Predictive Cruise Control (PCC) is an optimal control method for managing vehicle speed and gears, particularly suitable for Heavy-Duty Vehicles (HDV). Traditional PCC systems can only achieve suboptimal vehicle speed planning within a short prediction range. The development of intelligent connected vehicles based on vehicle-to-vehicle and vehicle-to-infrastructure communication provides new directions for optimizing PCC systems. This paper proposes a spatiotemporal data-driven framework for Vehicle-Road-Cloud Cooperation vehicle speed control, achieving optimal control of vehicle speed. To address limitations such as limited perception range of individual vehicles and insufficient road traffic information, a spatiotemporal data fusion network model is introduced based on the aforementioned framework. The simulation experiment results demonstrate that within a 5-second speed prediction range, the model proposed in this paper consistently achieves the lowest Mean Absolute Error (MAE) among various validation paths compared to other models. The error range is between 2.19 and 4.10 km/h. Furthermore, the model accurately predicts the acceleration or deceleration trends of the speed curve.
Research on vehicle speed control method based on spatiotemporal data and vehicle-road-cloud cooperation
2023-01-01
913458 byte
Conference paper
Electronic Resource
English
Special vehicle priority passing method based on vehicle-road cloud cooperation
European Patent Office | 2020
|Vehicle speed control method based on vehicle-road cloud collaborative optimization
European Patent Office | 2021
|Vehicle-road cooperation system and vehicle-road cooperation method
European Patent Office | 2021
|Vehicle curve vehicle speed alarm device based on vehicle-road cooperation
European Patent Office | 2021
|Vehicle-road cooperation speed control method and system based on multivariate data perception
European Patent Office | 2024
|