Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey

doi:10.1016/j.trc.2024.104654

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey
	Wu, Jingda 1; Huang, Chao 2; Huang, Hailong 1; Lv, Chen 3; Wang, Yuntong4 ; Wang, Fei-Yue4
发表期刊	TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
ISSN	0968-090X
	2024-07-01
卷号	164 页码:28
通讯作者	Huang, Chao(hchao.huang@polyu.edu.hk)
摘要	Autonomous driving (AD) holds the potential to revolutionize transportation efficiency, but its success hinges on robust behavior planning (BP) mechanisms. Reinforcement learning (RL) emerges as a pivotal tool in crafting these BP strategies. This paper offers a comprehensive review of RL-based BP strategies, spotlighting advancements from 2021 to 2023. We completely organize and distill the relevant literature, emphasizing paradigm shifts in RL-based BP. Introducing a novel categorization, we trace the trajectory of efforts aimed at surmounting practical challenges encountered by autonomous vehicles through innovative RL techniques. To guide readers, we furnish a quantitative analysis that maps the volume and diversity of recent RL configurations, elucidating prevailing trends. Additionally, we delve into the imminent challenges and potential directions for the future of RL-driven BP in AD. These directions encompass addressing safety vulnerabilities, fostering continual learning capabilities, enhancing data efficiency, championing collaborative vehicular cloud networks, integrating large language models, and enhancing ethical considerations.
关键词	Autonomous driving Reinforcement learning Behavior planning Decision Autonomous vehicle
DOI	10.1016/j.trc.2024.104654
关键词[WOS]	DECISION-MAKING ; SAFE ; VEHICLES ; MODEL ; SCENARIOS ; POLICIES ; EFFICIENT ; BARRIER
收录类别	SCI
语种	英语
资助项目	CATARC (Tianjin) Automotive Engineering Research Institute Co., Ltd.[P0048792]
项目资助者	CATARC (Tianjin) Automotive Engineering Research Institute Co., Ltd.
WOS研究方向	Transportation
WOS类目	Transportation Science & Technology
WOS记录号	WOS:001244862600001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58721
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Huang, Chao
作者单位	1.Hong Kong Polytech Univ, Dept Aeronaut & Aviat Engn, Hong Kong, Peoples R China 2.Hong Kong Polytech Univ, Dept Ind & Syst Engn, Hong Kong, Peoples R China 3.Nanyang Technol Univ, Sch Mech & Aerosp Engn, Nanyang 639798, Singapore 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wu, Jingda,Huang, Chao,Huang, Hailong,et al. Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey[J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES,2024,164:28.
APA	Wu, Jingda,Huang, Chao,Huang, Hailong,Lv, Chen,Wang, Yuntong,&Wang, Fei-Yue.(2024).Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey.TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES,164,28.
MLA	Wu, Jingda,et al."Recent advances in reinforcement learning-based autonomous driving behavior planning: A survey".TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 164(2024):28.