A fuzzy-inference-based reinforcement learning method of overtaking decision making for automated vehicles

doi:10.1177/09544070211018099

	A fuzzy-inference-based reinforcement learning method of overtaking decision making for automated vehicles
	Wu, Qiong 1,2; Cheng, Shuo 3; Li, Liang 3; Yang, Fan 4; Meng, Li Jun 4; Fan, Zhi Xian 3; Liang, Hua Wei 1
刊名	PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING
	2021-05-14
关键词	Automated vehicle intelligent decision making fuzzy inference reinforcement learning
ISSN号	0954-4070
DOI	10.1177/09544070211018099
通讯作者	Cheng, Shuo(chengs16@mails.tsinghua.edu.cn)
英文摘要	Intelligent decision control is one key issue of automated vehicles. Complex dynamic traffic flow and multi-requirement of passengers including vehicle safety, comfort, vehicle efficiency bring about tremendous challenges to vehicle decision making. Overtaking maneuver is a demanding task due to its large potential of traffic collision. Therefore, this paper proposes a fuzzy-inference-based reinforcement learning (FIRL) approach of autonomous overtaking decision making. Firstly, the problem of overtaking is formulated as a multi-objective Markov decision process (MDP) considering vehicle safety, driving comfort, and vehicle efficiency. Secondly, a temporal difference learning based on dynamic fuzzy (DF-TDL) is presented to learn optimized policies for autonomous overtaking decision making. Fuzzy inference is introduced to deal with continuous states and boost learning process. The RL algorithm decides whether to overtake or not based on the learned policies. Then, the automated vehicle executes local path planning and tracking. Furthermore, a simulation platform based on simulation of urban mobility (SUMO) is established to generate the random training data, that is, various traffic flows for algorithm iterative learning and validate the proposed method, extensive test results demonstrate the effectiveness of the overtaking decision-making method.
资助项目	Electric Automobile and Intelligent Connected Automobile Industry Innovation Project of Anhui Province[JAC2019022505] ; Key Research and Development Projects in Shandong Province[2019TSLH701] ; Key Research and Development Projects in Shandong Province[2019JZZY020116]
WOS关键词	INTELLIGENT VEHICLES
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	SAGE PUBLICATIONS LTD
WOS记录号	WOS:000682130200001
资助机构	Electric Automobile and Intelligent Connected Automobile Industry Innovation Project of Anhui Province ; Key Research and Development Projects in Shandong Province
内容类型	期刊论文
源URL	[http://ir.hfcas.ac.cn:8080/handle/334002/123054]
专题	中国科学院合肥物质科学研究院
通讯作者	Cheng, Shuo
作者单位	1.Chinese Acad Sci, Hefei Inst Phys Sci, Hefei, Peoples R China 2.Univ Sci & Technol, Hefei, Peoples R China 3.Tsinghua Univ, State Key Lab Automot Safety & Energy, Room A539-3,Lee Shau Kee Sci & Technol Bldg, Beijing 100084, Peoples R China 4.Tianjin Trinova Automobile Technol Co Ltd, Tianjin, Peoples R China
推荐引用方式 GB/T 7714	Wu, Qiong,Cheng, Shuo,Li, Liang,et al. A fuzzy-inference-based reinforcement learning method of overtaking decision making for automated vehicles[J]. PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING,2021.
APA	Wu, Qiong.,Cheng, Shuo.,Li, Liang.,Yang, Fan.,Meng, Li Jun.,...&Liang, Hua Wei.(2021).A fuzzy-inference-based reinforcement learning method of overtaking decision making for automated vehicles.PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING.
MLA	Wu, Qiong,et al."A fuzzy-inference-based reinforcement learning method of overtaking decision making for automated vehicles".PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART D-JOURNAL OF AUTOMOBILE ENGINEERING (2021).