The statistical characteristics of surrounding vehicles’ motions may significantly affect the performance of autonomous vehicles (AV). Therefore, AV driving policy may not work in a new area, which limits the driving of AVs across regions. This paper proposes a means of extracting and detecting traffic scenario characteristics, using a Variational Autoencoder (VAE). VAE is an unsupervised learning method, which can reconstruct the traffic data using neural networks. This method uses a vehicle’s state transition date as input and extracts latent variables in two dimensions. The extracted hidden variables can represent the driving characteristics of the environment. The scenario characteristics detector relies on the similarity of the hidden variables, using KL-divergence. The method is tested by the NGSIM (Next Generation Simulation) and highD dataset. The VAE are trained on 100,000 sets of data in 10 minutes. The results indicate that this method can accurately distinguish between regions, and detect traffic scenarios.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Decision-Oriented Driving Scenario Recognition Based on Unsupervised Learning


    Contributors:
    Deng, Nanshan (author) / Jiang, Kun (author) / Cao, Zhong (author) / Zhou, Weitao (author) / Yang, Diange (author)

    Conference:

    21st COTA International Conference of Transportation Professionals ; 2021 ; Xi’an, China


    Published in:

    CICTP 2021 ; 564-573


    Publication date :

    2021-12-14




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Decision-Oriented Driving Scenario Recognition Based on Unsupervised Learning

    Deng, Nanshan / Jiang, Kun / Cao, Zhong et al. | TIBKAT | 2021


    Unsupervised Random Forest Learning for Traffic Scenario Categorization

    Kruber, Friedrich / Wurst, Jonas / Botsch, Michael et al. | Springer Verlag | 2023


    Pattern Recognition for Driving Scenario Detection in Real Driving Data

    Montanari, Francesco / German, Reinhard / Djanatliev, Anatoli | IEEE | 2020


    PATTERN RECOGNITION FOR DRIVING SCENARIO DETECTION IN REAL DRIVING DATA

    Montanari, Francesco / German, Reinhard / Djanatliev, Anatoli | British Library Conference Proceedings | 2020


    Driving scenario machine learning network and driving environment simulation

    SIDDIQUI MATHEEN / LIN CHENG-YI / YUAN CHANG | European Patent Office | 2023

    Free access