Deep neural networks can be powerful tools, but require careful application-specific design to ensure that the most informative relationships in the data are learnable. In this paper, we apply deep neural networks to the nonlinear spatiotemporal physics problem of vehicle traffic dynamics. We consider problems of estimating macroscopic quantities (e.g., the queue at an intersection) at a lane level. First-principles modeling at the lane scale has been a challenge due to complexities in modeling social behaviors like lane changes, and those behaviors’ resultant macro-scale effects. Following domain knowledge that upstream/downstream lanes and neighboring lanes affect each others’ traffic flows in distinct ways, we apply a form of neural attention that allows the neural network layers to aggregate information from different lanes in different manners. Using a microscopic traffic simulator as a testbed, we obtain results showing that an attentional neural network model can use information from nearby lanes to improve predictions, and, that explicitly encoding the lane-to-lane relationship types significantly improves performance. We also demonstrate the transfer of our learned neural network to a more complex road network, discuss how its performance degradation may be attributable to new traffic behaviors induced by increased topological complexity, and motivate learning dynamics models from many road network topologies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Neural-Attention-Based Deep Learning Architectures for Modeling Traffic Dynamics on Lane Graphs


    Contributors:


    Publication date :

    2019-10-01


    Size :

    192175 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Modeling Traffic Flow Dynamics on Managed Lane Facility

    Liu, Xiaoyue Cathy / Zhang, Guohui / Lao, Yunteng et al. | Transportation Research Record | 2012


    Traffic monitoring system of multi lane based on deep learning using camera

    CHOI JUNG SAM / LEE KYOUNG SOO / LEE HAN GYEOL | European Patent Office | 2022

    Free access

    Integrated deep learning and stochastic car-following model for traffic dynamics on multi-lane freeways

    Lee, Seunghyeon / Ngoduy, Dong / Keyvan-Ekbatani, Mehdi | Elsevier | 2019


    Deep reinforcement learning traffic signal control method based on attention mechanism

    WU JIANGUANG / ZHOU SHUYA / HOU XIANGDONG et al. | European Patent Office | 2024

    Free access

    Variable lane and traffic signal cooperative control method based on deep reinforcement learning

    DING CHUAN / NIE WUYANG / LU YINGRONG et al. | European Patent Office | 2020

    Free access