考虑驾驶员模糊感知的深度学习跟驰模型
CSTR:
作者:
作者单位:

同济大学 道路与交通工程教育部重点实验室, 上海 201804

作者简介:

李林波(1974—),男,副教授,博士生导师,工学博士,主要研究方向为交通规划、交通拥挤管理等。 E-mail:llinbo@tongji.edu.cn

中图分类号:

U491.1

基金项目:

国家重点研发计划(2018YFE0102800);同济大学大型仪器设备开放测试基金(2021GX106)


Modeling of Car-Following Behaviors Considering Driver’s Fuzzy Perception Using Deep Learning
Author:
Affiliation:

Key Laboratory of Road and Traffic Engineering of the Ministry of Education,Tongji University,Shanghai 201084,China

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献 [26]
  • |
  • 相似文献 [20]
  • | | |
  • 文章评论
    摘要:

    为模拟驾驶人记忆效应以及模糊感知特性,设计了基于模糊感知时间窗的深度学习跟驰模型。提取highD数据集跟驰轨迹,以0.2 s最小时间间隔,连续3 s本车速度、前后车速度差、车头间距的时序数据作为模型输入,模拟驾驶记忆。训练深度学习跟驰模型,得出单层32个输出维度的门控循环单元(GRU)网络可以很好拟合实际数据。在每次输入模型的时序数据中,用模型预测值替换部分真实跟驰状态值,作为驾驶员对场景的估计,即模糊感知。实验得出对同一场景的不同模糊感知,可产生不同跟驰行为,模拟了驾驶行为的异质性,可为异质交通行为仿真提供方法。

    Abstract:

    In order to simulate driver's memory effects and fuzzy perception characteristics, a deep learning car-following model was designed based on fuzzy perception time window. Taking 3 s continuous speed, leading-following car speed difference and headway distance as model inputs with a minimum time interval of 0.2 s,the driving memory was simulated. A gated recurrent unit (GRU) network with a single layer of 32 output dimensions could fit the actual data well by training multiple groups of deep learning car-following models. In each input time series data of the model, part of the real car-following state value was replaced by the predicted value of the model as the driver’s estimation of the scenario, that is, fuzzy perception. The experiment results show that different fuzzy perceptions to the same scenario can produce different car following behaviors, and the heterogeneity of driving behaviors can be simulated, which provide a method for heterogeneous traffic behavior simulation.

    图1 路段2示意图Fig.1 Diagram of road segment 2
    图2 LSTM单元结构Fig.2 Structure of LSTM unit
    图3 GRU单元结构Fig.3 Structure of GRU unit
    图4 深度学习神经网络结构Fig.4 Structure of deep learning neural network
    图5 跟驰决策思维认知模拟图Fig.5 Cognitive simulation of car-following decision making
    图6 模糊感知时间窗设计图Fig.6 Diagram of fuzzy perception time window
    图7 模型性能比较Fig.7 Comparison of performance of models
    图8 GRU模型拟合结果图Fig.8 Diagram of model with GRU unit fitting results
    图9 不同场景下的模糊感知仿真结果Fig.9 Simulation results of fuzzy perception in different situation
    图10 多步模糊感知时间窗仿真Fig.10 Simulation results with different fuzzy perception windows
    图11 设计场景仿真结果Fig.11 Simulation results of designated scenario
    表 1 不同模型结构Table 1
    参考文献
    [1] 杨龙海,张春,仇晓赟,等. 车辆跟驰模型研究进展[J]. 交通运输工程学报, 2019, 19(5): 125.
    [2] DENOS C G, ROBERT H, RICHARD W R. Nonlinear follow-the-leader models of traffic flow[J]. Operations Research, 1961, 9(4):545.
    [3] GIPPS P G. A behavioural car-following model for computer simulation[J]. Transportation Research Part B: Methodological, 1981, 15(2) :105.
    [4] WIEDEMANN R. Simulation of road traffic in traffic flow[R]. Karlsruhe: University of Karlsruhe(TH), 1974.
    [5] BANDO M, HASEBE K, NAKAYAMA A, et al. Dynamical model of traffic congestion and numerical simulation[J]. Physical Review E, 1995, 51(2):1035.
    [6] TREIBER M, HENNECKE A, HELBING D. Congested traffic states in empirical observations and microscopic simulations[J]. Physical Review E, 2000,62(2):1805.
    [7] YU Shaowei, SHI Zhongke. An improved car-following model considering headway changes with memory[J]. Physica A: Statistical Mechanics and its Applications, 2015,421:1.
    [8] YU Shaowei , SHI Zhongke. An improved car-following model considering relative velocity fluctuation[J]. Communications in Nonlinear Science and Numerical Simulation, 2016, 36:319.
    [9] SUN Yuqing, GE Hongxia, CHENG Rongjun. An extended car-following model considering driver's memory and average speed of preceding vehicles with control strategy[J]. Physica A: Statistical Mechanics and its Applications, 2019, 521:752.
    [10] TANG T Q, HUANG H J, ZHAO S G, et al. An extended OV model with consideration of driver’s memory[J]. International Journal of Modern Physics B, 2009, 23(5):743.
    [11] CHAKROBORTY P,KIKUCHI S. Evaluation of the general motors based car-following models and a proposed fuzzy inference model[J]. Transportation Research Part C: Emerging Technologies,1999,7(4): 209.
    [12] 吴兵,罗雪,李林波. 考虑驾驶风格的模糊控制跟驰模型[J]. 同济大学学报(自然科学版),2020, 48(5): 694.
    [13] PANWAI S, DIA H. Development and evaluation of a reactive agent-Based car following model[C/CD]// Proceedings of the Intelligent Vehicles and Road Infrastructure Conference, 16th and 17th. Melbourne: Society of Automotive Engineers - Australasia, 2005.
    [14] WANG Xiao, JIANG Rui, LI Li, et al. Capturing car-following behaviors by deep learning [J]. IEEE Transaction on Intelligent Transportation Systems, Computers, Networks & Communications, 2018(19), 910.
    [15] HUANG Xiuling, SUN Jie, SUN Jian. A car-following model considering asymmetric driving behavior based on long short-term memory neural networks[J]. Transportation Research Part C: Emerging Technologies,2018,95:346.
    [16] 孙倩,郭忠印. 基于长短期记忆神经网络方法的车辆跟驰模型[J]. 吉林大学学报(工学版), 2020, 50(4): 1380.
    [17] WANG Xiao, JIANG Rui, Li Li.et al. Long memory is important: A test study on deep-learning based car-following model[J]. Physica A: Statistical Mechanics and its Applications, 2019,514:786.
    [18] ZHENG Jian, SUZUKI K, FUJITA M. Car-following behavior with instantaneous driver-vehicle reaction delay: A neural-network-based methodology[J]. Transportation Research Part C: Emerging Technologies, 2013,36: 339.
    [19] ZHOU Mofan, QU Xiaobo, LI Xiaopeng. A recurrent neural network based microscopic car following model to predict traffic oscillation[J]. Transportation Research Part C: Emerging Technologies, 2017,84:245.
    [20] 陆斯文,王俊骅. 基于ANFIS的高速公路车辆跟驰模型与仿真[J]. 同济大学学报(自然科学版),2010, 38(7): 1018.
    [21] COIFMAN B, LI Lizhe. A critical evaluation of the Next Generation Simulation (NGSIM) vehicle trajectory dataset[J]. Transportation Research Part B Methodological, 2017, 105:362.
    [22] RWTH Aachen University. Details about the dataset [EB/OL]. [2020-04-15]. https://www.highd-dataset.com/details.
    [23] KRAJEWSKI R, BOCK J, KLOEKER L, et al. The high D dataset: A drone dataset of naturalistic vehicle trajectories on German highways for validation of highly automated driving systems[C] // 21st International Conference on Intelligent Transportation Systems (ITSC). Maui, Hawaii, USA: IEEE, 2018: 2118-2125.
    [24] HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 2006,9(8):1735.
    [25] CHO K, MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. [C] // Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Doha: Association for Computational Linguistics, 2014: 1724-1734.
    [26] 王殿海, 陶鹏飞, 金盛, 等. 跟驰模型参数标定及验证方法[J]. 吉林大学学报(工学版), 2011,41(S1):59.
    引证文献
引用本文

李林波,李瑞杰,邹亚杰.考虑驾驶员模糊感知的深度学习跟驰模型[J].同济大学学报(自然科学版),2021,49(3):360~369

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-08-26
  • 在线发布日期: 2021-04-06
文章二维码