@inproceedings{13028caf967642fdb18d269ae97e1773,
title = "Improved real-time velocity prediction by considering preceding vehicle dynamics",
abstract = "This paper focuses on improving the previous velocity prediction method performance by incorporating preceding vehicle dynamics. Firstly, a vehicle-following system is established to obtain the target vehicle velocity, preceding vehicle velocity and the distance between them. After a systematic correlation analysis, an Artificial Neural Network (ANN) based on real-time velocity prediction is proposed to improve the prediction accuracy regarding the previous studies in the literature. The interaction pattern between front vehicle and target vehicle is learnt via the ANN model. Simulation results indicate that the improvement mainly gains from the awareness of acceleration switching dynamics during driving. The proposed method is able to increase prediction accuracy by over 30%. The velocity predictor can be used in the energy management, safety control or other fields for automotive engineering.",
keywords = "ANN, Correlation, Predictor, Vehicle-following, Velocity",
author = "Haidi Sun and Junqiu Li and Chao Sun",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 2019 IEEE Vehicle Power and Propulsion Conference, VPPC 2019 ; Conference date: 14-10-2019 Through 17-10-2019",
year = "2019",
month = oct,
doi = "10.1109/VPPC46532.2019.8952503",
language = "English",
series = "2019 IEEE Vehicle Power and Propulsion Conference, VPPC 2019 - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2019 IEEE Vehicle Power and Propulsion Conference, VPPC 2019 - Proceedings",
address = "United States",
}