MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method

In this paper, we investigate the problem of unmanned aerial vehicles (UAVs) autonomous tracking moving target with only an airborne camera sensor. We proposed a novel integrated controller framework for this problem based on multi-neural-network modules (MNNMs). In this framework, two neural networ...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mingjun Li, Zhihao Cai, Jiang Zhao, Yibo Wang, Yingxun Wang, Kelin Lu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	unmanned aerial vehicles autonomous tracking target perception and control integrated controller multi-neural-network modules deep learning Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/8069058fabaf465fa99653e723a67453
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8069058fabaf465fa99653e723a67453
record_format	dspace
spelling	oai:doaj.org-article:8069058fabaf465fa99653e723a674532021-11-11T19:15:33ZMNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method10.3390/s212173071424-8220https://doaj.org/article/8069058fabaf465fa99653e723a674532021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7307https://doaj.org/toc/1424-8220In this paper, we investigate the problem of unmanned aerial vehicles (UAVs) autonomous tracking moving target with only an airborne camera sensor. We proposed a novel integrated controller framework for this problem based on multi-neural-network modules (MNNMs). In this framework, two neural networks are designed for target perception and guidance control, respectively. The deep learning method and reinforcement learning method are applied to train the integrated controller. The training result demonstrates that the integrated controller can be trained more quickly and efficiently than the end-to-end controller trained by the deep reinforcement learning method. The flight tests with the integrated controller are implemented in simulated and realistic environments, the results show that the integrated controller trained in simulation can easily be transferred to the realistic environment and achieve the UAV tracking randomly moving target, which has a faster motion velocity. The integrated controller based on the MNNMs structure has a better performance on an autonomous tracking target than the control mode that combines with a perception network and a proportional integral derivative controller.Mingjun LiZhihao CaiJiang ZhaoYibo WangYingxun WangKelin LuMDPI AGarticleunmanned aerial vehiclesautonomous tracking targetperception and controlintegrated controllermulti-neural-network modulesdeep learningChemical technologyTP1-1185ENSensors, Vol 21, Iss 7307, p 7307 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	unmanned aerial vehicles autonomous tracking target perception and control integrated controller multi-neural-network modules deep learning Chemical technology TP1-1185
spellingShingle	unmanned aerial vehicles autonomous tracking target perception and control integrated controller multi-neural-network modules deep learning Chemical technology TP1-1185 Mingjun Li Zhihao Cai Jiang Zhao Yibo Wang Yingxun Wang Kelin Lu MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method
description	In this paper, we investigate the problem of unmanned aerial vehicles (UAVs) autonomous tracking moving target with only an airborne camera sensor. We proposed a novel integrated controller framework for this problem based on multi-neural-network modules (MNNMs). In this framework, two neural networks are designed for target perception and guidance control, respectively. The deep learning method and reinforcement learning method are applied to train the integrated controller. The training result demonstrates that the integrated controller can be trained more quickly and efficiently than the end-to-end controller trained by the deep reinforcement learning method. The flight tests with the integrated controller are implemented in simulated and realistic environments, the results show that the integrated controller trained in simulation can easily be transferred to the realistic environment and achieve the UAV tracking randomly moving target, which has a faster motion velocity. The integrated controller based on the MNNMs structure has a better performance on an autonomous tracking target than the control mode that combines with a perception network and a proportional integral derivative controller.
format	article
author	Mingjun Li Zhihao Cai Jiang Zhao Yibo Wang Yingxun Wang Kelin Lu
author_facet	Mingjun Li Zhihao Cai Jiang Zhao Yibo Wang Yingxun Wang Kelin Lu
author_sort	Mingjun Li
title	MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method
title_short	MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method
title_full	MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method
title_fullStr	MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method
title_full_unstemmed	MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method
title_sort	mnnms integrated control for uav autonomous tracking randomly moving target based on learning method
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8069058fabaf465fa99653e723a67453
work_keys_str_mv	AT mingjunli mnnmsintegratedcontrolforuavautonomoustrackingrandomlymovingtargetbasedonlearningmethod AT zhihaocai mnnmsintegratedcontrolforuavautonomoustrackingrandomlymovingtargetbasedonlearningmethod AT jiangzhao mnnmsintegratedcontrolforuavautonomoustrackingrandomlymovingtargetbasedonlearningmethod AT yibowang mnnmsintegratedcontrolforuavautonomoustrackingrandomlymovingtargetbasedonlearningmethod AT yingxunwang mnnmsintegratedcontrolforuavautonomoustrackingrandomlymovingtargetbasedonlearningmethod AT kelinlu mnnmsintegratedcontrolforuavautonomoustrackingrandomlymovingtargetbasedonlearningmethod
_version_	1718431594378690560

MNNMs Integrated Control for UAV Autonomous Tracking Randomly Moving Target Based on Learning Method

Ejemplares similares