Intention-Aware Lane Keeping Assist Using Driver Gaze Information

Paper in proceeding, 2023

A lane keeping assist system uses cameras and sensors to automatically steer the vehicle, whenever necessary, to keep it within the lanes. As the system is overriding the driver, it is therefore important that automatic interventions are only used when the driver is not aware of the situation, i.e., in cases of unintentional lane departures. Hence, one of the major challenges for such systems is to distinguish between intentional and unintentional driving behaviors. In this work, we implement an intention-aware lane keeping assist system based on machine learning, where the goal is to activate interventions only when the lane departure is unintentional. The system performance is evaluated using a real-world data set, partly consisting of unintentional lane departure events, normal driving, and intentional lane departure events, where the driver is making lane changes without using the turn indicator. The results show that driver state information, obtained from a camera-based gaze-tracking system, improves the lane keeping assist system's performance, especially for intentional lane departure events. It also shows that it is hard to predict the driver intention for prediction horizons longer than $1$~s.