Topic
Invariant extended Kalman filter
About: Invariant extended Kalman filter is a research topic. Over the lifetime, 7079 publications have been published within this topic receiving 187702 citations.
Papers published on a yearly basis
Papers
More filters
01 Oct 2007
TL;DR: The quantized Kalman filter based on the quantized observations (QKFQO) is presented, which requires that the fusion center broadcast the one-step prediction of state and innovation variances to the tasking sensor nodes.
Abstract: This paper is concerned with the estimation problem for a dynamic stochastic estimation in a sensor network. Firstly, the quantized Kalman filter based on the quantized observations (QKFQO) is presented. Approximate solutions for two optimal bandwidth scheduling problems are given, where the tradeoff between the number of quantization levels or the bandwidth constraint and the energy consumption is considered. However, for a large observed output, quantizing observations will result in large information loss under the limited bandwidth. To reduce the information loss, another quantized Kalman filter based on quantized innovations (QKFQI) is developed, which requires that the fusion center broadcast the one-step prediction of state and innovation variances to the tasking sensor nodes. Compared with QKFQO, QKFQI has better accuracy. Simulations show the effectiveness.
49 citations
21 Nov 2010
TL;DR: This study presents a maneuvering ocean vessel model based on a curvilinear motion model with the measurementsbased on a linear position model for the same purpose and proposes the Extended Kalman Filter as an adaptive filter algorithm for the estimation of position, velocity and acceleration.
Abstract: The accurate estimation and prediction of the trajectories of maneuvering vessels in ocean navigation are important tools to improve maritime safety and security. Therefore, many conventional ocean navigation systems and Vessel Traffic Management & Reporting Services are equipped with Radar facilities for this purpose. However, the accuracy of the predictions of maneuvering trajectories of vessels depends mainly on the goodness of estimation of vessel position, velocity and acceleration. Hence, this study presents a maneuvering ocean vessel model based on a curvilinear motion model with the measurements based on a linear position model for the same purpose. Furthermore, the system states and measurements models associated with a white Gaussian noise are also assumed. The Extended Kalman Filter is proposed as an adaptive filter algorithm for the estimation of position, velocity and acceleration that are used for prediction of maneuvering ocean vessel trajectory. Finally, the proposed models are implemented and successful computational results are obtained with respect to prediction of maneuvering trajectories of vessels in ocean navigation in this study. KeywordsTrajectory estimation; Trajectory prediction; Target tracking; Extended Kalman Filter; Curvilinear motion model.
49 citations
TL;DR: This work presents the wrapped Kalman filter (WKF) for tracking the azimuth of a speaker with a compact, 3-channel microphone array with a wrapped Gaussian distribution and shows that this achieves a lower mean squared error than 2-D methods.
Abstract: We present the wrapped Kalman filter (WKF) for tracking the azimuth of a speaker with a compact, 3-channel microphone array. Traditional extended and unscented filters assume that the observation is a rotating vector in \BBR2. However, the azimuth inhabits a 1-D subspace: the unit circle. We model the state variable with a wrapped Gaussian distribution and show that this achieves a lower mean squared error than 2-D methods. We demonstrate the superior tracking performance of the WKF in simulated and real reverberant environments.
49 citations
TL;DR: In this article, the authors propose a new way to introduce skewness to state-space models without losing the computational advantages of the Kalman filter operations, which comes from the extension of the multivariate normal distribution to the closed skew-normal distribution.
49 citations
TL;DR: In this article, a computational efficient attitude estimation method is proposed for the low-cost attitude and heading reference systems, where the velocity and position provided by the Global Positioning System and inertial sensors outputs are first used to construct the vector observations.
Abstract: In this paper, a computational efficient attitude estimation method is proposed for the low-cost attitude and heading reference systems. In the proposed method, the velocity and position provided by the Global Positioning System and inertial sensors outputs are first used to construct the vector observations. With the constructed vector observations, an error equations based filtering model is established using the Euler angles as the attitude parameterization. If the attitude has been well initialized, the established model can reduce to a linear state-space model, which enables the application of standard Kalman filtering. For the established attitude estimation model, an indirect Kalman filter is detailedly designed. Car-mounted filed test results demonstrate that the proposed method possesses superiority over the existing methods with consideration of both accuracy and efficiency.
49 citations