An Enhanced Fusion Strategy for Reliable Attitude Measurement Utilizing Vision and Inertial Sensors

Zhang Zhang,Zhao Zhao,Huang Huang,Chen Chen,Shen Shen,Guo Guo,Cao Cao

doi:10.3390/app9132656

Zhang Zhang, Zhao Zhao + Show 5 more

Open Access

https://doi.org/10.3390/app9132656

Copy DOI

Abstract

In this paper, we present a radial basis function (RBF) and cubature Kalman filter (CKF) based enhanced fusion strategy for vision and inertial integrated attitude measurement for sampling frequency discrepancy and divergence. First, the multi-frequency problem of the integrated system and the reason for attitude divergence are analyzed. Second, the filter equation and attitude differential equation are constructed to calculate attitudes separately in time series when visual and inertial data are available or when there are only inertial data. Third, attitude errors between inertial and vision are sent to the input layer of RBF for training. After this, through the activation function of the hidden layer, the errors are transferred to the output layer for weighting the sums, and the training model is established. To overcome the problem of divergence inherent in a multi-frequency system, the well-trained RBF, which can output the attitude errors, is utilized to compensate the attitudes calculated by pure inertial data. Finally, semi-physical simulation experiments under different scenarios are performed to validate the effectiveness and superiority of the proposed scheme in accurate attitude measurements and enhanced anti-divergence capability.

Highlights

Attitude measurement has received considerable attention from the research community due to its significant importance in navigation, positioning, tracking and control [1,2,3,4], where measurement precision and stability are important requirements
The attitude measurement technique is applied to the helmet tracking system, which is by capturing four feature points installed on the moving object with a camera
cubature Kalman filter (CKF), the proposed attitude can reduce problem divergence framework of CKF, the proposed attitude measurement not onlydata canbut reduce of in the intersampling of slow visionreliable data when calculated by only inertial the canproblem ensure the divergence inherent in the intersampling of slow vision data when calculated by only inertial data stability of the high frequency output of attitude angles

Summary

Introduction

Attitude measurement has received considerable attention from the research community due to its significant importance in navigation, positioning, tracking and control [1,2,3,4], where measurement precision and stability are important requirements. The main purpose of attitude measurement is to dynamically obtain the spatial attitude angles of the measured object using one or more sensors installed onto it in engineering measurement, military, controlling and locating robots [5,6,7]. The development of an effective attitude measurement strategy that performs well while ensuring stability and precision is still a significant challenge due to the following important reasons. (i) The single sensor has limited performance due to its own measurement characteristics. All the aforementioned factors pose multiple handicaps in implementing a high-performance attitude measurement system.

Objectives

Methods

Conclusion