Driver state monitoring to mitigate distraction.

There is no doubt that recent in-vehicle technologies such as GPS maps, entertainment systems and mobile telephones increase crash risk, the unknown is to what degree. Cars offer unique challenges in human-machine interaction. Vehicles are increasingly becoming automated systems that collaborate with, rather than are controlled by, the driver. In this paper we suggest an approach that, by design, minimises and manages information system distractions. It is not possible to know what the driver is thinking. We can, however, monitor the driver’s gaze and compare it with information in their view-field to make an inference. We outline our capabilities in road scene understanding and driver monitoring. Then demonstrate how our capabilities can be used in driver assistance systems with intuitive and integrated human machine interfaces.