例，据此结合二者提出一类自适应卡尔曼滤波，数值算例验证其对含间歇性未建模碰撞的质量-弹簧-阻尼器系统状态估计更优，可为非经典扰动系统提供增益。

2024-04-16cs.SYeess.SPeess.SY

[Re] 面向非线性和非高斯观测模型贝叶斯滤波的判别式卡尔曼滤波器

[Re] The Discriminative Kalman Filter for Bayesian Filtering with Nonlinear and Non-Gaussian Observation Models

Rice University（莱斯大学）

本研究复现了Burkhart等人2020年提出的判别式卡尔曼滤波器的神经科学核心结果，提供了该MATLAB算法的开源Python替代版本，通过多随机种子和未用试次进一步验证了滤波器有效性。

2024-01-24cs.LGcs.ROeess.SP

Optimal Sensing Precision in Ensemble and Unscented Kalman Filtering

We consider the problem of selecting an optimal set of sensor precisions to estimate the states of a non-linear dynamical system using an Ensemble Kalman filter and an Unscented Kalman filter, which uses random and deterministic ensembles respectively. Specifically, the goal is to choose at run-time, a sparse set of sensor precisions for active-sensing that satisfies certain constraints on the estimated state covariance. In this paper, we show that this sensor precision selection problem is a semidefinite programming problem when we use l1 norm over precision vector as the surrogate measure to…

2020-03-12eess.SPmath.OC