Framework of Adaptive Driving: Linking Situation Awareness, Driving Goals, and Driving Intentions Using Eye-Tracking and Vehicle Kinetic Data

Abstract

Although current Artificial Intelligence (AI) can detect maneuvering intentions, it often overlooks the underlying driving goals that reveal drivers’ genuine requirements. To detect real-time driving goals using AI for providing effective decision aids, this research introduces the Framework of Adaptive Driving (FAD), which considers cognitive activities and action strategies. We have outlined five driving goals to elucidate the connections between Situation Awareness (SA), and intentions. The study involved 31 participants and 573 driving simulation events, during which we collected both eye-tracking and kinetic data. Exploratory Factor Analysis (EFA) identified 8 factors, categorized into SA and maneuver-related factors. Statistical and qualitative analysis follow up to specify the varying requirements among the driving foals defined. Generally, factor ‘Cognitive load’ can reflect cognitive activities, while ‘Saccade on the surroundings’ and ‘Saccade movement’ can indicate action strategies. For the goals where emerging risks are not a concern, ‘Active acceleration’ signifies drivers’ intention to enhance driving efficiency. However, the diverse features in ‘Saccade on the surroundings’ imply varying driving considerations. Goals for routine tasks focus on internal vehicle operations, while goals for driving benefits management highlight adjacent surroundings. Conversely, for goals addressing emerging risks, ‘Deceleration’ prevails. Furthermore, ‘Steering strategy’ implies a preference for steering when SA is adequate. In this context, SA-related factors like ‘Front observation,’ ‘Saccade movement,’ and ‘Cognitive load’ signify efforts to enhance SA under time constraints. However, for the driving goals under extreme urgency, the factor ‘Lateral movement’ replaces ‘Steering strategy’, implying severe steering without adequate SA.