mlsanityData to 7 Oct 2026

KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics

arXiv 2107.10043 ↗First posted 21 Jul 2021eess.SP cs.LG stat.MLcited by 128

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 128 papers in the map (data through 7 Oct 2026). Builds on 26 of its 82 references that are in the map. First posted on arXiv 21 Jul 2021.

Builds on

26 of 82 references.

References · 26

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2013Auto-Encoding Variational Bayescited by 3,980
  4. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  5. 2016Variational Inference: A Review for Statisticianscited by 1,466
  6. 2017Gate-Variants of Gated Recurrent Unit (GRU) Neural Networkscited by 239
  7. 2016Structured Inference Networks for Nonlinear State Space Modelscited by 182
  8. 2015Deep Kalman Filterscited by 163
  9. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 154
  10. 2020Model-Based Deep Learningcited by 136
  11. 2017A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learningcited by 107
  12. 2017Variational Sequential Monte Carlocited by 93
14 more
  1. 2019Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spacescited by 64
  2. 2016Backprop KF: Learning Discriminative Deterministic State Estimatorscited by 47
  3. 2020KFNet: Learning Temporal Camera Relocalization using Kalman Filteringcited by 43
  4. 2017Long Short-Term Memory Kalman Filters:Recurrent Neural Estimators for Pose Regularizationcited by 36
  5. 2019Combining Generative and Discriminative Models for Hybrid Inferencecited by 34
  6. 2015Black box variational inference for state space modelscited by 31
  7. 2019ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detectioncited by 25
  8. 2020DeepSIC: Deep Soft Interference Cancellation for Multiuser MIMO Detectioncited by 23
  9. 2017State Space LSTM Models with Particle MCMC Inferencecited by 11
  10. 2019Fitting a Kalman Smoother to Datacited by 9
  11. 2020Learned Factor Graphs for Inference from Stationary Time Sequencescited by 8
  12. 2015Robust Kalman Filtering under Model Perturbationscited by 4
  13. 2015On the Robustness of the Bayes and Wiener Estimators under Model Uncertaintycited by 3
  14. 2021Learning the tuned liquid damper dynamics by means of a robust EKFcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 3; 2022: 9; 2023: 15; 2024: 25; 2025: 40; 2026: 36.

128 papers.

Sort:

By area:

  1. 2023Machine learning with data assimilation and uncertainty quantification for dynamical systems: a reviewcited by 74
  2. 2022Model-Based Deep Learning: On the Intersection of Deep Learning and Optimizationcited by 50
  3. 2024Deep Generative Data Assimilation in Multimodal Settingcited by 28
  4. 2022Theoretical Perspectives on Deep Learning Methods in Inverse Problemscited by 22
  5. 2023DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setupcited by 19
  6. 2023Forking Uncertainties: Reliable Prediction and Model Predictive Control with Sequence Models via Conformal Risk Controlcited by 19
  7. 2021Unsupervised Learned Kalman Filteringcited by 17
  8. 2023Focus Your Attention (with Adaptive IIR Filters)cited by 12
  9. 2024KFD-NeRF: Rethinking Dynamic NeRF with Kalman Filtercited by 11
  10. 2023GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filteringcited by 10
  11. 2024Normalizing Flow-based Differentiable Particle Filterscited by 10
  12. 2023Optimization or Architecture: How to Hack Kalman Filteringcited by 8
38 more
  1. 2024Beyond Kalman Filters: Deep Learning-Based Filters for Improved Object Trackingcited by 8
  2. 2024CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilationcited by 7
  3. 2021Uncertainty in Data-Driven Kalman Filtering for Partially Known State-Space Modelscited by 6
  4. 2023Discussing the Spectrum of Physics-Enhanced Machine Learning; a Survey on Structural Mechanics Applicationscited by 6
  5. 2024CGNSDE: Conditional Gaussian Neural Stochastic Differential Equation for Modeling Complex Systems and Data Assimilationcited by 6
  6. 2024Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videoscited by 6
  7. 2025Recursive KalmanNet: Deep Learning-Augmented Kalman Filtering for State Estimation with Consistent Uncertainty Quantificationcited by 6
  8. 2025Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Networkcited by 6
  9. 2022Hybrid Neural Network Augmented Physics-based Models for Nonlinear Filteringcited by 5
  10. 2023Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inferencecited by 5
  11. 2024Deep Bayesian Filter for Bayes-faithful Data Assimilationcited by 5
  12. 2024Deep Learning-Based Robust Multi-Object Tracking via Fusion of mmWave Radar and Camera Sensorscited by 5
  13. 2023Towards Flexibility and Interpretability of Gaussian Process State-Space Modelcited by 4
  14. 2023Prediction and Interpretation of Vehicle Trajectories in the Graph Spectral Domaincited by 4
  15. 2024Learning Semilinear Neural Operators : A Unified Recursive Framework For Prediction And Data Assimilationcited by 4
  16. 2024A Survey of Machine Learning Techniques for Improving Global Navigation Satellite Systemscited by 4
  17. 2025Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarioscited by 4
  18. 2025Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Artcited by 4
  19. 2025Structured Kolmogorov-Arnold Neural ODEs for Interpretable Learning and Symbolic Discovery of Nonlinear Dynamicscited by 4
  20. 2021Self-Supervised Inference in State-Space Modelscited by 3
  21. 2024KODA: A Data-Driven Recursive Model for Time Series Forecasting and Data Assimilation using Koopman Operatorscited by 3
  22. 2024Online Control-Informed Learningcited by 3
  23. 2024AI-Aided Kalman Filterscited by 3
  24. 2025HybridTrack: A Hybrid Approach for Robust Multi-Object Trackingcited by 3
  25. 2025Flow-based Bayesian filtering for high-dimensional nonlinear stochastic dynamical systemscited by 3
  26. 2025Cellular Traffic Prediction via Deep State Space Models with Attention Mechanismcited by 3
  27. 2022Neural Augmented Kalman Filtering with Bollinger Bands for Pairs Tradingcited by 2
  28. 2023KARNet: Kalman Filter Augmented Recurrent Neural Network for Learning World Models in Autonomous Driving Taskscited by 2
  29. 2024Hybrid Data-Driven SSM for Interpretable and Label-Free mmWave Channel Predictioncited by 2
  30. 2025Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systemscited by 2
  31. 2025RL-DAUNCE: Reinforcement Learning-Driven Data Assimilation with Uncertainty-Aware Constrained Ensemblescited by 2
  32. 2025GKNet: Graph Kalman Filtering and Model Inference via Model-based Deep Learningcited by 2
  33. 2026Amortized Filtering and Smoothing with Conditional Normalizing Flowscited by 2
  34. 2026One Operator for Many Densities: Amortized Approximation of Conditioning by Neural Operatorscited by 2
  35. 2022Continuous Forecasting via Neural Eigen Decompositioncited by 1
  36. 2022Outlier-Insensitive Kalman Filtering Using NUV Priorscited by 1
  37. 2023Mobility-Induced Graph Learning for WiFi Positioningcited by 1
  38. 2023Motion Informed Needle Segmentation in Ultrasound Imagescited by 1

50 most cited of 128 All 128 (JSON)