期刊
PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
卷 599, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.physa.2022.127303
关键词
Vehicle trajectory prediction; Car following; Lane changing; Integrated framework; Neural network with a switch structure
资金
- University of Wisconsin Traffic Operation and Safety Laboratory
This paper proposes a deep learning-based trajectory prediction model that can predict the combined behaviors of car following and lane change processes. Experimental results demonstrate that the proposed model outperforms other models in both short-term and long-term predictions.
Vehicle trajectory prediction is essential for the operation safety and control efficiency of automated driving. Prevailing studies predict car following and lane change processes in a separate manner, ignoring the dependencies of these two behaviors. To remedy this issue, this paper proposes an integrated deep learning-based two-dimension trajectory prediction model that can predict combined behaviors. Specifically, we designed a switch neural network structure based on the attention mechanism, bi-directional long-short term memory (BiLSTM) and Temporal convolution neural network (TCN) to mimic and predict the joint behaviors. Experiments are conducted based on the Next Generation Simulation (NGSIM) dataset to validate the effectiveness of our proposed model. As results indicate, our proposed model outperforms the state-of-art trajectory prediction models and can provide accurate short-term and long-term predictions. (C) 2022 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据