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
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 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
    相似文献
    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