Planning-Inspired Hierarchical Trajectory Prediction via Lateral-Longitudinal Decomposition for Autonomous Driving

doi:10.1109/TIV.2023.3307116

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 深度强化学习

	Planning-Inspired Hierarchical Trajectory Prediction via Lateral-Longitudinal Decomposition for Autonomous Driving
	Li, Ding 2,3; Zhang, Qichao 2,3; Xia, Zhongpu 1,3; Zheng, Yupeng 2; Zhang, Kuan 1; Yi, Menglong 1; Jin, Wenda 1; Zhao, Dongbin 2,3
刊名	IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
	2024
卷号	9 期号:1 页码:692-703
关键词	Trajectory Roads Predictive models Planning Task analysis Behavioral sciences Vehicle dynamics Autonomous driving trajectory prediction anchor-based prediction
ISSN号	2379-8858
DOI	10.1109/TIV.2023.3307116
通讯作者	Zhang, Qichao(zhangqichao2014@ia.ac.cn)
英文摘要	Trajectory prediction plays a crucial role in bridging the gap between perception and planning in autonomous driving systems. However, most existing methods perform motion forecasting directly in the coupled spatiotemporal space but disregard a more fundamental and faithful interpretation of path intentions. To address this challenge, we propose a novel Planning-inspired Hierarchical (PiH) trajectory prediction framework that selects path and goal intentions through a hierarchical lateral and longitudinal decomposition. For path selection, we propose a hybrid lateral predictor to choose fixed-distance lateral paths from a candidate set of map-based road-following paths and cluster-based free-move paths. For goal selection, we propose a lateral-conditional longitudinal predictor to choose plausible goals by sampling from the selected lateral paths. Finally, we incorporate lateral-longitudinal information to generate final future trajectories based on a category distribution of path-goal intentions. Experimental results demonstrate that PiH achieves competitive and well-balanced performance compared to state-of-the-art methods on both the Argoverse and the Waymo Open Motion Dataset.
资助项目	National Key Research and Development Program of China[2022YFA1004000] ; National Natural Science Foundation of China (NSFC)[62173325] ; CCF Baidu Open Fund
WOS关键词	MODEL
WOS研究方向	Computer Science ; Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001173317800065
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China (NSFC) ; CCF Baidu Open Fund
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58764]
专题	复杂系统管理与控制国家重点实验室_深度强化学习
通讯作者	Zhang, Qichao
作者单位	1.Baidu Inc, Beijing 100085, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Li, Ding,Zhang, Qichao,Xia, Zhongpu,et al. Planning-Inspired Hierarchical Trajectory Prediction via Lateral-Longitudinal Decomposition for Autonomous Driving[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(1):692-703.
APA	Li, Ding.,Zhang, Qichao.,Xia, Zhongpu.,Zheng, Yupeng.,Zhang, Kuan.,...&Zhao, Dongbin.(2024).Planning-Inspired Hierarchical Trajectory Prediction via Lateral-Longitudinal Decomposition for Autonomous Driving.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(1),692-703.
MLA	Li, Ding,et al."Planning-Inspired Hierarchical Trajectory Prediction via Lateral-Longitudinal Decomposition for Autonomous Driving".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.1(2024):692-703.