A fast learning approach for autonomous navigation using a deep reinforcement learning method

Abstract Deep reinforcement learning‐based methods employ an ample amount of computational power that affects the learning process. This paper proposes a novel approach to speed up the training process and improve the performance of autonomous navigation for a tracked robot. The proposed model named...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Muhammad Mudassir Ejaz, Tong Boon Tang, Cheng‐Kai Lu
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/5d00fccac16c4c09b8f53c68bbb338b2
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5d00fccac16c4c09b8f53c68bbb338b2
record_format	dspace
spelling	oai:doaj.org-article:5d00fccac16c4c09b8f53c68bbb338b22021-11-16T10:15:44ZA fast learning approach for autonomous navigation using a deep reinforcement learning method1350-911X0013-519410.1049/ell2.12057https://doaj.org/article/5d00fccac16c4c09b8f53c68bbb338b22021-01-01T00:00:00Zhttps://doi.org/10.1049/ell2.12057https://doaj.org/toc/0013-5194https://doaj.org/toc/1350-911XAbstract Deep reinforcement learning‐based methods employ an ample amount of computational power that affects the learning process. This paper proposes a novel approach to speed up the training process and improve the performance of autonomous navigation for a tracked robot. The proposed model named “layer normalization dueling double deep Q‐network” has been trained in a virtual environment and then implemented it to a tracked robot for testing in a real‐world scenario. Depth images have been used instead of RGB images to preserve the temporal information. Features are extracted using convolutional neural networks, and actions are derived using the dueling double deep Q‐network. The input data has been normalized before each convolutional layer, which reduces the covariate shift by 69%. This end‐to‐end network architecture of the proposed model provides stability to the network, relieves the burden of computational cost, and converges in much less number of episodes. Compared with three Q‐variant models, the proposed model demonstrates outstanding performance in terms of episodic reward and convergence rate. The proposed model took 12.8% fewer episodes for training compared to other models.Muhammad Mudassir EjazTong Boon TangCheng‐Kai LuWileyarticleElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENElectronics Letters, Vol 57, Iss 2, Pp 50-53 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Electrical engineering. Electronics. Nuclear engineering TK1-9971 Muhammad Mudassir Ejaz Tong Boon Tang Cheng‐Kai Lu A fast learning approach for autonomous navigation using a deep reinforcement learning method
description	Abstract Deep reinforcement learning‐based methods employ an ample amount of computational power that affects the learning process. This paper proposes a novel approach to speed up the training process and improve the performance of autonomous navigation for a tracked robot. The proposed model named “layer normalization dueling double deep Q‐network” has been trained in a virtual environment and then implemented it to a tracked robot for testing in a real‐world scenario. Depth images have been used instead of RGB images to preserve the temporal information. Features are extracted using convolutional neural networks, and actions are derived using the dueling double deep Q‐network. The input data has been normalized before each convolutional layer, which reduces the covariate shift by 69%. This end‐to‐end network architecture of the proposed model provides stability to the network, relieves the burden of computational cost, and converges in much less number of episodes. Compared with three Q‐variant models, the proposed model demonstrates outstanding performance in terms of episodic reward and convergence rate. The proposed model took 12.8% fewer episodes for training compared to other models.
format	article
author	Muhammad Mudassir Ejaz Tong Boon Tang Cheng‐Kai Lu
author_facet	Muhammad Mudassir Ejaz Tong Boon Tang Cheng‐Kai Lu
author_sort	Muhammad Mudassir Ejaz
title	A fast learning approach for autonomous navigation using a deep reinforcement learning method
title_short	A fast learning approach for autonomous navigation using a deep reinforcement learning method
title_full	A fast learning approach for autonomous navigation using a deep reinforcement learning method
title_fullStr	A fast learning approach for autonomous navigation using a deep reinforcement learning method
title_full_unstemmed	A fast learning approach for autonomous navigation using a deep reinforcement learning method
title_sort	fast learning approach for autonomous navigation using a deep reinforcement learning method
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/5d00fccac16c4c09b8f53c68bbb338b2
work_keys_str_mv	AT muhammadmudassirejaz afastlearningapproachforautonomousnavigationusingadeepreinforcementlearningmethod AT tongboontang afastlearningapproachforautonomousnavigationusingadeepreinforcementlearningmethod AT chengkailu afastlearningapproachforautonomousnavigationusingadeepreinforcementlearningmethod AT muhammadmudassirejaz fastlearningapproachforautonomousnavigationusingadeepreinforcementlearningmethod AT tongboontang fastlearningapproachforautonomousnavigationusingadeepreinforcementlearningmethod AT chengkailu fastlearningapproachforautonomousnavigationusingadeepreinforcementlearningmethod
_version_	1718426549414264832

A fast learning approach for autonomous navigation using a deep reinforcement learning method

Ejemplares similares