University of California Institute of Transportation Studies

Onboard eco-driving systems provide drivers with real-time information about their driving behavior and road conditions, encouraging them to optimize their driving speed and consequently reduce fuel consumption and emissions. However, there are barriers to making eco-driving a habit. To determine the elements that influence drivers’ intentions to practice eco-driving and their acceptance of eco-driving technology, we developed a theoretical model based on established theories on planned behavior, technology acceptance, and personal goals. The findings showed that drivers’ intention to practice eco-driving has an indirect effect on their intention to use the system via the factor of perceived ease of use. We also explored how cognitive distraction while using an eco-driving system can be a potential barrier to acceptance. The intent is to put forward a solution to improve drivers’ usage eco-driving by turning off guidance when the system detects that the driver is experience from serious distraction. To investigate how to detect a driver’s cognitive distraction status when they are interacting with an eco-driving system, we used a driving simulator and leveraged machine learning algorithms to classify drivers’ attentional states. The findings showed that the glance features played a more important role than the driving features in cognitive distraction.