Assessing Cognitive Load for Driver State Detection

Mental overload while driving, caused by factors such as multitasking or excessive information, is a significant safety risk on the road. TModern driver monitoring systems aim to provide a comprehensive assessment of the driver to effectively respond to potential safety hazards in real time. Detecting cognitive load is a crucial element in advancing these driver monitoring systems.

Therefore, we are researching robust AI-based algorithms to detect overload in real time.

We are developing robust AI-based algorithms to detect cognitive overload in real time.

As a foundation for our algorithms, we have developed the multimodal Autonomous Driving Cognitive Load Assessment Database (ADABase) for detecting mental overload while driving, which includes:

• A specific study design tailored to the requirements and environments within the vehicle.
• Scientifically validated stimuli for inducting cognitive overload.
• Synchronized multimodal data acquisition to capture psycho-physiological states.

Study design

Stimuli for inducing overload

• n-back test: Gold standard method in psychological research
• k-drive test: Newly developed test concept, precisely adapted to the challenges of driving a car
  

Physiological responses: Synchronized recordings of multimodal biosignals

• Electroencephalography (EEG)
• Eyetracker
• Respiration rate
• Thermal camera
• Electrodermal activity (EDA)
• Oxygen saturation (sO2)
• Electromyography (EMG)
• Facial expression
• Electrocardiography (ECG)
• Heart rate variability (HRV)
• Photoplethysmography (PPG)
• Electrogastrography (EGG)

Behavioral responses

• Face and emotion analysis: Facial Action Coding System Action Units
• Performance parameters, such as hit rate and false positive rate
• Reaction time
• Direction of gaze (eye tracking)

Subjective experience measured by questionnaires

• NASA TLX questionnaires
• OCEAN personality traits