Lane Change Trajectory Prediction of Vehicles in Highway Interweaving Area Using Seq2Seq-attention Network

被引：0
作者：
Han H. [1 ]
Xie T. [1 ]
机构：
[1] College of Transport & Communications, Shanghai Maritime University, Shanghai
来源：
Zhongguo Gonglu Xuebao/China Journal of Highway and Transport | 2020年 / 33卷 / 06期
基金：
中国国家自然科学基金;
关键词：
Attention mechanism; Interweaving area lane change; LSTM; Seq2seq; Traffic engineering; Trajectory prediction; Vehicle interaction;
D O I：
10.19721/j.cnki.1001-7372.2020.06.010
中图分类号：
学科分类号：
摘要：
In highway interweaving areas with complex traffic states, experienced drivers can make timely lane changes by correctly inferring the future movements of surrounding vehicles. This is essential for safe and efficient autonomous driving. However, existing autonomous vehicles often lack this prediction ability. Therefore, in this study, a method is proposed to predict the mandatory lane change trajectories of vehicles in the highway interweaving area. This method combines an Attention Mechanism and sequence-to-sequence (Seq2Seq) network structure, using next generation simulation (NGSIM) data set to extract key features during vehicle lane-changing process, and introduces two types of risk indicators: time to collision (TTC) and deceleration rate to avoid a crash (DRAC). It treats the lane change vehicle and its surrounding vehicles as an overall state unit and simultaneously completes the spatio-temporal features of different vehicles in the state unit at lateral and longitudinal directions, to effectively describe the dynamic interaction between vehicles. Subsequently, the continuous window sequences of different observed vehicles are input into the Seq2Seq model, based on the long short-term memory (LSTM) network, to predict the future motion trajectories of lane change vehicles in the interweaving area, by adding a Soft Attention module. This module focuses on key information that affects the position change of vehicles at different times and reproduces the lane-changing behavior of vehicles in real traffic scenarios. The experimental verification results illustrate that the Seq2Seq-attention model has higher trajectory prediction accuracy than the currently popular models, such as ConvLSTM, XGBoost, especially for long-term horizon trajectory fitting. In addition, it provides new ideas for the development of assisted and autonomous driving. © 2020, Editorial Department of China Journal of Highway and Transport. All right reserved.
引用
收藏
页码：106 / 118
页数：12
相关论文
共 29 条
  • [1] DOLGOV D., Google Self-driving Car Project Monthly Report, (2016)
  • [2] PUEBOOBPAPHAN R, LIU F, VAN A B., The Impacts of a Communication Based Merging Assistant on Traffic Flows of Manual and Equipped Vehicles at an On-ramp Using Traffic Flow Simulation, Proceedings of the 13th International IEEE Conference on Intelligent Transportation Systems, pp. 1468-1473, (2010)
  • [3] MILANES V, GODOY J, VILLAGRA J, Et al., Automated On-ramp Merging System for Congested Traffic Situations, IEEE Transactions on Intelligent Transportation Systems, 12, 2, pp. 500-508, (2010)
  • [4] LIU Xiao-ming, WANG Xiu-ying, Study of Vehicle Lane-changing Behavior Model of Cellular Automata Based on Information Interaction, Application Research of Computers, 27, 10, pp. 3826-3828, (2010)
  • [5] DONG Chang-yin, Control Strategy for Autonomous Vehicles on Off-ramp Route Optimization, (2016)
  • [6] YUAN Wei, FU Rui, GUO Ying-shi, Et al., Drivers' Lane Changing Intention Identification Based on Visual Characteristics, China Journal of Highway and Transport, 26, 4, pp. 132-138, (2013)
  • [7] SCHAKELW J, KNOOP V L, VAN A B., Integrated Lane Change Model with Relaxation and Syn-chronization, Transportation Research Record, 2316, 1, pp. 47-57, (2012)
  • [8] LI Gen, Merging Model in Freeway Weaving Section Based on Gradient Boosting Decision Tree, Journalof Southeast University: Natural Science Edition, 48, 3, pp. 563-567, (2018)
  • [9] HOU Y, EDARA P, SUN C., Situation Assessment and Decision Making for Lane Change Assistance Using Ensemble Learning Methods [J], Expert Systems with Applications, 42, 8, pp. 3875-3882, (2015)
  • [10] MA Yong, FU Rui, GUO Ying-shi, Et al., Multi-parameter Prediction of Driver's Lane Change Behavior Based on Real-world Driving Tests, Journal of Chang'an University: Natural Science Edition, 34, 5, pp. 101-108, (2014)
123