Vehicle driving behavior recognition is critical to improve the safety and rationality of autonomous vehicle decision-making and planning in heterogeneous vehicle mixed scenarios. Aiming at the problems that traditional driving behavior recognition methods only consider a single driving behavior, which has insufficient recognition accuracy, and the lack of consideration of the impact on the neighborhood between traffic subjects, the algorithm robustness is poor. A driving behavior recognition method based on Gaussian mixture hidden Markov model (GMM-HMM) is proposed. Firstly, preprocess the NGSIM data sample, take the surrounding vehicles lateral displacement, lateral speed are taken as the HMM observation sequence, the HMM driving behavior recognition model is established. Then, the Baum-Welch algorithm and the Viterbi algorithm are used to train the parameters of the HMM to obtain Hidden state sequence of driving behavior. Finally, the proposed driving behavior recognition model of surrounding vehicles is validated by using real vehicle date and NGSIM vehicle natural trajectory data. The results show that the driving behavior recognition method based on GMM-HMM can effectively recognize typical driving behaviors such as vehicles going straight and changing lanes. The average correct recognition rate reaches 94%, and the average prediction delay is 176ms, compared with the random forest algorithm under the same scene and training data, the model is better. This method can effectively identify the driving behavior of the vehicle, and can provide a theoretical basis for the decision-making and planning of the autonomous vehicle in the heterogeneous vehicle mixed scenario.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Recognition of Surrounding Vehicles Driving Behavior Based on Gaussian Mixture Model-Hidden Markov Model for Autonomous Vehicle


    Weitere Titelangaben:

    Sae Technical Papers


    Beteiligte:
    Wang, Jinxiang (Autor:in) / ZHAO, Shu-en (Autor:in) / Wang, Yandong (Autor:in) / Li, Yuling (Autor:in)

    Kongress:

    SAE 2021 Intelligent and Connected Vehicles Symposium Part I ; 2021



    Erscheinungsdatum :

    15.12.2021




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    Recognition of Surrounding Vehicles Driving Behavior Based on Gaussian Mixture Model-Hidden Markov Model for Autonomous Vehicle

    ZHAO, Shu-en / Wang, Yandong / Wang, Jinxiang et al. | British Library Conference Proceedings | 2021


    Driving intention recognition method based on Gaussian mixture-hidden Markov model

    SHEN YU / LIU GUANGHUI / XU JIAWEN et al. | Europäisches Patentamt | 2024

    Freier Zugriff

    Wheel Loader Driving Intention Recognition with Gaussian Mixture - Hidden Markov Model

    Cao Guoxiang / Wang Anlin / Xu Donghuan | DOAJ | 2018

    Freier Zugriff

    Vehicle behavior prediction method based on dual-channel Gaussian mixture hidden Markov model

    WANG YIJING / LI ZHENG / ZUO ZHIQIANG | Europäisches Patentamt | 2022

    Freier Zugriff

    Research of Driving Fatigue Detection Based on Gaussian Mixture Hidden Markov Model

    Zhang, Mingheng / Wan, Xing / Liu, Zhaoyang et al. | SAE Technical Papers | 2020