A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory

doi:10.1109/TITS.2024.3398648

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 > 先进控制与自动化团队

	A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory
	Li, Wenli 5; Zhang, Yinan 5; Li, Lingxi 4; Lv, Yisheng 1,2,3; Wang, Mengxin 5
刊名	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2024-05-22
页码	16
关键词	Right-turn intersections pedestrian trajectory prediction pedestrian-vehicle interaction game theory social-generative adversarial network
ISSN号	1524-9050
DOI	10.1109/TITS.2024.3398648
通讯作者	Li, Lingxi(LL7@iupui.edu)
英文摘要	This paper aims to propose a pedestrian trajectory prediction model based on pedestrian-vehicle game theory to study pedestrian trajectories during pedestrian-vehicle interaction at unsignalized right-turn intersections. First, pedestrian-vehicle interaction scene data at unsignalized right-turn intersections were collected. Then, a novel pedestrian-vehicle game theory model was established, where its parameters were calibrated using the Nash equilibrium of a complete information static game and the probabilities of pedestrians and vehicles crossing the street. A new pedestrian-vehicle game utility matrix is embedded into the social-generative adversarial network pedestrian trajectory prediction model, which considers information between pedestrians and vehicles and analyzes the state of pedestrian-vehicle-interactions under various decisions through microscopic motion factors and macroscopic game decisions. The experimental results show that the proposed model is more accurate and explanatory than traditional pedestrian trajectory prediction models, such as long short-term memory (LSTM), Social LSTM, Social generative adversarial network(S-GAN), and Sophie.
资助项目	Science and Technology Innovation Key Research and Development Program of Chongqing
WOS研究方向	Engineering ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:001230781300001
资助机构	Science and Technology Innovation Key Research and Development Program of Chongqing
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/58464]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者	Li, Lingxi
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Shandong Jiaotong Univ, Shandong Key Lab Smart Transportat Preparat, Jinan 250353, Peoples R China 3.Chinese Acad Sci, Inst Automat, State Key Lab Multimodal Artificial Intelligence S, Beijing 100190, Peoples R China 4.Indiana Univ Purdue Univ Indianapolis, Dept Elect & Comp Engn, Indianapolis, IN 46202 USA 5.Chongqing Univ Technol, Key Lab Adv Mfg Technol Automobile Parts, Int Joint Lab Intelligent Mfg Control Key Parts En, Minist Educ, Chongqing 400050, Peoples R China
推荐引用方式 GB/T 7714	Li, Wenli,Zhang, Yinan,Li, Lingxi,et al. A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2024:16.
APA	Li, Wenli,Zhang, Yinan,Li, Lingxi,Lv, Yisheng,&Wang, Mengxin.(2024).A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,16.
MLA	Li, Wenli,et al."A Pedestrian Trajectory Prediction Model for Right-Turn Unsignalized Intersections Based on Game Theory".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2024):16.