On the Forces of Driver Distraction: Explainable Predictions for the Visual Demand of In-Vehicle Touchscreen Interactions
URL: http://arxiv.org/abs/2301.02065v1
archive: archived pipeline: cataloged verified
Abstract
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 touchscreen Human-Machine Interfaces (HMIs) 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 2.4 s. 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.
Summary
HFES conference proceedings report (Aspire Conference) documenting N-back temporal instability findings. Two-experiment study showing N-back performance improvement and workload decrease over 26+ on-road driving sessions. Experiment 1: 10 participants with 26+ exposures show systematic accuracy increases and cognitive demand decreases. Experiment 2: Old vs New digit sequences tested with 20 participants; equivalent performance confirms strategy-based improvement.
Key finding
N-back accuracy and DRT-based workload measures show systematic drift over repeated on-road sessions, with improvements attributable to general strategy acquisition (subvocal rehearsal, automatization) rather than sequence-specific learning.
Methodology
Exp 1: 10 participants, repeated measures across 6 sessions from 26 total. Exp 2: 20 participants, Old/New sequence comparison. On-road driving paradigm with DRT and NASA-TLX measures.
Sample size: Exp 1: N=10; Exp 2: N=20
Quality score: 5 / 5