吉林大学学报(工学版)2024,Vol.54Issue(9) :2547-2556.DOI:10.13229/j.cnki.jdxbgxb.20221391

共驾型智能车辆人机接管行为序列编码与解析

Man-machine takeover behavior sequence coding and analysis of shared driving intelligent vehicle

严利鑫 曾涛 贺宜 郭军华 胡鑫辉
吉林大学学报(工学版)2024,Vol.54Issue(9) :2547-2556.DOI:10.13229/j.cnki.jdxbgxb.20221391

共驾型智能车辆人机接管行为序列编码与解析

Man-machine takeover behavior sequence coding and analysis of shared driving intelligent vehicle

严利鑫 1曾涛 1贺宜 2郭军华 1胡鑫辉1
扫码查看

作者信息

  • 1. 华东交通大学 交通运输工程学院,南昌 330013
  • 2. 武汉理工大学 智能交通系统研究中心,武汉 430063
  • 折叠

摘要

共驾型智能车辆同时具备人工驾驶和自动驾驶模式,其驾驶行为特性必将呈现新的特征.本文收集了15名被试人机接管的驾驶数据,采用符号聚合近似方法和视频录像标定法构建了驾驶行为特征图谱,通过最长公共子序列算法得出共通行为序列.结果表明,当车辆前方出现障碍物时,驾驶接管共通行为序列为:同时注视前方和制动踏板踩下-同时观察左后视镜和打开左转向灯-向左打方向盘-关闭左转向灯,该结论有助于提高智能车辆接管的有效性.

Abstract

Co-driving autonomous vehicles have manual and automated driving mode.The driving behavior characteristics of co-driving autonomous vehicles will show new characteristics.The driving behavior data of 15 drivers are collected.The characteristic map of driving behavior is constructed by using symbol aggregation approximation method and video recording calibration method.The common behavior sequence of autonomous vehicle man-machine takeover is excavated based on longest common subsequence algorithm.The results show that when obstacles appear in front of the autonomous vehicle the common behavior sequence is:looking ahead and pressing the brake pedal-observing the left rearview mirror and turning on the left turn signal-turning the steering wheel to the left-closing left turn signal.This study may helpful to improve the effectiveness of autonomous vehicle takeover.

关键词

交通运输系统工程/人机接管/驾驶行为/时间序列符号聚合近似方法/图谱

Key words

engineering of transportation and communication system/human-machine takeover/driving behavior/symbolic aggregate approximation/graph

引用本文复制引用

基金项目

国家自然科学基金项目(52162049)

国家自然科学基金项目(52262048)

国家自然科学基金项目(52072292)

江西省"赣鄱俊才支持计划"项目(20232BCJ23012)

江西省研究生创新专项资金项目(YC2021-S458)

出版年

2024
吉林大学学报(工学版)
吉林大学

吉林大学学报(工学版)

CSTPCD北大核心
影响因子:0.792
ISSN:1671-5497
段落导航相关论文