Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight

This paper presents a dynamical recurrent neural network- (RNN-) based model predictive control (MPC) structure for the formation flight of multiple unmanned quadrotors. A distributed hierarchical control system with the translation subsystem and rotational subsystem is proposed to handle the format...

Full description

Saved in:
Bibliographic Details
Main Authors: Boyang Zhang, Xiuxia Sun, Shuguang Liu, Xiongfeng Deng
Format: Article
Language:English
Published: Wiley 2019-01-01
Series:International Journal of Aerospace Engineering
Online Access:http://dx.doi.org/10.1155/2019/7272387
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850209346242215936
author Boyang Zhang
Xiuxia Sun
Shuguang Liu
Xiongfeng Deng
author_facet Boyang Zhang
Xiuxia Sun
Shuguang Liu
Xiongfeng Deng
author_sort Boyang Zhang
collection DOAJ
description This paper presents a dynamical recurrent neural network- (RNN-) based model predictive control (MPC) structure for the formation flight of multiple unmanned quadrotors. A distributed hierarchical control system with the translation subsystem and rotational subsystem is proposed to handle the formation-tracking problem for each quadrotor. The RNN-based MPC is proposed for each subsystem, where the RNN is introduced as the predictive model in MPC. And to improve the modeling accuracy, an adaptive updating law is developed to tune weights online for the RNN. Besides, the adaptive differential evolution (DE) algorithm is utilized to solve the optimization problem for MPC. Furthermore, the closed-loop stability is analyzed; meanwhile, the convergence of the DE algorithm is discussed as well. Finally, some simulation examples are provided to illustrate the validity of the proposed control structure.
format Article
id doaj-art-91da2fc175c44e75bc4fd888fb034dcf
institution OA Journals
issn 1687-5966
1687-5974
language English
publishDate 2019-01-01
publisher Wiley
record_format Article
series International Journal of Aerospace Engineering
spelling doaj-art-91da2fc175c44e75bc4fd888fb034dcf2025-08-20T02:10:02ZengWileyInternational Journal of Aerospace Engineering1687-59661687-59742019-01-01201910.1155/2019/72723877272387Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation FlightBoyang Zhang0Xiuxia Sun1Shuguang Liu2Xiongfeng Deng3Equipment Management and Unmanned Aerial Vehicle Engineering College, Air Force Engineering University, Xi’an 710051, ChinaEquipment Management and Unmanned Aerial Vehicle Engineering College, Air Force Engineering University, Xi’an 710051, ChinaEquipment Management and Unmanned Aerial Vehicle Engineering College, Air Force Engineering University, Xi’an 710051, ChinaEquipment Management and Unmanned Aerial Vehicle Engineering College, Air Force Engineering University, Xi’an 710051, ChinaThis paper presents a dynamical recurrent neural network- (RNN-) based model predictive control (MPC) structure for the formation flight of multiple unmanned quadrotors. A distributed hierarchical control system with the translation subsystem and rotational subsystem is proposed to handle the formation-tracking problem for each quadrotor. The RNN-based MPC is proposed for each subsystem, where the RNN is introduced as the predictive model in MPC. And to improve the modeling accuracy, an adaptive updating law is developed to tune weights online for the RNN. Besides, the adaptive differential evolution (DE) algorithm is utilized to solve the optimization problem for MPC. Furthermore, the closed-loop stability is analyzed; meanwhile, the convergence of the DE algorithm is discussed as well. Finally, some simulation examples are provided to illustrate the validity of the proposed control structure.http://dx.doi.org/10.1155/2019/7272387
spellingShingle Boyang Zhang
Xiuxia Sun
Shuguang Liu
Xiongfeng Deng
Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight
International Journal of Aerospace Engineering
title Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight
title_full Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight
title_fullStr Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight
title_full_unstemmed Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight
title_short Recurrent Neural Network-Based Model Predictive Control for Multiple Unmanned Quadrotor Formation Flight
title_sort recurrent neural network based model predictive control for multiple unmanned quadrotor formation flight
url http://dx.doi.org/10.1155/2019/7272387
work_keys_str_mv AT boyangzhang recurrentneuralnetworkbasedmodelpredictivecontrolformultipleunmannedquadrotorformationflight
AT xiuxiasun recurrentneuralnetworkbasedmodelpredictivecontrolformultipleunmannedquadrotorformationflight
AT shuguangliu recurrentneuralnetworkbasedmodelpredictivecontrolformultipleunmannedquadrotorformationflight
AT xiongfengdeng recurrentneuralnetworkbasedmodelpredictivecontrolformultipleunmannedquadrotorformationflight