A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID

Cooperative adaptive cruise control (CACC) has important significance for the development of the connected and automated vehicle (CAV) industry. The traditional proportional integral derivative (PID) platoon controller adjustment is not only time-consuming and laborious, but also unable to adapt to...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Junru Yang, Duanfeng Chu, Weifeng Peng, Chuan Sun, Zejian Deng, Liping Lu, Chaozhong Wu
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	learning control deep deterministic policy gradient (DDPG) parameter tuning automated platoon vehicles longitudinal tracking control Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/713e89ec629a4fa1a8622d6123e4bcea
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:713e89ec629a4fa1a8622d6123e4bcea
record_format	dspace
spelling	oai:doaj.org-article:713e89ec629a4fa1a8622d6123e4bcea2021-11-11T15:36:58ZA Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID10.3390/electronics102125802079-9292https://doaj.org/article/713e89ec629a4fa1a8622d6123e4bcea2021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2580https://doaj.org/toc/2079-9292Cooperative adaptive cruise control (CACC) has important significance for the development of the connected and automated vehicle (CAV) industry. The traditional proportional integral derivative (PID) platoon controller adjustment is not only time-consuming and laborious, but also unable to adapt to different working conditions. This paper proposes a learning control method for a vehicle platooning system using a deep deterministic policy gradient (DDPG)-based PID. The main contribution of this study is automating the PID weight tuning process by formulating this objective as a deep reinforcement learning (DRL) problem. The longitudinal control of the vehicle platooning is divided into upper and lower control structures. The upper-level controller based on the DDPG algorithm can adjust the current PID controller parameters. Through offline training and learning in a SUMO simulation software environment, the PID controller can adapt to different road and vehicular platooning acceleration and deceleration conditions. The lower-level controller controls the gas/brake pedal to accurately track the desired acceleration and speed. Based on the hardware-in-the-loop (HIL) simulation platform, the results show that in terms of the maximum speed error, for the DDPG-based PID controller this is 0.02–0.08 m/s less than for the conventional PID controller, with a maximum reduction of 5.48%. In addition, the maximum distance error of the DDPG-based PID controller is 0.77 m, which is 14.44% less than that of the conventional PID controller.Junru YangDuanfeng ChuWeifeng PengChuan SunZejian DengLiping LuChaozhong WuMDPI AGarticlelearning controldeep deterministic policy gradient (DDPG)parameter tuningautomated platoon vehicleslongitudinal tracking controlElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2580, p 2580 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	learning control deep deterministic policy gradient (DDPG) parameter tuning automated platoon vehicles longitudinal tracking control Electronics TK7800-8360
spellingShingle	learning control deep deterministic policy gradient (DDPG) parameter tuning automated platoon vehicles longitudinal tracking control Electronics TK7800-8360 Junru Yang Duanfeng Chu Weifeng Peng Chuan Sun Zejian Deng Liping Lu Chaozhong Wu A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID
description	Cooperative adaptive cruise control (CACC) has important significance for the development of the connected and automated vehicle (CAV) industry. The traditional proportional integral derivative (PID) platoon controller adjustment is not only time-consuming and laborious, but also unable to adapt to different working conditions. This paper proposes a learning control method for a vehicle platooning system using a deep deterministic policy gradient (DDPG)-based PID. The main contribution of this study is automating the PID weight tuning process by formulating this objective as a deep reinforcement learning (DRL) problem. The longitudinal control of the vehicle platooning is divided into upper and lower control structures. The upper-level controller based on the DDPG algorithm can adjust the current PID controller parameters. Through offline training and learning in a SUMO simulation software environment, the PID controller can adapt to different road and vehicular platooning acceleration and deceleration conditions. The lower-level controller controls the gas/brake pedal to accurately track the desired acceleration and speed. Based on the hardware-in-the-loop (HIL) simulation platform, the results show that in terms of the maximum speed error, for the DDPG-based PID controller this is 0.02–0.08 m/s less than for the conventional PID controller, with a maximum reduction of 5.48%. In addition, the maximum distance error of the DDPG-based PID controller is 0.77 m, which is 14.44% less than that of the conventional PID controller.
format	article
author	Junru Yang Duanfeng Chu Weifeng Peng Chuan Sun Zejian Deng Liping Lu Chaozhong Wu
author_facet	Junru Yang Duanfeng Chu Weifeng Peng Chuan Sun Zejian Deng Liping Lu Chaozhong Wu
author_sort	Junru Yang
title	A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID
title_short	A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID
title_full	A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID
title_fullStr	A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID
title_full_unstemmed	A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID
title_sort	learning control method of automated vehicle platoon at straight path with ddpg-based pid
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/713e89ec629a4fa1a8622d6123e4bcea
work_keys_str_mv	AT junruyang alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT duanfengchu alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT weifengpeng alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT chuansun alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT zejiandeng alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT lipinglu alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT chaozhongwu alearningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT junruyang learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT duanfengchu learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT weifengpeng learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT chuansun learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT zejiandeng learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT lipinglu learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid AT chaozhongwu learningcontrolmethodofautomatedvehicleplatoonatstraightpathwithddpgbasedpid
_version_	1718434990036877312

A Learning Control Method of Automated Vehicle Platoon at Straight Path with DDPG-Based PID

Ejemplares similares