Enhancing Older Adults' Safe Use of Automated Vehicles Using Eye-Tracking Data

Explore a research presentation on enhancing the safety of older adults using automated vehicles. Delve into the concept of mode confusion in automated driving and its particular relevance for older drivers. Learn about a proposed design framework for Driver State Monitoring systems that uses eye-tracking data to detect mode confusion in older drivers. Discover how the study utilized classification models trained on eye-tracking features, with a focus on the novel weighted static gaze entropy feature. Examine the results of an ensemble stacking model that achieved high classification performance in distinguishing between automated and non-automated driving scenarios as perceived by older drivers. Gain insights into how this research can inform future designs of driver state monitoring systems to mitigate safety risks associated with mode confusion in automated vehicles, particularly for older adults.