The primary objective of this project is to explore how machine learning and AI can enhance the analysis of data collected by a high-fidelity driving simulator and integrated eye tracking. By utilizing these advanced technologies, we gain deeper insights into driver behavior, identify potential risk factors, and develop effective interventions to improve transportation safety.
Total project length: 175 hours
Driver Distraction Detection: Students can develop machine learning models that analyze eye tracking data to detect signs of driver distraction, such as prolonged gaze away from the road. This project would involve training models on the collected data and developing a real-time system for distraction detection.
Object Detection and Tracking: Machine learning models can be trained to detect and track various objects in video streams, such as vehicles, pedestrians, traffic signs, or road markings. This enables automated analysis of the interactions between the driver and the surrounding environment, providing insights into driving behavior and potential safety hazards.
Driving Style Classification: Students can develop machine learning models to classify different driving styles based on the data collected from the driving simulator. This project would involve training models to recognize patterns in driving behavior and categorize drivers into different styles, such as aggressive, cautious, or distracted.
Predictive Modeling for Crash Risk: Students can build machine learning models that integrate data from the driving simulator, eye tracking, and real-world crash reports to predict crash risk. This project would involve training models to identify factors that contribute to crashes and develop a predictive model to estimate the likelihood of crashes in different scenarios.
Gaze Analysis: With eye tracking data integrated into the driving simulator studies, machine learning techniques can be employed to analyze gaze patterns. AI models can identify regions of interest, determine the duration of fixations, and understand the driver’s visual attention during different driving scenarios. This analysis can reveal insights into driver distraction, hazard perception, and cognitive workload.
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
Intermediate
Please use this link to access the test for this project.
Please DO NOT contact mentors directly by email. Instead, please email human-ai@cern.ch with Project Title and include your CV and test results. The mentors will then get in touch with you.