Applications of AI and machine learning with eye tracking data in driving simulator scenarios


Surgical residents are a population prone to high work demands, rigorous schedules, and at risk of drowsy driving. The project above could detect key metrics as predictors of safety risk to residents, identifying when alternative modes of transportation or scheduling changes are recommended. The applications of AI and machine learning with eye tracking data in driving simulator scenarios can contribute to improving driver attention, safety, and overall performance. By analyzing eye movements, detecting fatigue, assessing cognitive load, and monitoring driver states, these techniques can enhance driver training programs, develop intelligent assistance systems, and promote safer driving practices. By applying innovative algorithms, we aim to advance transportation safety and driving behavior research. Some potential areas of exploration include real-time driver monitoring, drowsing driving detection, and predictive analysis for motor collision prevention.


Total project length: 175 hours

Task ideas

  1. Detect fatigued and drowsy driving from video data. AI algorithms can analyze eye tracking and facial observation cameras to detect signs of fatigue and drowsiness in drivers. By monitoring factors such as yawning, eye closure duration, and blink rate, AI can provide early warnings and interventions to prevent drowsy driving related crashes or near-crashes.
  2. Monitor driver state. AI can utilize eye tracking and facial observation video data to monitor a driver’s emotional state and cognitive load. This can help detect signs of stress, distraction, or frustration.
  3. Attention analysis: Machine learning algorithms can analyze eye tracking data to determine where drivers are focusing their attention during a potentially fatigued or drowsy state. This can provide insights into which areas of the environment drivers are prioritizing while drowsy or fatigued, such as road signs, pedestrians, or other vehicles. Understanding attention patterns can help improve road design, signage placement, and driver training programs.

Expected results


Proficiency in programming languages such as Python, Java, or C++, knowledge of machine learning frameworks, solid understanding of statistical analysis, data visualization, and data preprocessing.

Project difficulty level



Please use this link to access the test for this project.


Please DO NOT contact mentors directly by email. Instead, please email with Project Title and include your CV and test results. The mentors will then get in touch with you.

Corresponding Project

Participating Organizations