On the identification of variances and adaptive Kalman filtering

1970/04/01 by R. Mehra, R.К. Mehra · 1,389 citations
Computer Science · Decision Sciences · Mathematics · #Algorithm #Artificial intelligence #Computer science #Distributed Sensor Networks and Detection Algorithms #Kalman filter #Mathematics #Scientific Measurement and Uncertainty Evaluation #Target Tracking and Data Fusion in Sensor Networks

paper · doi:10.1109/tac.1970.1099422

published in IEEE Transactions on Automatic Control 15(2), 175-184 (Institute of Electrical and Electronics Engineers)

openalex publication_date 1970/04/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

A Kalman filter requires an exact knowledge of the process noise covariance matrixQand the measurement noise covariance matrixR. Here we consider the case in which the true values ofQandRare unknown. The system is assumed to be constant, and the random inputs are stationary. First, a correlation test is given which checks whether a particular Kalman filter is working optimally or not. If the filter is suboptimal, a technique is given to obtain asymptotically normal, unbiased, and consistent estimates ofQandR. This technique works only for the case in which the form ofQis known and the number of unknown elements inQis less thann × rwherenis the dimension of the state vector andris the dimension of the measurement vector. For other cases, the optimal steady-state gain Kopis obtained directly by an iterative procedure without identifyingQ. As a corollary, it is shown that the steady-state optimal Kalman filter gain Kopdepends only onn × rlinear functionals ofQ. The results are first derived for discrete systems. They are then extended to continuous systems. A numerical example is given to show the usefulness of the approach.

Cited by

• A Review of Innovation-Based Methods to Jointly Estimate Model and Observation Error Covariance Matrices in Ensemble Data Assimilation
• Selection-Induced Contraction of Innovation Statistics in Gated Kalman Filters
• Distributionally Robust Kalman Filter
• Distributed Noise Covariance Matrices Estimation in Sensor Networks
• Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning
• Convolution-based reformulation and Kalman-filter identification of short-time kernel operators for seat-human vibration modeling
• Correlation-Aware Dual-View Pose and Velocity Estimation for Dynamic Robotic Manipulation
• Trajectory Based Observer Design: A Framework for Lightweight Sensor Fusion
• Introduction to the Kalman Filter and Tuning its Statistics for Near Optimal Estimates and Cramer Rao Bound
• A simple and robust method for noise variance estimation for time-varying signals
• Riemannian Trust-Region based Adaptive Kalman filter with unknown noise Covariance matrices
• An Autocovariance Least-Squares-Based Data-Driven Kalman Filter for Unknown Systems
• Adaptive Inference through Bayesian and Inverse Bayesian Inference with Symmetry-Bias in Nonstationary Environments
• On the Movements of the North Atlantic Subpolar Front in the Preinstrumental Past*
• A new look at the statistical model identification
• Adaptive error covariances estimation methods for ensemble Kalman filters
• The Adaptive Tobit Kalman Filter: Tracking Position with Censored Measurements in the IoT
• Bayesian Inference for Linear Dynamic Models With Dirichlet Process Mixtures
• Robust fundamental frequency estimation in sustained vowels: detailed algorithmic comparisons and information fusion with adaptive Kalman filtering. [europepmc]
• Linear theory for filtering nonlinear multiscale systems with model error. [europepmc]
• Fuzzy Neural Network-Based Interacting Multiple Model for Multi-Node Target Tracking Algorithm. [europepmc]
• A Novel Adaptively-Robust Strategy Based on the Mahalanobis Distance for GPS/INS Integrated Navigation Systems. [europepmc]
• A Modified Extended Kalman Filter for a Two-Antenna GPS/INS Vehicular Navigation System. [europepmc]
• Estimating snow mass in North America through assimilation of AMSR-E brightness temperature observations using the Catchment land surface model and support vector machines. [europepmc]
• Measurement Noise Recommendation for Efficient Kalman Filtering over a Large Amount of Sensor Data. [europepmc]
• A Novel Online Approach for Drift Covariance Estimation of Odometries Used in Intelligent Vehicle Localization. [europepmc]
• A Neuron-Based Kalman Filter with Nonlinear Autoregressive Model. [europepmc]
• Robust Outlier-Adaptive Filtering for Vision-Aided Inertial Navigation. [europepmc]
• An FPGA Based Tracking Implementation for Parkinson's Patients. [europepmc]
• Estimation of a Human-Maneuvered Target Incorporating Human Intention. [europepmc]
• Novel Process Noise Model for GNSS Kalman Filter Based on Sensitivity Analysis of Covariance with Poor Satellite Geometry. [europepmc]
• Multi-Agent Reinforcement Learning via Adaptive Kalman Temporal Difference and Successor Representation. [europepmc]
• A CW-CNN regression model-based real-time system for virtual hand control. [europepmc]
• SmartFPS: Neural network based wireless-inertial fusion positioning system. [europepmc]
• Pedestrian Localization with Stride-Wise Error Estimation and Compensation by Fusion of UWB and IMU Data. [europepmc]
• A Novel Approach for Kalman Filter Tuning for Direct and Indirect Inertial Navigation System/Global Navigation Satellite System Integration. [europepmc]
• Real-Time Turning Movement, Queue Length, and Traffic Density Estimation and Prediction Using Vehicle Trajectory and Stationary Sensor Data. [europepmc]
• High-Precision Laser Time-Frequency Synchronization in Space Based on an Improved Kalman Filtering Method. [europepmc]

Related

• Perspective Chapter: Insights from Kalman Filtering with Correlated Noises Recursive Least-Square Algorithm for State and Parameter Estimation
• A Normal Variance Mixture Model for Robust Kalman Filtering
• Introduction to the Kalman Filter and Tuning its Statistics for Near Optimal Estimates and Cramer Rao Bound
• Bridging a gap in Kalman filtering output estimation with correlated noises or with direct feed-through from process noise into measurements
• Outlier-Insensitive Kalman Filtering Using NUV Priors