CAN-Modes: In-vehicle datasets generation and analysis in different driving situations

In-vehicle networks are responsible for safety-critical control applications, depending on data communication between electronic control units, and most are based on the CAN protocol. A huge amount of data is necessary for reliability, safety, and cybersecurity analysis in today's automotive solutions, especially to feed machine learning models. It is relevant to provide comprehensive datasets about CAN communication and different driving situations, which represents a lack in recent research because most public datasets are very limited. This paper addresses this problem by providing a set of CAN datasets collected in real cars and driving conditions, analyzed, and preprocessed for further research applications. The results present data collection and labeling, in three car brands, two data types (RAW and OBD pids), and they are available in recognized public sources.