Data-Driven Control Strategy for On-Ramp Vehicles

Konferenz: ISCTT 2021 - 6th International Conference on Information Science, Computer Technology and Transportation
26.11.2021 - 28.11.2021 in Xishuangbanna, China

Tagungsband: ISCTT 2021

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Wei, Kai (Beijing Jiaotong University, Beijing, China)

Mandatory lane-changing(MLC) ,which is one of the basic driving behaviors. The MLC efficiency of on-ramp vehicles on expressways directly affects the throughput of the entire road network. Due to the complexity of the on-ramp vehicle’s MLC and the uncertainty of the driver’s driving behavior, modeling the lane-changing process of vehicles is challenging. To solve this problem, this paper proposes a data-driven on-ramp vehicle lane-changing model based on a Bi-directional Long Short-Term Memory(Bi-LSTM). The vehicle lane changing data provided by Next Generation Simulation project (NGSIM) is utilized to train and test the proposed Bi-LSTM model. The results show that the proposed vehicle lane changing model can accurately predict the MLC process of vehicles.