Rafael Cirino Gonçalves
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rafael Cirino Gonçalves has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Natasha Merat
University of Leeds, Leeds, United Kingdom
8 shared publications - Jonny Kuo
Seeing Machines Ltd., Canberra, Australia
6 shared publications - Jorge Pardo
Centre for Accident Research and Road Safety - Queensland (CARRS-Q), Queensland University of Technology, Brisbane, Australia
5 shared publications - Ronald Schroeter
Queensland University of Technology, Brisbane, Australia
5 shared publications - Mike Lenné
Seeing Machines Ltd., Melbourne, Australia
4 shared publications - Courtney Michael Goodridge
Institute for Transport Studies, University of Leeds, Leeds, United Kingdom
3 shared publications
Latest Publications
- Open Access
- 31 July 2026
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 236, 108681
Drivers have constrained cognitive resources under cognitive and visual distraction: Safety implications for transitions of control from vehicle automation
- 31 July 2026
- Published by Elsevier in Accident Analysis & Prevention
- Vol. 236, 108681
Open AccessDrivers have constrained cognitive resources under cognitive and visual distraction: Safety implications for transitions of control from vehicle automation
- Open Access
- 31 March 2026
- Published by Elsevier in SSRN Electronic Journal
Drivers have Impaired Working Memory under High Cognitive Load and Visual Distraction: Safety Implications for Transitions of Control from Vehicle Automation
The objective of this study was to evaluate the effect of both cognitive load and visual distraction on drivers’ gaze behaviour and takeover performance during an SAE Level 2 automated drive. A driving simulator study was conducted where drivers needed to take over control during a safety critical scenario i) while engaged in an auditory version of the 2-back task (cognitive load), ii) during ambient occlusion of the driving scene (visual distraction) or iii) a combination of both. In line with previous studies, results showed that, under the 2-back task, drivers showed a lower horizontal dispersion of gaze for scanning the environment. In the ambient occlusion condition, drivers compensated for the temporary absence of the driving scene by dispersing their gaze vertically and towards offroad areas of the environment. In terms of their takeover performance, the results found no significant differences between cognitive load and visual distraction manipulations alone. However, drivers’ performance was significantly worse, when both manipulations were combined. The findings suggest that both visual distraction and cognitive load may tax drivers’ working memory and consequently impact their takeover performance. This finding is relevant for future development of driver monitoring systems, which should consider the impact of cognitive load on drivers’ performance, even if their eyes are facing towards the road.
- 31 March 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessDrivers have Impaired Working Memory under High Cognitive Load and Visual Distraction: Safety Implications for Transitions of Control from Vehicle Automation
The objective of this study was to evaluate the effect of both cognitive load and visual distraction on drivers’ gaze behaviour and takeover performance during an SAE Level 2 automated drive. A driving simulator study was conducted where drivers needed to take over control during a safety critical scenario i) while engaged in an auditory version of the 2-back task (cognitive load), ii) during ambient occlusion of the driving scene (visual distraction) or iii) a combination of both. In line with previous studies, results showed that, under the 2-back task, drivers showed a lower horizontal dispersion of gaze for scanning the environment. In the ambient occlusion condition, drivers compensated for the temporary absence of the driving scene by dispersing their gaze vertically and towards offroad areas of the environment. In terms of their takeover performance, the results found no significant differences between cognitive load and visual distraction manipulations alone. However, drivers’ performance was significantly worse, when both manipulations were combined. The findings suggest that both visual distraction and cognitive load may tax drivers’ working memory and consequently impact their takeover performance. This finding is relevant for future development of driver monitoring systems, which should consider the impact of cognitive load on drivers’ performance, even if their eyes are facing towards the road.
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 245-249
It Matters Who Is Behind The Wheel: Driver Monitoring Feature Analysis Using Explainable AI
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 245-249
Open AccessIt Matters Who Is Behind The Wheel: Driver Monitoring Feature Analysis Using Explainable AI
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 145-150
Self-supervised Learning for Detecting Local Contextual Anomalous Gaze Patterns of Individual Drivers in Level 3 Automated Driving
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 145-150
Open AccessSelf-supervised Learning for Detecting Local Contextual Anomalous Gaze Patterns of Individual Drivers in Level 3 Automated Driving
- Open Access
- 21 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 198-207
Drivers’ Attention to Dash-Based Human-Machine Interfaces: The Effect of Partial Automation and Cognitive Load
- 21 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 198-207
Open AccessDrivers’ Attention to Dash-Based Human-Machine Interfaces: The Effect of Partial Automation and Cognitive Load
- Open Access
- 21 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 26-35
Measuring Driver Electrodermal Activity when Exposed to HMIs Conveying Uncertainty in Conditional Automated Driving
- 21 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 26-35
Open AccessMeasuring Driver Electrodermal Activity when Exposed to HMIs Conveying Uncertainty in Conditional Automated Driving
- Open Access
- 30 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 395-407
Using gaze to understand shifts in visual attention during conditional automation with non-driving related tasks
- 30 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 395-407
Open AccessUsing gaze to understand shifts in visual attention during conditional automation with non-driving related tasks
- Open Access
- 22 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 161-165
Markov Chain Analysis of Gaze Transitions: Assessing Attention Management in SAE Level 3 Automated Driving
This work-in-progress examines how the use of different non-driving related task (NDRT) interfaces (mobile phone vs. head-up display and baseline) influences drivers’ visual attention and scanning strategies during conditional automated driving. We present preliminary findings from a driving simulator study (N=46) that utilised Markov Chain analysis of gaze transitions and gaze dispersion metrics. Results show that NDRTs, particularly on mobile phones, compromise drivers’ attention distribution and gaze transitions. While HUDs keep drivers’ gaze closer to the road, they may still hinder hazard perception. Markov Chain analysis reveals valuable insights into drivers’ attention management, informing the design of safer in-vehicle interfaces for automated vehicles. These findings highlight the need for careful consideration when designing in-vehicle interfaces and NDRT interactions for automated vehicles.
- 22 September 2024
- Published by Association for Computing Machinery (ACM)
- p. 161-165
Open AccessMarkov Chain Analysis of Gaze Transitions: Assessing Attention Management in SAE Level 3 Automated Driving
This work-in-progress examines how the use of different non-driving related task (NDRT) interfaces (mobile phone vs. head-up display and baseline) influences drivers’ visual attention and scanning strategies during conditional automated driving. We present preliminary findings from a driving simulator study (N=46) that utilised Markov Chain analysis of gaze transitions and gaze dispersion metrics. Results show that NDRTs, particularly on mobile phones, compromise drivers’ attention distribution and gaze transitions. While HUDs keep drivers’ gaze closer to the road, they may still hinder hazard perception. Markov Chain analysis reveals valuable insights into drivers’ attention management, informing the design of safer in-vehicle interfaces for automated vehicles. These findings highlight the need for careful consideration when designing in-vehicle interfaces and NDRT interactions for automated vehicles.
- Open Access
- 18 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 256-259
What do we mean by cognitive load? Towards more accurate definition of the term for better identification by driver monitoring systems
- 18 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 256-259
Open AccessWhat do we mean by cognitive load? Towards more accurate definition of the term for better identification by driver monitoring systems