A sequence to sequence learning based car-following model for multi-step predictions considering reaction delay. (November 2020)

• Record Type: Journal Article
• Authors: Ma, Lijing; Qu, Shiru
• Is Part Of: Transportation research. Volume 120(2020)
• Publication Date: 2020-11
• Subjects: Sequence to sequence (seq2seq) -- Deep learning -- Car-following -- Reaction delay -- Traffic flow; Transportation -- Periodicals; Transportation -- Technological innovations -- Periodicals; 388.011
• DOI: 10.1016/j.trc.2020.102785
• Languages: English
• ISSNs: 0968-090X

Abstract

Highlights: A car-following model based on sequence to sequence (seq2seq) learning is proposed. The model makes multi-step predictions with the consideration of reaction delay. The model outperforms other models in simulating trajectory and capturing heterogeneous driving behaviors. The model well reproduces different levels of hysteresis phenomenon. The model extended with spatial anticipation improves platoon simulation accuracy and traffic flow stability. Abstract: Car-following behavior modeling is of great importance for traffic simulation and analysis. Considering the multi-steps decision-making process in human driving, we propose a sequence to sequence (seq2seq) learning based car-following model incorporating not only memory effect but also reaction delay. Since the seq2seq architecture has the advantage of handling variable lengths of input and output sequences, in this paper, it is applied to car-following behavior modeling to memorize historical information and make multi-step predictions. We further compare the seq2seq model with a classical car-following model (IDM) and a deep learning car-following model (LSTM). The evaluation results indicate that the proposed model outperforms others for reproducing trajectory and capturing heterogeneous driving behaviors. Moreover, the platoon simulation demonstrates that the proposed model can well reproduce different levels of hysteresis phenomenon. The proposed model is further extended with spatial anticipation, which improves platoon simulation accuracy and traffic flow stability.