Abstract

In this paper, an innovative optimal information fusion methodology based on adaptive and robust unscented Kalman filter (UKF) for multi-sensor nonlinear stochastic systems is proposed. Based on the linear minimum variance criterion, this multi-sensor information fusion method has a two-layer architecture: at the first layer, a new adaptive UKF scheme for the time-varying noise covariance is developed and serves as a local filter to improve the adaptability together with the estimated measurement noise covariance by applying the redundant measurement noise covariance estimation, which is isolated from the state estimation; the second layer is the fusion structure to calculate the optimal matrix weights and gives the final optimal state estimations. Based on the hypothesis testing theory with the Mahalanobis distance, the new adaptive UKF scheme utilizes both the innovation and the residual sequences to adapt the process noise covariance timely. The results of the target tracking simulations indicate that the proposed method is effective under the condition of time-varying process-error and measurement noise covariance.

Highlights

  • The remainder of this paper is organized as follows: we describe the standard unscented Kalman filter (UKF), the redundant measurement noise covariance estimation (RMNCE), an innovative adaptive UKF (AUKF) proposed by this paper and the decentralized multi-sensor information filters (MSIF)

  • A set of numerical simulations of the radar tracking problems will be presented to illustrate the effectiveness of the proposed ARUKF‐MSIF

  • A set of numerical simulations of the radar tracking problems will be presented to illustrate the effectiveness of the proposed ARUKF-MSIF

Read more

Summary

Introduction

There have been increasing demands for developing robust, adaptive, and accurate multi-sensor information filters (MSIF), which have been widely applied to many fields such as navigation systems, modern industries, military threat detection, target tracking, and remote sensing [1,2]. By using a multi-sensor structure, an information fusion algorithm can obtain much more accurate estimations than a single one [5,6]. The first method is the centralized filter where all raw sensor data are fed to a central site for processing [1]. The second one is the decentralized or distributed filter where the process is divided between some local filter concurrently to obtain individual raw data-based estimates and one master/center filter to fuse those local estimates to provide a much accurate global optimal estimate [6,8]

Objectives
Findings
Discussion
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call