Incorporating lane-change prediction into energy-efficient speed control of connected autonomous vehicles at intersections

Abstract

Technology advancements in recent years introduced more options to intelligent transportation systems (ITS). Automation and connectivity are two major opportunities that are highly admired and studied in ITS. Connected and autonomous vehicles (CAVs) possess the capability of perception and information broadcasting with other CAVs and connected intersections. They can communicate with other CAVs to transmit vehicle dynamics and receive signal timing plans from connected intersections. Additionally, they exhibit computational abilities and can be controlled strategically. Optimal control strategies offer energy efficiency with respect to vehicle dynamics and traffic constraints. One potential control strategy is real-time speed control, which adjusts the target vehicle speed by taking advantage of broadcasted traffic information, such as signal timings. Connectivity at the vehicle level provides information about the current traffic conditions, while connection to the signalized intersection achieves current and future signal timing plans. Given the traffic information, a macroscopic traffic flow model predicts the behavior of the preceding vehicle for a short-term horizon, which results in optimally controlling the target CAV. However, the optimal control is likely to increase the gap in front of the controlled CAV, which induces lane changing by other drivers. This study proposes a modified traffic flow model that aims to predict lane-changing occurrences and assess the impact of lane changes on future traffic states. The primary objective is to improve energy efficiency for a certain vehicle. The prediction model is based on a cell division platform and is derived considering the additional flow during lane changing. First, the lane-change time and cell location are predicted and second, the impact of the additional flow due to lane-change is demonstrated in the traffic flow model. An optimal control strategy is then developed, subject to the predicted trajectory generated for the preceding vehicle. Lane change prediction estimates future speed and gap of vehicles, based on predicted traffic states. The proposed framework outperforms the non-lane change traffic model, resulting in up to 13% energy savings for the target vehicle when lane changing is predicted 4-6 seconds in advance.