A definition and framework for vehicular knowledge networking

To operate intelligent vehicular applications such as automated driving, mechanisms including machine learning (ML), artificial intelligence (AI), and others are used to abstract knowledge from information. Knowledge is defined as a state of understanding obtained through experience and analysis of collected information, and it is promising for vehicular applications. However, to achieve its full potential, it requires a unified framework that is cooperatively created and shared. This article investigates the meaning and scope of knowledge as applied to vehicular networks and defines a structure for vehicular knowledge description, storage, and sharing. Through the example of passenger-comfort-based automated driving, we expose the potential benefits of such knowledge structuring for network load and delay.