Please use this identifier to cite or link to this item:
Title: Autonomous Navigation of an Aircraft Using a NARX Recurrent Neural Network
Authors: Sezginer, Kaan
Kasnakoğlu, Coşku
Keywords: Helicopters 
 attitude control 
Issue Date: Nov-2019
Publisher: Institute of Electrical and Electronics Engineers Inc.
Source: Sezginer, K., & Kasnakoğlu, C. (2019). Autonomous Navigation of an Aircraft Using a NARX Recurrent Neural Network. In 2019 11th International Conference on Electrical and Electronics Engineering (ELECO) (pp. 895-899). IEEE.
Abstract: This paper explores autonomous aircraft navigation using machine learning approach focusing on the ground run and takeoff which is one of the most critical control problems in the aircraft navigation. A controller which controls the aircraft during the takeoff is designed as a black-box method focusing on the input-output relationship between the flight data and control commands. The controller is modelled using the time-series relationship among the data realizing a recurrent neural network (RNN) with the nonlinear autoregressive network with exogenous inputs (NARX) architecture. The flight data are acquired from pilot experiences in the X-Plane flight simulator. Furthermore, the modelling of the controller is constituted using these experiences. This paper also discusses the takeoff performance of the controller network in clean weather conditions that includes additional wind layers at various altitudes. The simulation results establish a satisfactory flight performance of controlling the aircraft in a smooth and stable manner. © 2019 Chamber of Turkish Electrical Engineers.
ISBN: 978-605011275-7
Appears in Collections:Elektrik ve Elektronik Mühendisliği Bölümü / Department of Electrical & Electronics Engineering
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection

Show full item record

CORE Recommender


checked on Sep 23, 2022

Page view(s)

checked on Dec 26, 2022

Google ScholarTM



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