Driver Attention Assessment Using Physiological Measures from EEG, ECG, and EDA Signals.

Area of Science:

• Neuroscience
• Human-Computer Interaction
• Automotive Engineering

Background:

• Traditional driver attention monitoring relies on cameras, limiting its scope.
• Assessing driver mental state is crucial for road safety, especially with evolving autonomous systems.

Purpose of the Study:

• To evaluate driver mental attention using physiological signals (EDA, ECG, EEG).
• To compare mental workload and engagement levels between manual and autonomous driving scenarios.

Main Methods:

• Subjects drove in simulated highway environments under manual and autonomous conditions.
• Physiological data including electrodermal activity (EDA), electrocardiogram (ECG), and electroencephalogram (EEG) were recorded.
• Extracted features included blink rate, EEG beta band power, heart rate, and SPR characteristics.

Main Results:

• Statistical analysis confirmed manual driving elicited a more challenged mental state and higher attention.
• Physiological signals indicated greater mental workload during manual driving compared to autonomous driving.
• Results were consistent across different driving setups, reinforcing manual driving's higher cognitive demand.

Conclusions:

• The proposed method effectively monitors driver attention using physiological signals.
• Manual driving is demonstrably more mentally demanding than autonomous driving.
• This approach offers a robust alternative for assessing driver engagement and cognitive load.