Digital Twins and Simulations for Scalable Deployment of Connected and Automated Vehicles

Connected and Automated Vehicles are the main pillar of the future mobility paradigm. Indeed, these vehicles employ various sensors to retrieve raw data from the road context, Machine Learning models to process and retrieve deep knowledge from acquired data, and sophisticated communication technologies to promptly and reliably share data. It is possible to improve their effectiveness by leveraging technologies expected to play a crucial role in the upcoming sixth generation network, such as Digital Twin and edge computing. Moreover, their large-scale evaluation entails accurate and realistic vehicular network simulation platforms, also coupled to the Digital Twin. In this challenging and intriguing context, the interplay of the aforementioned technologies and methodologies raises several concerns, which are addressed by my PhD research, conducted under the supervision of Claudia Campolo.