How Does a Digital Twin Network Work Well for Connected and Automated Vehicles: Joint Perception, Planning, and Control

The cutting-edge technology of connected and automated vehicles (CAVs) will advance transportation systems for the foreseeable future. CAVs are expected to maintain fully automated judgment and manipulation without human intervention and, additionally, create safer driving and smarter traffic management. Digital twins (DTs) are the quiet but powerful forces enabling these new possibilities behind the scenes. In this article, we design a DT network (DTN) consisting of connected DTs to help CAVs in terms of ubiquitous perception, adaptive path planning, and precise motion control. Heterogeneous learning models and diverse learning methods are employed at different scales of solution, progressing toward specificity, adaptation, and accuracy. Qualitative evaluation of the proposed system is performed with the final goal of demonstrating the DTN's assistance in improving the performance and effectiveness of CAVs, ultimately leading to a safer, more efficient, and more sustainable transportation system.