Trajectory prediction of cyclist based on dynamic Bayesian network and long short-term memory model at unsignalized intersections  

作　　者：Hongbo GAO Hang SU Yingfeng CAI Renfei WU Zhengyuan HAO Yongneng XU Wei WU Jianqing WANG Zhijun LI Zhen KAN 

机构地区：[1]Department of Automation,University of Science and Technology of China,Hefei 230026,China [2]Institute of Advanced Technology,University of Science and Technology of China,Hefei 230088,China [3]The Dipartimento di Elettronica,Informazione e Bioingegneria,Politecnico di Milano,Milano 20133,Italy [4]Automotive Engineering Research Institute,Jiangsu University,Zhenjiang 212013,China [5]College of Traffic and Transportation,Southeast University,Nanjing 210018,China [6]School of Automation,Nanjing University of Science and Technology,Nanjing 210094,China [7]School of Vehicle and Mobility,Tsinghua University,Beijing 100084,China

出　　处：《Science China(Information Sciences)》2021年第7期100-112,共13页中国科学（信息科学）（英文版）

基　　金：This work was supported in part by National Natural Science Foundation of China(Grant Nos.U1804161,U2013601,U20A20225);Key Research and Development Plan of Anhui Province(Grant No.202004a05020058);Fundamental Research Funds for the Central Universities,Science and Technology Innovation Planning Project of Ministry of Education of China,NVIDIA NVAIL program,and Key Laboratory of Advanced Perception and Intelligent Control of High-end Equipment of Ministry of Education(Anhui Polytechnic University,Wuhu,China,241000)(Grant No.GDSC202007);And experiments are conducted on NVIDIA DGX-2.

摘　　要：Cyclist trajectory prediction is of great significance for both active collision avoidance and path planning of intelligent vehicles.This paper presents a trajectory prediction method for the motion intention of cyclists in real traffic scenarios.This method is based on dynamic Bayesian network(DBN)and long short-term memory(LSTM).The motion intention of cyclists is hard to predict owing to potential large uncertainties.The DBN is used to infer the distribution of cyclists’intentions at intersections to improve the prediction time.The LSTM with encoder-decoder is used to predict the cyclists’trajectories to improve the accuracy of prediction.Therefore,the DBN and LSTM are adopted to guarantee prediction accuracy and improve the prediction time.The experiment results are presented to show the effectiveness of the predict strategies.

关 键 词：trajectory prediction dynamic Bayesian network(DBN) long short-term memory(LSTM) unsignalized intersections motion intention 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程] U491[自动化与计算机技术—控制科学与工程]