交通运输系统工程与信息

交通运输系统工程与信息 ›› 2021, Vol. 21 ›› Issue (1): 48-55.

• 智能交通系统与信息技术 • 上一篇    下一篇

基于自然驾驶跟车数据的驾驶人差异性分析与辨识

刘志强，张凯铎，倪捷*   

  1. 江苏大学，汽车与交通工程学院，江苏 镇江 212013
  • 收稿日期:2020-09-20 修回日期:2020-11-05 出版日期:2021-02-25 发布日期:2021-02-25
  • 作者简介:刘志强(1963- )，男，江苏靖江人，教授。
  • 基金资助:

    江苏省高校自然科学研究基金/Natural Science Foundation of the Higher Education Institutions of Jiangsu Province, China(17KJB580004)。

Analysis and Identification of Drivers' Difference in Car-following Condition Based on Naturalistic Driving Data

LIU Zhi-qiang, ZHANG Kai-duo, NI Jie*   

  1. School of Automobile and Traffic Engineering, Jiangsu University, Zhenjiang 212013, Jiangsu, China
  • Received:2020-09-20 Revised:2020-11-05 Online:2021-02-25 Published:2021-02-25

PDF

摘要：

为研究跟车工况下个体驾驶行为特性及其辨识，以驾驶人自然驾驶数据为基础，通过统计分析，频域分析及时频分析，多尺度对比驾驶人加速度、碰撞时间倒数、跟车时距等跟车轨迹特征参数分布的差异性；利用统计方法和离散小波变换提取能够表征驾驶人跟车习性差异的特征参数，分析不同参数输入结果，确定最优参数组合，建立基于随机森林的驾驶人差异性辨识模型；对 8位驾驶人的实车数据分析和辨识结果表明，以加速度，与前车相对速度、相对距离，跟车时距，碰撞时间倒数的平均值、标准差、中位数、小波能量熵为特征向量的随机森林模型，驾驶人识别的准确率能达到96.48%，袋外错误率为4.55%，相比于支持向量机、K近邻、BP神经网络，具有更高的识别准确性。说明运用多尺度细化特征向量建立的随机森林模型在识别跟车工况下驾驶人的差异性方面是可行的，该结果对驾驶行为精细化研究及个性化辅助驾驶系统发展具有重要意义。

关键词: 交通工程, 驾驶行为, 随机森林, 驾驶人识别, 跟车行为, 个体差异性

Abstract:

To study the behavior characteristics and identification of individual drivers in car-following condition, the differences in the distribution of car- following characteristics, including acceleration, relative speed, relative distance, time to headway (THW), time to collision (TTC), were compared based on naturalistic driving data by statistical analysis, frequency domain analysis and time- frequency analysis. The key features that characterize the difference in drivers' car- following behavior were extracted using statistical methods and discrete wavelet transform (DTW). A driver identification model based on Random Forest (RF) was established by using different parameters as the input vectors and determining the best parameters. The results of the naturalistic driving data from 8 drivers show that RF model with mean, standard deviation, median, and wavelet energy entropy of the acceleration, relative speed, relative distance, THW, TTC as feature vectors has an accuracy of 96.81% and an out- of- bag error rate of 4.55% in driver recognition. Compared with Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and BP Neural Network, RF model established by multi- scale feature vectors is effective to obtain higher recognition accuracy in driver identification under the car-following condition. This result is important for the refined research of driving behavior and the development of personalized driving assistance systems.

Key words: traffic engineering, driving behavior, random forest, driver identification；car- following behavior, individual difference

中图分类号: