Underwater Vehicle Positioning by Correntropy-Based Fuzzy Multi-Sensor Fusion

Abstract

The ability of the underwater vehicle to determine its precise position is vital to completing a mission successfully. Multi-sensor fusion methods for underwater vehicle positioning are commonly based on Kalman filtering, which requires the knowledge of process and measurement noise covariance. As the underwater conditions are continuously changing, incorrect process and measurement noise covariance affect the accuracy of position estimation and sometimes cause divergence. Furthermore, the underwater multi-path effect and nonlinearity cause outliers that have a significant impact on positional accuracy. These non-Gaussian outliers are difficult to handle with conventional Kalman-based methods and their fuzzy variants. To address these issues, this paper presents a new and improved adaptive multi-sensor fusion method by using information-theoretic, learning-based fuzzy rules for Kalman filter covariance adaptation in the presence of outliers. Two novel metrics are proposed by utilizing correntropy Gaussian and Versoria kernels for matching theoretical and actual covariance. Using correntropy-based metrics and fuzzy logic together makes the algorithm robust against outliers in nonlinear dynamic underwater conditions. The performance of the proposed sensor fusion technique is compared and evaluated using Monte-Carlo simulations, and substantial improvements in underwater position estimation are obtained.

3D Localization for Mobile Node in Wireless Sensor Network

“…WSN node location information is extremely important in many WSN applications. The data information collected by WSN is based on the known node location information [12].…”

Probabilistic Framework Allocation on Underwater Vehicular Systems Using Hydrophone Sensor Networks

“…Despite the fact that energy savings are maximised, the data processing strategy is not slanted in any portion of the procedures, and such designs will only satisfy industrial needs. In response to the aforementioned worry, a practical solution has been developed to meet the demands of all persons in aquatic farms [8]. The aforementioned method focuses on multi-modal fusion technology by combining sensors into fuzzy systems with Monte-Carlo simulations used for the estimate.…”

The attitude control optimization of small rocket

“…The proposed algorithm was found to have a better position and velocity estimation under the negative influence of shot noise compared with Kalman and fuzzy-based sensor fusion techniques. [4] And H. Zhu studied the necessity and advantages of multi-scale multi-sensor data fusion, through which the structure model of multi-scale and multi-sensor data fusion is analyzed. The researcher find that the configuration scheme of multi-sensor fusion is helpful to improve the reliability, accuracy, fault detection and isolation requirements of MEMS gyroscope data processing.…”

“…Therefore, the first-order complementary algorithm is used to combine the acceleration with the different weights given by the gyroscope for data fusion. [4] Without explicitly calculating the attitude angle, only the corrected PI value is output to the subsequent controller, and the operation can be completed only by the integer algorithm, so as to reduce the delay and improve the real-time performance.…”