VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation

doi:10.1002/cav.2298

	VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation
	Liu, Jingyao 1,2; Mao, Tianlu 1; Wang, Zhaoqi 1
	2024-11-01
发表期刊	COMPUTER ANIMATION AND VIRTUAL WORLDS
ISSN	1546-4261
卷号	35 期号:6 页码:12
摘要	Simulating vehicle trajectories at intersections is one of the challenging tasks in traffic simulation. Existing methods are often ineffective due to the complexity and diversity of lane topologies at intersections, as well as the numerous interactions affecting vehicle motion. To address this issue, we propose a deep learning based vehicle trajectory simulation method. First, we employ a vectorized representation to uniformly extract features from traffic elements such as pedestrians, vehicles, and lanes. By fusing all factors that influence vehicle motion, this representation makes our method suitable for a variety of intersections. Second, we propose a deep learning model, which has an attention network to dynamically extract features from the surrounding environment of the vehicles. To address the issue of vehicles continuously entering and exiting the simulation scene, we employ an asynchronous recurrent neural network for the extraction of temporal features. Comparative evaluations against existing rule-based and deep learning-based methods demonstrate our model's superior simulation accuracy. Furthermore, experimental validation on public datasets demonstrates that our model can simulate vehicle trajectories among the urban intersections with different topologies including those not present in the training dataset.
关键词	attention networks intersection traffic traffic simulation vehicle trajectories
DOI	10.1002/cav.2298
收录类别	SCI
语种	英语
资助项目	Innovation Research Program of ICT
WOS研究方向	Computer Science
WOS类目	Computer Science, Software Engineering
WOS记录号	WOS:001368138400001
出版者	WILEY
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41139
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Mao, Tianlu
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Beijing Key Lab Mobile Comp & Pervas Device, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Dept Comp Sci, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Liu, Jingyao,Mao, Tianlu,Wang, Zhaoqi. VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation[J]. COMPUTER ANIMATION AND VIRTUAL WORLDS,2024,35(6):12.
APA	Liu, Jingyao,Mao, Tianlu,&Wang, Zhaoqi.(2024).VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation.COMPUTER ANIMATION AND VIRTUAL WORLDS,35(6),12.
MLA	Liu, Jingyao,et al."VTSIM: Attention-Based Recurrent Neural Network for Intersection Vehicle Trajectory Simulation".COMPUTER ANIMATION AND VIRTUAL WORLDS 35.6(2024):12.