Eco-Driving of Connected and Automated Vehicle With Preceding Driver Behavior Prediction

Mehmet Fatih Ozkan, Yao Ma

Research output: Contribution to journalArticlepeer-review

Abstract

<jats:title>Abstract</jats:title><br> <jats:p>The development of vehicle connectivity and autonomy in the ground transportation sector is not only able to enhance traffic safety and driving comfort as well as fuel economy. This study presents a receding-horizon optimization-based control strategy integrated with the preceding vehicle speed prediction model to achieve an eco-driving strategy for connected and automated vehicles (CAVs). In the real traffic scenario where the CAV follows the preceding vehicle on the road, a gated recurrent unit (GRU) network is used to predict the behavior of the preceding vehicle by utilizing the historical inter-vehicle information collected through on-board sensors. Then, a nonlinear model predictive control (NMPC) algorithm is adopted for CAV to minimize the accumulated fuel consumption within the preview horizon. The NMPC approach solves the fuel-optimal speed profile of the CAV, considering a predicted short-term speed preview of the
Original languageEnglish
JournalDefault journal
DOIs
StatePublished - Jan 1 2021

Fingerprint

Dive into the research topics of 'Eco-Driving of Connected and Automated Vehicle With Preceding Driver Behavior Prediction'. Together they form a unique fingerprint.

Cite this