Intelligent information systems and advanced driver assistance systems help drivers maintain a high level of situational awareness during vehicle operation; however, they also increase visual distraction and cognitive load because of ubiquitous demands for peripheral interactions and additional cognitive engagement in virtual information space. Nevertheless, existing research has inadequately addressed how an intervention of context-sensitive information feeds back into drivers’ attention management and cognitive load, and whether it increases workload and thus hinders attentive/safe driving. To fill this gap, this project aims to build and install a series of in-vehicle sensing prototypes, examine a broad range of sensor data streams to understand driver/driving states (e.g., driver's peripheral interaction states, driver's cognitive workload states, etc.), and then present a model-based driver/driving assessment by using machine learning technology.