Effects of Adopting Voice Assistants Countermeasures on Alerting Drowsy Drivers

Drowsy driving is one of the leading contributing factors to traffic accidents. As drivers continue driving despite being aware of their drowsy states, it is necessary to adopt active countermeasures to avoid them falling asleep behind the wheel. Based on the multiple resources model, this study proposed five countermeasure types using voice assistants (no countermeasure vs. meaninglessly listening vs. meaningfully listening vs. repeating vs. answering) and investigated their effects on countering drowsiness of younger (25-35 years) and middle-aged (36-65 years) drivers. A simulated manual driving experiment with 29 participants was conducted to evaluate the effectiveness of countermeasures on driving behaviors, physiological indicators, eye movement indicators, and subjective ratings. All results indicated that the repeating and answering conditions were the most effective in alerting drowsy drivers, suggesting that countermeasures involving more human resource stages can enhance alertness. The trend of higher alertness in the answering condition compared to the repeating condition highlighted the potential advantage of increasing cognitive load in countering drowsiness. Listening conditions showed limited effects on alerting drivers but no adverse effects on driving performance or worsening drowsiness. Regarding age, younger and middle-aged drowsy drivers did not differ on average in response to different countermeasures. However, considering individual differences in physiological activation in reacting to countermeasures, drowsiness countermeasures should be tailored to the individual needs, particularly for middle-aged drivers. Apart from facilitating the understanding of drowsiness countermeasure mechanisms, the present findings provided implications for vehicle designers and engineers in utilizing in-vehicle voice assistants as an effective drowsiness countermeasure.