KalmanNet: Neural Network Aided Kalman Filtering for Partially Known Dynamics

Abstract

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.

Accepted for publication in IEEE Transactions on Signal Processing - TSP

References in corpus (8)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
• Cooperative Parallel Particle Filters for online model selection and applications to Urban Mobility
• A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
• Recurrent Kalman Networks: Factorized Inference in High-Dimensional Deep Feature Spaces
• State Space LSTM Models with Particle MCMC Inference
• Expectation Maximization as Message Passing - Part I: Principles and Gaussian Messages
• Particle Learning and Smoothing

Cited by in corpus (18)

• DANSE: Data-driven Non-linear State Estimation of Model-free Process in Unsupervised Learning Setup
• Deep Learning-Based Robust Multi-Object Tracking via Fusion of mmWave Radar and Camera Sensors
• Near-Field Localization and Sensing with Large-Aperture Arrays: From Signal Modeling to Processing
• Neural Kalman Filters for Acoustic Echo Cancellation
• CGNSDE: Conditional Gaussian Neural Stochastic Differential Equation for Modeling Complex Systems and Data Assimilation
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• Multi-Sensor Fusion for Quadruped Robot State Estimation using Invariant Filtering and Smoothing
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
• Energy efficiency analysis of Spiking Neural Networks for space applications
• Sparse Graphical Linear Dynamical Systems
• From Target Tracking to Targeting Track -- Part II: Regularized Polynomial Trajectory Optimization
• Legged Robot State Estimation Using Invariant Neural-Augmented Kalman Filter with a Neural Compensator
• Data-Driven Discovery of Interpretable Kalman Filter Variants through Large Language Models and Genetic Programming
• DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation
• InEKFormer: A Hybrid State Estimator for Humanoid Robots
• Nonparametric Filtering, Estimation and Classification using Neural Jump ODEs
• Kalman Filter Aided Federated Koopman Learning
• Q-Net: Queue Length Estimation via Kalman-based Neural Networks