Data-driven Predictive Connected Cruise Control

Abstract

In this paper, we propose a data-driven predictive controller for connected automated vehicles (CAVs) traveling in mixed traffic consisting of both connected and non-connected vehicles. We assume a low penetration of connectivity, with only one connected vehicle in the downstream traffic. A model predictive controller is designed to integrate multiple specifications, including safety and energy efficiency, while accounting for the time delay in the longitudinal dynamics of the vehicle. A data-driven prediction method based on the behavioral theory of linear systems is proposed to model the relationship between the speeds of the distant connected vehicle and the vehicle immediately in front of the CAV. The proposed method is evaluated using real traffic data and demonstrates improved prediction accuracy and energy efficiency compared to model-based prediction methods.