KalmanNet: Neural Network Aided Kalman Filtering for Partially Known
Dynamics
- URL: http://arxiv.org/abs/2107.10043v1
- Date: Wed, 21 Jul 2021 12:26:46 GMT
- Title: KalmanNet: Neural Network Aided Kalman Filtering for Partially Known
Dynamics
- Authors: Guy Revach, Nir Shlezinger, Xiaoyong Ni, Adria Lopez Escoriza, Ruud J.
G. van Sloun, and Yonina C. Eldar
- Abstract summary: We present KalmanNet, a real-time state estimator that learns from data to carry out Kalman filtering under non-linear dynamics.
We numerically demonstrate that KalmanNet overcomes nonlinearities and model mismatch, outperforming classic filtering methods.
- Score: 84.18625250574853
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Real-time state estimation of dynamical systems is a fundamental task in
signal processing and control. 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 numerically demonstrate that KalmanNet
overcomes nonlinearities and model mismatch, outperforming classic filtering
methods operating with both mismatched and accurate domain knowledge.
Related papers
- GSP-KalmanNet: Tracking Graph Signals via Neural-Aided Kalman Filtering [23.19392802641989]
We study the tracking of graph signals using a hybrid model-based/data-driven approach.
We develop the GSP-KalmanNet, which tracks the hidden graphical states from the graphical measurements.
The proposed GSP-KalmanNet achieves enhanced accuracy and run time performance as well as improved robustness to model misspecifications.
arXiv Detail & Related papers (2023-11-28T08:43:10Z) - Kalman Filter for Online Classification of Non-Stationary Data [101.26838049872651]
In Online Continual Learning (OCL) a learning system receives a stream of data and sequentially performs prediction and training steps.
We introduce a probabilistic Bayesian online learning model by using a neural representation and a state space model over the linear predictor weights.
In experiments in multi-class classification we demonstrate the predictive ability of the model and its flexibility to capture non-stationarity.
arXiv Detail & Related papers (2023-06-14T11:41:42Z) - Building a Fuel Moisture Model for the Coupled Fire-Atmosphere Model
WRF-SFIRE from Data: From Kalman Filters to Recurrent Neural Networks [0.0]
Current fuel moisture content (FMC) subsystems in WRF-SFIRE and its workflow system WRFx use a time-lag differential equation model.
We observe that the data flow in a system consisting of a model and the Kalman filter can be interpreted to be the same as the data flow in a recurrent neural network (RNN)
Because standard AI approaches did not converge to reasonable solutions, we pre-train the RNN with special initial weights devised to turn it into a numerical solver of the differential equation.
arXiv Detail & Related papers (2023-01-13T07:56:01Z) - Split-KalmanNet: A Robust Model-Based Deep Learning Approach for SLAM [101.32324781612172]
Simultaneous localization and mapping (SLAM) is a method that constructs a map of an unknown environment and localizes the position of a moving agent on the map simultaneously.
Extended Kalman filter (EKF) has been widely adopted as a low complexity solution for online SLAM.
We present a robust EKF algorithm using the power of deep learning for online SLAM, referred to as Split-KalmanNet.
arXiv Detail & Related papers (2022-10-18T07:10:38Z) - Recurrent Neural Network Training with Convex Loss and Regularization
Functions by Extended Kalman Filtering [0.20305676256390928]
We show that the learning method outperforms gradient descent in a nonlinear system identification benchmark.
We also explore the use of the algorithm in data-driven nonlinear model predictive control and its relation with disturbance models for offset-free tracking.
arXiv Detail & Related papers (2021-11-04T07:49:15Z) - Unsupervised Learned Kalman Filtering [84.18625250574853]
unsupervised adaptation is achieved by exploiting the hybrid model-based/data-driven architecture of KalmanNet.
We numerically demonstrate that when the noise statistics are unknown, unsupervised KalmanNet achieves a similar performance to KalmanNet with supervised learning.
arXiv Detail & Related papers (2021-10-18T04:04:09Z) - Uncertainty in Data-Driven Kalman Filtering for Partially Known
State-Space Models [84.18625250574853]
We investigate the ability of KalmanNet, a proposed hybrid model-based deep state tracking algorithm, to estimate an uncertainty measure.
We show that the error covariance matrix can be computed based on its internal features, as an uncertainty measure.
We demonstrate that when the system dynamics are known, KalmanNet-which learns its mapping from data without access to the statistics-provides uncertainty similar to that provided by the Kalman filter.
arXiv Detail & Related papers (2021-10-10T08:52:18Z) - Neural Kalman Filtering [62.997667081978825]
We show that a gradient-descent approximation to the Kalman filter requires only local computations with variance weighted prediction errors.
We also show that it is possible under the same scheme to adaptively learn the dynamics model with a learning rule that corresponds directly to Hebbian plasticity.
arXiv Detail & Related papers (2021-02-19T16:43:15Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.