摘要
Intersections are quite important and complex traffic scenarios,where the future motion of surrounding vehicles is an indispensable reference factor for the decision-making or path planning of autonomous vehicles.Considering that the motion trajectory of a vehicle at an intersection partly obeys the statistical law of historical data once its driving intention is determined,this paper proposes a long short-term memory based(LSTM-based)framework that combines intention prediction and trajectory prediction together.First,we build an intersection prior trajectories model(IPTM)by clustering and statistically analyzing a large number of prior traffic flow trajectories.The prior trajectories model with fitted probabilistic density is used to approximate the distribution of the predicted trajectory,and also serves as a reference for credibility evaluation.Second,we conduct the intention prediction through another LSTM model and regard it as a crucial cue for a trajectory forecast at the early stage.Furthermore,the predicted intention is also a key that is associated with the prior trajectories model.The proposed framework is validated on two publically released datasets,next generation simulation(NGSIM)and INTERACTION.Compared with other prediction methods,our framework is able to sample a trajectory from the estimated distribution,with its accuracy improved by about 20%.Finally,the credibility evaluation,which is based on the prior trajectories model,makes the framework more practical in the real-world applications.
基金
partly supported by the National Natural Science Foundation of China(61903034,U1913203,61973034,91120003)
the Program for Changjiang Scholars and Innovative Research Team in University(IRT-16R06,T2014224)
China Postdoctoral Science Foundation funded project(2019TQ0035)
Beijing Institute of Technology Research Fund Program for Young Scholars。
作者简介
Ting Zhang,received the B.S.degree in automation from Beijing Institute of Technology,China in 2018,where she received the Doctor recommendation qualification.She is currently a Ph.D.candidate for the third year in navigation guidance and control at the School of Automation,Beijing Institute of Technology,China.Her research interests include trajectories and behavioral predictions of unmanned vehicles in a variety of traffic environments,as well as prediction-based decision making and planning.e-mail:3120185483@bit.edu.cn;Corresponding author:Wenjie Song,received the B.S.and Ph.D.degrees from Beijing Institute of Technology,China,in 2013 and 2019,respectively.He studied in Princeton University as a Visiting Scholar from 2016 to 2017.He is currently an Assistant Professor with the School of Automation,Beijing Institute of Technology,Beijing,China.His research interests include autonomous driving,environmental perception,SLAM,path planning,etc.He has taken part in“China Intelligent Vehicle Future Challenge”for several times as the captain or the core member.e-mail:songwj@bit.edu.cn;Mengyin Fu,received the Ph.D.degree from Chinese Academy of Sciences,China.He is the President of Nanjing University of Science and Technology,China.His research interest covers integrated navigation,intelligent navigation,image processing,learning and recognition as well as their applications.He was elected as the Yangtze River Scholar Distinguished Professor in 2009,and won the Guanghua Engineering Science and Technology Award for Youth Award in 2010.He has got National Science and Technology Progress Award for several times in recent years.e-mail:fumy@bit.edu.cn;Yi Yang,received the Ph.D.degree in automation from Beijing Institute of Technology,Beijing,China,in 2010.He is currently a Professor with the School of Automation,Beijing Institute of Technology,Beijing,China.His research interests include autonomous vehicles,bioinspired robots,intelligent navigation,semantic mapping,scene understanding,motion planning and control,and robot design and development.He is author/co-author of more than 50 conference and journal papers in the area of unmanned ground vehicle.e-mail:yang_yi@bit.edu.cn;Meiling Wang,received the B.S.degree in automation from the Beijing Institute of Technology,China,in 1992,and the M.S.and Ph.D.degrees from Beijing Institute of Technology,China,in 1995 and 2007,respectively.She has been teaching in Beijing Institute of Technology since 1995,and worked in University of California San Diego as a Visiting Scholar in 2004.She is currently the Director of Integrated Navigation and Intelligent Navigation Laboratory,Beijing Institute of Technology,China.Her research interests include advanced technology of sensing and detecting and vehicle intelligent navigation.She was elected as the Yangtze River scholar Distinguished Professor in 2014.e-mail:wangml@bit.edu.cn。
