Visual Attention Patterns in Automated and Manual Lane Change Maneuvers

Author:

Noonan T. Zach1,Gershon Pnina1,Mehler Bruce1,Reimer Bryan1

Affiliation:

1. MIT Center for Transportation & Logistics, AgeLab, Cambridge, MA, USA

Abstract

Tesla auto lane change is a feature which automatically steers the vehicle into an adjacent lane when prompted by the driver. 2,473 naturalistic motorway lane changes were annotated to compare driver eye glance behavior before, during, and after maneuvers performed manually and with automation. Change point detection and glance area prevalence revealed distinct patterns in the drivers’ glance behavior. In manual lane changes drivers had more glances to adjacent lanes and over-the-shoulder prior to and during lane crossing compared to automated lane changes which were associated with fewer glances laterally but more glances to the rearview mirror. These differences were more pronounced in lane changes into the leftmost lane. However, in automated exiting maneuvers, drivers had more preparatory glances to adjacent lanes compared to manual. These behaviors could be related to differences in driver visual attention associated with the use of automation.

Publisher

SAGE Publications

Subject

General Medicine,General Chemistry

Reference16 articles.

1. Barry K. (2018, November 2). Tesla’s Navigate on Autopilot Shows the Promise and Problems of Self-Driving Cars. Consumer Reports. https://www.consumerreports.org/autonomous-driving/teslanavigate-on-autopilot-shows-promise-and-problems-of-selfdriving-cars/

2. Chovan J. D., Tijerina L., Alexander G., Hendricks D. L. (1994). Examination of Lane Change Crashes and Potential Ivhs Countermeasure (HS-808 071). Article HS-808 071. https://trid.trb.org/view/454117

3. Investigating Improper Lane Changes: Driver Performance Contributing to Lane Change Near-Crashes

4. MIT Advanced Vehicle Technology Study: Large-Scale Naturalistic Driving Study of Driver Behavior and Interaction With Automation

5. The Effect of Partial Automation on Driver Attention: A Naturalistic Driving Study

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3