When Context Dominates: Multimodal Signatures of Takeover Readiness Under Varying Hazard and Cognitive Load Conditions

Jul 16, 2026

Upload by Skyler

Semi-automated driving systems reduce crashes by assisting perception and control, but they also increase human-factors demands: drivers must monitor automation and resume control quickly after failures. Prolonged passive monitoring can lower vigilance and delay reactions, while the joint influence of hazard context, distraction, and drivers’ cognitive/physiological states on takeover performance remains insufficiently resolved. A controlled within-subject simulator experiment evaluates these interactions using multimodal vehicle, workload, autonomic, and fNIRS measures, highlighting hazard context as dominant and enabling adaptive driver monitoring.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages57

Reading Time2 h 24 min

Abstract

Introduction

Motivation: crashes, distraction, and semi-automation

Takeover readiness and the role of internal state

Gap in evidence and study purpose

arXiv :2607 . 10945v1 [ cs .HC] 12 Jul 2026 When Context Dominates: Multimodal Signatures of Takeover Readiness Under Varying Hazard and Cognitive Load Conditions Shiva Azimia , Yasaman Hakiminejada , Luis Gomerob , Elizabeth Pantescoc , Irene P. Kanc , Meltem Izzetoglub , Arash Tavakolia a Department of Civil and Environmental Engineering, Villanova University, 800 E Lancaster Ave, Villanova, 19085, PA, US b Department of Electrical and Computer Engineering, Villanova University, 800 E Lancaster Ave, Villanova, 19085, PA, US c Department of Psychological and Brain Sciences, Villanova University, 800 E Lancaster Ave, Villanova, 19085, PA, US Abstract Semi-automated driving systems promise to reduce crashes by assisting with perception and control, yet they simultaneously introduce additional human factors challenges by requiring drivers to monitor automation and rapidly resume control when failures occur. Prolonged passive monitoring can degrade vigilance, delay reactions, and increase takeover risk, but the extent to which distraction, hazard context, and drivers’ underlying cognitive and physiological states jointly shape takeover performance remains insufficiently understood. This study investigates these interacting factors using a controlled, within-subjects driving simulator experiment that crosses two hazard types (dynamic pedestrian and static crash events) with three levels of secondary task engagement (no task, conversation, and working memory load) . Driver responses were assessed using a multimodal sensing framework that integrates vehicle-dynamics measures, subjective workload ratings, autonomic physiology (electrodermal activity and heart rate variability), and prefrontal cortical activation measured with functional near-infrared spectroscopy. Results show that hazard context is the primary determinant of takeover behavior, with pedestrian events producing longer and more variable maneuversand crash events yielding faster and more stable responses. Secondary tasks exerted smaller effects on objective vehicle control, while internal-state measures showed more variable task-related patterns. These findings highlight the importance of jointly considering environmental context and human state when evaluating takeover readiness and designing driver monitoring systems. This study lays the groundwork for adaptive, context-aware strategies that support safer human–automation collaboration in semi-automated vehicles. Keywords: Semi-automated driving, Driver takeover performance, Driver distraction, Cognitive workload, Driver monitoring systems, Multimodal sensing, Physiological signals, Human–automation interaction 1. Introduction Motor vehicle crashes remain a leading cause of injury and death worldwide, with over 40,000 fatalities annually in the United States alone [63] . Beyond their tragic human toll, these incidents impose substantial economic costs through lost productivity, property damage, and medical expenses. A large proportion of these crashes stem from human error, and among the most pervasive contributors is driver distraction [45, 65] . Distraction, whether cognitive, visual, or manual, undermines situational awareness and delays reaction times during critical moments, making it one of the most pressing safety challenges in modern transportation systems [67, 51] . Automated driving technologies have emerged as a powerful tool to address these challenges. By delegating aspects of perception, decision-making, and control to machines, automation promises to reduce the frequency of human-induced crashes, enhance roadway efficiency, and mitigate driver fatigue [23, 87] . The progression from advanced driver-assistance systems (ADAS) to higher levels of automation has already begun to reshape the landscape of personal mobility. Automated features such as adaptive cruise control, lane-keeping assistance, and collision avoidance have demonstrated their capacity to support drivers in ro

FAQs

What is the primary factor shaping takeover behavior in the study?

Hazard context is identified as the primary determinant, with pedestrian events producing longer and more variable maneuvers and crash events yielding faster and more stable responses.

How were hazard types and distraction levels arranged in the experiment?

The study uses a controlled within-subject simulator design that crosses two hazard types (dynamic pedestrian and static crash events) with three secondary-task conditions (no task, conversation, and working memory load).

What sensing modalities were used to assess drivers’ takeover readiness?

Takeover responses were evaluated with a multimodal framework combining vehicle-dynamics measures, subjective workload ratings, autonomic physiology (electrodermal activity and heart-rate variability), and prefrontal cortical activation via functional near-infrared spectroscopy.

Jul 16, 2026

Upload by Skyler