Multi-Sensor Fusion for Underwater Vehicle Localization by Augmentation of RBF Neural Network and Error-State Kalman Filter.

Pablo Otero,Muhammad Javed Iqbal,Muhammad Moinuddin,Ahmed Ali,Nabil Shaukat

doi:10.3390/s21041149

Pablo Otero, Muhammad Javed Iqbal + Show 3 more

Open Access

https://doi.org/10.3390/s21041149

Copy DOI

Abstract

The Kalman filter variants extended Kalman filter (EKF) and error-state Kalman filter (ESKF) are widely used in underwater multi-sensor fusion applications for localization and navigation. Since these filters are designed by employing first-order Taylor series approximation in the error covariance matrix, they result in a decrease in estimation accuracy under high nonlinearity. In order to address this problem, we proposed a novel multi-sensor fusion algorithm for underwater vehicle localization that improves state estimation by augmentation of the radial basis function (RBF) neural network with ESKF. In the proposed algorithm, the RBF neural network is utilized to compensate the lack of ESKF performance by improving the innovation error term. The weights and centers of the RBF neural network are designed by minimizing the estimation mean square error (MSE) using the steepest descent optimization approach. To test the performance, the proposed RBF-augmented ESKF multi-sensor fusion was compared with the conventional ESKF under three different realistic scenarios using Monte Carlo simulations. We found that our proposed method provides better navigation and localization results despite high nonlinearity, modeling uncertainty, and external disturbances.

Highlights

The ocean floor has billions of dollars of natural resources in the form of precious elements and medicinal herbs
To take advantage of ocean resources, seabed mapping is the ultimate tool that depends on precise sensors and robust navigation fusion algorithms for autonomous underwater vehicles (AUVs) and remotely operated underwater vehicles (ROVs)
In order to compare performances, the proposed algorithm and error-state Kalman filter (ESKF) were simulated in three different realistic scenarios

Summary

Introduction

The ocean floor has billions of dollars of natural resources in the form of precious elements and medicinal herbs. To take advantage of ocean resources, seabed mapping is the ultimate tool that depends on precise sensors and robust navigation fusion algorithms for autonomous underwater vehicles (AUVs) and remotely operated underwater vehicles (ROVs). Navigational accuracy is a key requirement for complex seabed mapping tasks [1]. Most commonly used fusion algorithms based on extended Kalman filter (EKF) and its variant error-state Kalman (ESKF) suffer from divergence and degraded mean square error (MSE) performance in the nonlinear underwater condition because of linear approximation [2]. The higher the nonlinearity present in the system, the greater the error of the EKF state prediction, and it can induce filter divergence

Objectives

Results

Conclusion