Abstract
This research paper explores the impact of cognitive load on drivers’ physiological state and driving performance during an automated driving to manual control transition scenario, using a driving simulator. Whilst driving in the automated mode, cognitive load was manipulated using the “N-Back” task, which participants engaged with via a visual display. Results suggest that non-optimal levels of workload during the automated driving conditions impair driving performance, especially lateral control of the vehicle, and the magnitude of this impairment varied with increasing cognitive load. In addition to these findings, the present paper introduces a novel method for determining stabilisation times of both driver state and driving performance indicators following a transition of vehicle control. Using this method we demonstrate that mean and standard deviation of lane position impairments were found to take longer to stabilise following transition to manual driving following a higher level of cognitive load during the automated driving period, taking up to 22 s for driving performance to normalise after take-over. In addition, heart rate parameters take between 20 and 30 s to stabilise following a planned take-over request. Finally, this paper demonstrates how the magnitude of cognitive load can be estimated in context of automated driving using physiological measures, captured by consumer electronic devices. We discuss the impact our findings have on the design of SAE Level 3 systems. Relevant suggestions are provided to the research community and automakers working on future implementation of vehicles capable of conditional automation.
| Original language | English |
|---|---|
| Article number | 105967 |
| Number of pages | 14 |
| Journal | Accident Analysis & Prevention |
| Volume | 151 |
| Early online date | 11 Jan 2021 |
| DOIs | |
| Publication status | Published - Mar 2021 |
Bibliographical note
NOTICE: this is the author’s version of a work that was accepted for publication in Accident Analysis & Prevention. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Accident Analysis & Prevention, 151, (2021) DOI: 10.1016/j.aap.2020.105967© 2021, Elsevier. Licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International http://creativecommons.org/licenses/by-nc-nd/4.0/
Funder
The financial support for this work was provided by Engineering & Physical Sciences Research Council (EPSRC) and Jaguar Land Rover (JLR).Keywords
- Automotive engineering
- Autonomous driving
- Biometrics
- Human factors
- Physiology
- Vehicle safety
ASJC Scopus subject areas
- Human Factors and Ergonomics
- Safety, Risk, Reliability and Quality
- Public Health, Environmental and Occupational Health
