Modeling Vehicle Interactions via Modified LSTM Models for Trajectory Prediction

被引:209
作者
Dai, Shengzhe [1 ,2 ]
Li, Li [1 ]
Li, Zhiheng [1 ,2 ]
机构
[1] Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Grad Sch Shenzhen, Shenzhen 518055, Peoples R China
基金
中国国家自然科学基金;
关键词
Trajectory prediction; vehicle interactions; shortcut connection; long short-term memory (LSTM); LANE;
D O I
10.1109/ACCESS.2019.2907000
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The long short-term memory (LSTM) model is one of the most commonly used vehicle trajectory predicting models. In this paper, we study two problems of the existing LSTM models for long-term trajectory prediction in dense traffic. First, the existing LSTM models cannot simultaneously describe the spatial interactions between different vehicles and the temporal relations between the trajectory time series. Thus, the existing models cannot accurately estimate the infiuence of the interactions in dense traffic. Second, the basic LSTM models often suffer from vanishing gradient problem and are, thus, hard to train for long time series. These two problems sometimes lead to large prediction errors in vehicle trajectory predicting. In this paper, we proposed a spatio-temporal LSTM-based trajectory prediction model (ST-LSTM) which includes two modifications. We embed spatial interactions into LSTM models to implicitly measure the interactions between neighboring vehicles. We also introduce shortcut connections between the inputs and the outputs of two consecutive LSTM layers to handle gradient vanishment. The proposed new model is evaluated on the I-80 and US-101 datasets. Results show that our new model has a higher trajectory predicting accuracy than one state-of-the-art model [maneuver-LSTM (M-LSTM)].
引用
收藏
页码:38287 / 38296
页数:10
相关论文
共 29 条
[1]   Social LSTM: Human Trajectory Prediction in Crowded Spaces [J].
Alahi, Alexandre ;
Goel, Kratarth ;
Ramanathan, Vignesh ;
Robicquet, Alexandre ;
Li Fei-Fei ;
Savarese, Silvio .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :961-971
[2]  
Altché F, 2017, IEEE INT C INTELL TR
[3]  
[Anonymous], 2016, PROC CVPR IEEE, DOI DOI 10.1109/CVPR.2016.573
[4]  
Aoude G., 2011, INFOTECH AEROSPACE 2, P1512, DOI DOI 10.2514/6.2011-1512
[5]   Driver Behavior Classification at Intersections and Validation on Large Naturalistic Data Set [J].
Aoude, Georges S. ;
Desaraju, Vishnu R. ;
Stephens, Lauren H. ;
How, Jonathan P. .
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS, 2012, 13 (02) :724-736
[6]  
Deo N, 2018, IEEE INT VEH SYM, P1179, DOI 10.1109/IVS.2018.8500493
[7]   How Would Surround Vehicles Move? A Unified Framework for Maneuver Classification and Motion Prediction [J].
Deo, Nachiket ;
Rangesh, Akshay ;
Trivedi, Mohan M. .
IEEE TRANSACTIONS ON INTELLIGENT VEHICLES, 2018, 3 (02) :129-140
[8]  
Goodfellow I, 2016, ADAPT COMPUT MACH LE, P1
[9]  
Gosain A, 2017, 2017 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), P79, DOI 10.1109/ICACCI.2017.8125820
[10]  
Guo CS, 2016, IEEE INT VEH SYM, P1279, DOI 10.1109/IVS.2016.7535555