EKFNet: Learning System Noise Statistics from Measurement Data
Liang Xu, Ruixin Niu
Abstract
In this paper, to reduce the time and manpower spent on fine-tuning an extended Kalman filter (EKF), we propose a new learning framework, EKFNet, for automatically estimating the best process and measurement noise covariance pair from the real measurement data. The EKFNet is trained by using backpropagation through time (BPTT). The proposed method can choose among several optimization criteria, such as maximizing the likelihood, minimizing the measurement residual error, or minimizing the posterior state estimation error. We illustrate the proposed method's performance using real GPS data, which outperforms existing methods and a manually tuned EKF.
Topics & Concepts
Computer scienceKalman filterNoise (video)CovarianceExtended Kalman filterNoise measurementResidualGlobal Positioning SystemObservational errorProcess (computing)BackpropagationArtificial intelligenceMachine learningData miningAlgorithmArtificial neural networkStatisticsNoise reductionMathematicsImage (mathematics)Operating systemTelecommunicationsTarget Tracking and Data Fusion in Sensor NetworksInertial Sensor and NavigationTime Series Analysis and Forecasting