How does drivers’ trust in vehicle automation affect non-driving-related task engagement, vigilance, and initiative takeover performance after experiencing system failure?

Transportation Research Part F Traffic Psychology and Behaviour, Год журнала: 2023, Номер 98, С. 73 - 90

Опубликована: Сен. 13, 2023

Язык: Английский

---

Exploring driving anger-caused impairment of takeover performance among professional taxi drivers during partially automated driving

Accident Analysis & Prevention, Год журнала: 2024, Номер 205, С. 107686 - 107686

Опубликована: Июнь 22, 2024

Язык: Английский

---

Impact of non-driving related task types, request modalities, and automation on driver takeover: A meta-analysis

Safety Science, Год журнала: 2024, Номер 181, С. 106704 - 106704

Опубликована: Ноя. 1, 2024

Язык: Английский

---

How do visual and cognitive non-driving related tasks affect drivers’ visual attention and takeover performance in conditionally automated driving?

Journal of Transportation Safety & Security, Год журнала: 2024, Номер unknown, С. 1 - 27

Опубликована: Июнь 17, 2024

This study examines changes in visual attention during drivers' engagement or cognitive NDRTs conditionally automated driving, and determines how these affect takeover performance. Seventy-five participants took part a driving simulator study, performing three pre-takeover tasks: the an auditory-imagery-verbal task (cognitive NDRT); video-watching (visual monitoring (baseline/non NDRT). Also, there were two hazardous events (breakdown sudden merging of vehicle ahead) leading to requests issued with 7-s 5-s lead times. The results revealed that negatively affected attention, which caused lower saccade frequency between different areas interest shorter amplitude. Drivers paid more road ahead in-vehicle information system when NDRTs, respectively. drivers performance (e,g longer reaction time, heavier maximal brake pedal input, etc.). reduction request time impaired findings will support design eye tracker-based "out-of-loop" discrimination techniques human-machine interaction interfaces vehicles. contributes literature by examining types performance, specifically focusing on attention.

Язык: Английский

---

Identifying factors affecting driver takeover time and crash risk during the automated driving takeover process

Journal of Transportation Safety & Security, Год журнала: 2025, Номер unknown, С. 1 - 26

Опубликована: Янв. 10, 2025

This study aims to develop prediction models of driver takeover time and crash risks during the automated driving process. A simulator experiment was conducted collect vehicle trajectory behavior data. The random-parameter duration model first built time. Results indicated that young drivers, novice request lead time, traffic volume had varying impacts on due unobserved heterogeneity. Then, an explainable machine learning utilized predict explore various predictors' crashes. Validation results revealed developed provided satisfactory accuracy in predicting SHAP used interpret estimated by examining contributory factors' main effects interactive risks. Takeover risk is positively correlated with speed, maximum lateral acceleration, volume, tasks watching videos playing games. Additionally, longitudinal deceleration were found affect negatively. Research findings shed insights into modeling process, highlight importance considering heterogeneity drivers when designing systems (ADS) improve performance.

Язык: Английский

---

Comprehensive assessment of mental workload of armored vehicle operators based on SVM and DS evidence theory

Cognition Technology & Work, Год журнала: 2025, Номер unknown

Опубликована: Фев. 18, 2025

Язык: Английский

---

Multi-body sensor based drowsiness detection using convolutional programmed transfer VGG-16 neural network with automatic driving mode conversion

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Март 14, 2025

Язык: Английский

---

Exploring the effect of driver drowsiness on takeover performance during automated driving: An updated literature review

Accident Analysis & Prevention, Год журнала: 2025, Номер 216, С. 108023 - 108023

Опубликована: Апрель 3, 2025

Vehicle automation technology has considerable potential for reducing road crashes associated with human error, including issues related to driver drowsiness. However, before full becomes available on public roads, it will be essential drivers take back control from automated driving systems when requested. This poses a challenge drivers, particularly as may further exacerbate paper aims update systematic review published in 2022 (Merlhiot & Bueno, Accident Analysis and Prevention, 170, 106536), discuss factors affecting drowsiness takeover performance particular focus those not identified previous review. Following the Preferred Reporting Items Systematic Reviews Meta-analyses guidelines, three databases: Web of Science, PubMed Scopus were searched studies between March 2021 October 2024. The following eligibility criteria applied study inclusion: 1) participants must have interacted simulated or real-world vehicle featured Level 2 above; 2) at least one measurement indicator drowsiness; 3) performance; 4) conducted within controlled experimental design. From an initial selection 182 articles databases, total twelve obtained after removing duplicates, title, abstracts texts checking. Additionally, 17 included, resulting 29 this study. Driver (e.g, increased Karolinska Sleepiness Scale levels, blink frequency) tended increase both duration levels. Engaging non-driving tasks (NDRTs) alleviates lower heart rate percentage eye closure), but reduces (e.g., longer braking reaction times, stronger longitudinal acceleration, shorter minimal time collision). Compared older younger more susceptible drowsiness, while had worse delayed steering time, higher collision rates). Sleep inertia circadian rhythms also influencing performance. monitoring task helps prevent excessive participation NDRTs improves reduced brake times maximum velocity, minimum Digital voice assistants scheduled manual help maintain alertness decreased duration) enhance resume steering). There several limitations methodologies existing studies, among which were: lack verification through experiments; insufficient diversity singularity scenarios; failure reveal mechanism by affects Factors such driving, NDRT engagement, age, sleep-related levels influence development subsequent literature highlights necessary directions future research: what underlying affect over how occurrence alleviate once occurs; assist drowsy regain safely quickly.

Язык: Английский

---

Dual-perspective safety driver secondary task detection method based on swin-transformer and cross-attention

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103320 - 103320

Опубликована: Апрель 6, 2025

Язык: Английский

---

An integrated framework for driving risk evaluation that combines lane-changing detection and an attention-based prediction model

Traffic Injury Prevention, Год журнала: 2024, Номер unknown, С. 1 - 9

Опубликована: Окт. 2, 2024

In recent years, the increase in traffic accidents has emerged as a significant social issue that poses serious threat to public safety. The objective of this study is predict risky driving scenarios improve road

Язык: Английский

---