{"title":"Detecting driver cognitive distraction in lane-change behavior: multi-source indicators from intention and execution phases","authors":"Jinshuan Peng , Chaoyu Ren , Xianghao Yang , Hao Yuan , Linjun Zhang","doi":"10.1016/j.trf.2025.103343","DOIUrl":null,"url":null,"abstract":"<div><div>Lane changes are critical driving maneuvers that pose increased risk under cognitive distractions, thereby comprising operational safety. This study investigated the interaction between cognitive distraction and lane-change behavior using a driving simulator combined with eye-tracking technology, aiming to detect drivers’ distracted states prior to lane-change maneuvers. The lane-change process was divided into two phases: intention and execution. Visual and vehicle control data were collected from drivers with varying driving experience under three states: calculation, conversation and normal driving. The analysis revealed that cognitive distraction delayed lane-change intention, shortened the intention time window, and increased instability in distance judgment and driving decisions. Specifically, distracted drivers maintained a shorter distance to the lead vehicle at the generation moment of lane-change intention, as well as a reduced gap to the trailing vehicle at the execution phase starting point. Distraction also caused more rigid visual scanning patterns, impaired information processing efficiency, and degraded speed regulation and maneuver timing, resulting in longer lane-change durations and poorer lateral and longitudinal control. Inexperienced drivers performed worse under distraction compared to experienced drivers, showing more unstable control behaviors, which increased the risk of lane-change operations. Finally, a cognitive distraction detection model using a random forest algorithm combined with a sliding time window achieved an accuracy of 91.67% in distinguishing distraction samples during the intention phase and 95% before crossing the lane boundary. The proposed method demonstrates strong real-time capabilities and offers valuable insights for developing advanced lane-change assistance systems.</div></div>","PeriodicalId":48355,"journal":{"name":"Transportation Research Part F-Traffic Psychology and Behaviour","volume":"115 ","pages":"Article 103343"},"PeriodicalIF":4.4000,"publicationDate":"2025-09-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transportation Research Part F-Traffic Psychology and Behaviour","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1369847825002980","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, APPLIED","Score":null,"Total":0}
引用次数: 0
Abstract
Lane changes are critical driving maneuvers that pose increased risk under cognitive distractions, thereby comprising operational safety. This study investigated the interaction between cognitive distraction and lane-change behavior using a driving simulator combined with eye-tracking technology, aiming to detect drivers’ distracted states prior to lane-change maneuvers. The lane-change process was divided into two phases: intention and execution. Visual and vehicle control data were collected from drivers with varying driving experience under three states: calculation, conversation and normal driving. The analysis revealed that cognitive distraction delayed lane-change intention, shortened the intention time window, and increased instability in distance judgment and driving decisions. Specifically, distracted drivers maintained a shorter distance to the lead vehicle at the generation moment of lane-change intention, as well as a reduced gap to the trailing vehicle at the execution phase starting point. Distraction also caused more rigid visual scanning patterns, impaired information processing efficiency, and degraded speed regulation and maneuver timing, resulting in longer lane-change durations and poorer lateral and longitudinal control. Inexperienced drivers performed worse under distraction compared to experienced drivers, showing more unstable control behaviors, which increased the risk of lane-change operations. Finally, a cognitive distraction detection model using a random forest algorithm combined with a sliding time window achieved an accuracy of 91.67% in distinguishing distraction samples during the intention phase and 95% before crossing the lane boundary. The proposed method demonstrates strong real-time capabilities and offers valuable insights for developing advanced lane-change assistance systems.
期刊介绍:
Transportation Research Part F: Traffic Psychology and Behaviour focuses on the behavioural and psychological aspects of traffic and transport. The aim of the journal is to enhance theory development, improve the quality of empirical studies and to stimulate the application of research findings in practice. TRF provides a focus and a means of communication for the considerable amount of research activities that are now being carried out in this field. The journal provides a forum for transportation researchers, psychologists, ergonomists, engineers and policy-makers with an interest in traffic and transport psychology.