On the forces of driver distraction: Explainable predictions for the visual demand of in-vehicle touchscreen interactions

• Published in: Accident analysis and prevention Vol. 183; p. 106956
• Main Authors: Ebel, Patrick, Lingenfelder, Christoph, Vogelsang, Andreas
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.04.2023
• Subjects: Accidents, Traffic - prevention & control; Automation; Automobile Driving; Distracted Driving; Driver distraction; Humans; In-vehicle information systems; Naturalistic driving data; Touchscreen interactions; Visual demand; Driver distraction; Visual demand; In-vehicle information systems; Naturalistic driving data; Touchscreen interactions
• ISSN: 0001-4575; 1879-2057
• DOI: 10.1016/j.aap.2023.106956

With modern infotainment systems, drivers are increasingly tempted to engage in secondary tasks while driving. Since distracted driving is already one of the main causes of fatal accidents, in-vehicle touchscreens must be as little distracting as possible. To ensure that these systems are safe to use, they undergo elaborate and expensive empirical testing, requiring fully functional prototypes. Thus, early-stage methods informing designers about the implication their design may have on driver distraction are of great value. This paper presents a machine learning method that, based on anticipated usage scenarios, predicts the visual demand of in-vehicle touchscreen interactions and provides local and global explanations of the factors influencing drivers’ visual attention allocation. The approach is based on large-scale natural driving data continuously collected from production line vehicles and employs the SHapley Additive exPlanation (SHAP) method to provide explanations leveraging informed design decisions. Our approach is more accurate than related work and identifies interactions during which long glances occur with 68% accuracy and predicts the total glance duration with a mean error of 2.4s. Our explanations replicate the results of various recent studies and provide fast and easily accessible insights into the effect of UI elements, driving automation, and vehicle speed on driver distraction. The system can not only help designers to evaluate current designs but also help them to better anticipate and understand the implications their design decisions might have on future designs. •ML approach to predict the visual demand of touchscreen interactions while driving.•Trained on 12,142 secondary task engagements during naturalistic driving.•SHAP-based explanations provide insights into drivers’ visual attention allocation.•Drivers’ visual attention allocation differs for different types of UI elements.•Drivers modulate their visual attention allocation based on the driving demand.