Please use this identifier to cite or link to this item:
Title: Intelligent GNSS/INS integrated navigation system for a commercial UAV flight control system
Authors: Zhang, G 
Hsu, LT 
Keywords: UAV
Kalman filter
Adaptive tuning
Machine learning
Issue Date: Sep-2018
Publisher: Elsevier Masson
Source: Aerospace science and technology, Sept. 2018, v. 80, p. 368-380 How to cite?
Journal: Aerospace science and technology 
Abstract: Owing to the increase in civil applications using quadcopters, commercial flight control systems such as Pixhawk are a popular solution to provide the sensing and control functions of an unmanned aerial vehicle (UAV). A low-cost global navigation satellite system (GNSS) receiver is crucial for the low-cost flight control system. However, the accuracy of GNSS positioning is severely degraded by the notorious multipath effect in mega-urbanized cities. The multipath effect cannot be eliminated but can be mitigated; hence, the GNSS/inertial navigation system (INS) integrated navigation is a popular approach to reduce this error. This study proposes an adaptive Kalman filter for adjusting the noise covariance of GNSS measurements under different positioning accuracies. The adaptive tuning is based on a proposed accuracy classification model trained by a supervised machine-learning method. First, principal component analysis is employed to identify the significant GNSS accuracy related features. Subsequently, the positioning accuracy model is trained based on a random forest learning algorithm with the labeled real GNSS dataset encompassing most scenarios concerning modern urban areas. To reduce the cases of misclassifying the GNSS accuracy, a fuzzy logic algorithm is employed to consider the GNSS accuracy propagation. Additionally, the process noise covariance of the INS is determined using the Allan variance analysis. The positioning performance of the proposed adaptive Kalman filter is compared with both a conventional Kalman filter and the positioning solution provided by the commercial flight control system, Pixhawk 2. The results show that the proposed adaptive Kalman filter using random forest with fuzzy logic can achieve a better classification of GNSS accuracy compared to the others. The overall positioning result improved by approximately 50% compared with the onboard solution.
ISSN: 1270-9638
EISSN: 1626-3219
DOI: 10.1016/j.ast.2018.07.026
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record

Page view(s)

Citations as of Mar 22, 2019

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.