Autonomous Driving Control Using the DDPG and RDPG Algorithms

Recently, autonomous driving has become one of the most popular topics for smart vehicles. However, traditional control strategies are mostly rule-based, which have poor adaptability to the time-varying traffic conditions. Similarly, they have difficulty coping with unexpected situations that may oc...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Che-Cheng Chang, Jichiang Tsai, Jun-Han Lin, Yee-Ming Ooi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	autonomous driving Deep Deterministic Policy Gradient (DDPG) Recurrent Deterministic Policy Gradient (RDPG) Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
Acceso en línea:	https://doaj.org/article/566af39682ae4b7ca712c37f3d0735ea
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:566af39682ae4b7ca712c37f3d0735ea
record_format	dspace
spelling	oai:doaj.org-article:566af39682ae4b7ca712c37f3d0735ea2021-11-25T16:34:36ZAutonomous Driving Control Using the DDPG and RDPG Algorithms10.3390/app1122106592076-3417https://doaj.org/article/566af39682ae4b7ca712c37f3d0735ea2021-11-01T00:00:00Zhttps://www.mdpi.com/2076-3417/11/22/10659https://doaj.org/toc/2076-3417Recently, autonomous driving has become one of the most popular topics for smart vehicles. However, traditional control strategies are mostly rule-based, which have poor adaptability to the time-varying traffic conditions. Similarly, they have difficulty coping with unexpected situations that may occur any time in the real-world environment. Hence, in this paper, we exploited Deep Reinforcement Learning (DRL) to enhance the quality and safety of autonomous driving control. Based on the road scenes and self-driving simulation modules provided by AirSim, we used the Deep Deterministic Policy Gradient (DDPG) and Recurrent Deterministic Policy Gradient (RDPG) algorithms, combined with the Convolutional Neural Network (CNN), to realize the autonomous driving control of self-driving cars. In particular, by using the real-time images of the road provided by AirSim as the training data, we carefully formulated an appropriate reward-generation method to improve the convergence speed of the adopted DDPG and RDPG models and the control performance of moving driverless cars.Che-Cheng ChangJichiang TsaiJun-Han LinYee-Ming OoiMDPI AGarticleautonomous drivingDeep Deterministic Policy Gradient (DDPG)Recurrent Deterministic Policy Gradient (RDPG)TechnologyTEngineering (General). Civil engineering (General)TA1-2040Biology (General)QH301-705.5PhysicsQC1-999ChemistryQD1-999ENApplied Sciences, Vol 11, Iss 10659, p 10659 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	autonomous driving Deep Deterministic Policy Gradient (DDPG) Recurrent Deterministic Policy Gradient (RDPG) Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999
spellingShingle	autonomous driving Deep Deterministic Policy Gradient (DDPG) Recurrent Deterministic Policy Gradient (RDPG) Technology T Engineering (General). Civil engineering (General) TA1-2040 Biology (General) QH301-705.5 Physics QC1-999 Chemistry QD1-999 Che-Cheng Chang Jichiang Tsai Jun-Han Lin Yee-Ming Ooi Autonomous Driving Control Using the DDPG and RDPG Algorithms
description	Recently, autonomous driving has become one of the most popular topics for smart vehicles. However, traditional control strategies are mostly rule-based, which have poor adaptability to the time-varying traffic conditions. Similarly, they have difficulty coping with unexpected situations that may occur any time in the real-world environment. Hence, in this paper, we exploited Deep Reinforcement Learning (DRL) to enhance the quality and safety of autonomous driving control. Based on the road scenes and self-driving simulation modules provided by AirSim, we used the Deep Deterministic Policy Gradient (DDPG) and Recurrent Deterministic Policy Gradient (RDPG) algorithms, combined with the Convolutional Neural Network (CNN), to realize the autonomous driving control of self-driving cars. In particular, by using the real-time images of the road provided by AirSim as the training data, we carefully formulated an appropriate reward-generation method to improve the convergence speed of the adopted DDPG and RDPG models and the control performance of moving driverless cars.
format	article
author	Che-Cheng Chang Jichiang Tsai Jun-Han Lin Yee-Ming Ooi
author_facet	Che-Cheng Chang Jichiang Tsai Jun-Han Lin Yee-Ming Ooi
author_sort	Che-Cheng Chang
title	Autonomous Driving Control Using the DDPG and RDPG Algorithms
title_short	Autonomous Driving Control Using the DDPG and RDPG Algorithms
title_full	Autonomous Driving Control Using the DDPG and RDPG Algorithms
title_fullStr	Autonomous Driving Control Using the DDPG and RDPG Algorithms
title_full_unstemmed	Autonomous Driving Control Using the DDPG and RDPG Algorithms
title_sort	autonomous driving control using the ddpg and rdpg algorithms
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/566af39682ae4b7ca712c37f3d0735ea
work_keys_str_mv	AT chechengchang autonomousdrivingcontrolusingtheddpgandrdpgalgorithms AT jichiangtsai autonomousdrivingcontrolusingtheddpgandrdpgalgorithms AT junhanlin autonomousdrivingcontrolusingtheddpgandrdpgalgorithms AT yeemingooi autonomousdrivingcontrolusingtheddpgandrdpgalgorithms
_version_	1718413075825033216

Autonomous Driving Control Using the DDPG and RDPG Algorithms

Ejemplares similares