The technology provides methods for cloud-based model deployment and control for autonomous driving. The methods provide a cloud-based platform, an onboard unit (OBU), and a Vehicle-to-System component. The cloud-based platform comprises a localization-enhancement subsystem and a cloud computing module. The methods collect detectable data and undetectable data from vehicles, road, and cloud. Then, the methods provide a set of end-to-end AI models and methods for automated driving services, comprising sensing, prediction, planning, and control services. The AI models and methods are trained and optimized to process collected data for providing operating parameters for vehicles. Then, the vehicles can be effectively and efficiently controlled and operated using these methods. In addition, these methods generate and provide detailed time-sensitive vehicle specific control instructions.