Conditional Goal-Oriented Trajectory Prediction for Interacting Vehicles

doi:10.1109/TNNLS.2023.3321564

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

	Conditional Goal-Oriented Trajectory Prediction for Interacting Vehicles
	Li, Ding 2,3; Zhang, Qichao 2,3; Lu, Shuai 1; Pan, Yifeng 1; Zhao, Dongbin 2,3
刊名	IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
	2023-10-17
页码	13
关键词	Trajectory Predictive models Behavioral sciences Pipelines Task analysis Feature extraction Vehicle dynamics Conditional prediction goal-oriented trajectory prediction hierarchical vectorized representation joint trajectory prediction marginal prediction
ISSN号	2162-237X
DOI	10.1109/TNNLS.2023.3321564
通讯作者	Zhang, Qichao(zhangqichao2014@ia.ac.cn)
英文摘要	Predicting future trajectories of pairwise traffic agents in highly interactive scenarios, such as cut-in, yielding, and merging, is challenging for autonomous driving. The existing works either treat such a problem as a marginal prediction task or perform single-axis factorized joint prediction, where the former strategy produces individual predictions without considering future interaction, while the latter strategy conducts conditional trajectory-oriented prediction via agentwise interaction or achieves conditional rollout-oriented prediction via timewise interaction. In this article, we propose a novel double-axis factorized joint prediction pipeline, namely, conditional goal-oriented trajectory prediction (CGTP) framework, which models future interaction both along the agent and time axes to achieve goal and trajectory interactive prediction. First, a goals-of-interest network (GoINet) is designed to extract fine-grained features of goal candidates via hierarchical vectorized representation. Furthermore, we propose a conditional goal prediction network (CGPNet) to produce multimodal goal pairs in an agentwise conditional manner, along with a newly designed goal interactive loss to better learn the joint distribution of the intermediate interpretable modes. Explicitly guided by the goal-pair predictions, we propose a goal-oriented trajectory rollout network (GTRNet) to predict scene-compliant trajectory pairs via timewise interactive rollouts. Extensive experimental results confirm that the proposed CGTP outperforms the state-of-the-art (SOTA) prediction models on the Waymo open motion dataset (WOMD), Argoverse motion forecasting dataset, and In-house cut-in dataset. Code is available at https://github.com/LiDinga/CGTP/.
资助项目	National Key Research and Development Program of China[2022YFA1004000] ; National Natural Science Foundation of China (NSFC)[62173325] ; China Computer Federation (CCF) Baidu Open Fund ; National Key Research and Development Program of China[2022YFA1004000] ; National Natural Science Foundation of China (NSFC)[62173325] ; China Computer Federation (CCF) Baidu Open Fund
WOS关键词	MODEL
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001090718900001
资助机构	National Key Research and Development Program of China ; National Natural Science Foundation of China (NSFC) ; China Computer Federation (CCF) Baidu Open Fund ; National Key Research and Development Program of China ; National Natural Science Foundation of China (NSFC) ; China Computer Federation (CCF) Baidu Open Fund
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54385]
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 S, 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,Lu, Shuai,et al. Conditional Goal-Oriented Trajectory Prediction for Interacting Vehicles[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2023:13.
APA	Li, Ding,Zhang, Qichao,Lu, Shuai,Pan, Yifeng,&Zhao, Dongbin.(2023).Conditional Goal-Oriented Trajectory Prediction for Interacting Vehicles.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,13.
MLA	Li, Ding,et al."Conditional Goal-Oriented Trajectory Prediction for Interacting Vehicles".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2023):13.