With the rapid development of big data and artificial intelligence technology, autonomous driving has increasingly become a research hotspot in the field of transportation. Based on the basic meaning and development status of the overall automatic driving, the requirements of urban driving infrastructure for different levels of automatic driving are analyzed. From the theoretical level, the influence of autonomous driving on road capacity is analyzed. Two road networks are constructed by TransModeler simulation software. The effects of different levels of autonomous driving on road capacity and intersection delay were evaluated. In order to control other variables, only the one-way street is used to simulate the autopilot capacity, while the traffic delay is simulated by a single intersection. The study found that in a one-way two-lane environment, the traffic capacity under automatic driving conditions is about 63.74% higher than that of manned driving, but there is no significant difference between different levels of autonomous driving capacity; in the intersection environment, it is indicated automated driving can reduce the average delay of the intersection by 1%, but there is little difference between different levels of autonomous driving. The research results show that in the L4 level automatic driving environment, high-adaptive traffic signal control system, Beidou/GPS system ground enhancement station, high-precision positioning, roadside alarm unit, and other facilities should be constructed in the L5-level automatic driving environment. The networked vehicle system based on 5G technology and the implementation of the vehicle basic data interaction platform and artificial intelligence should be upgraded. Under the conditions of automatic driving, the road capacity is significantly improved, and the delay of the intersection is significantly reduced, indicating that the automatic driving has a good improvement effect on the road traffic operation state.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Determining the Influence of Auto-Driving on Urban Road Traffic Conditions


    Beteiligte:
    Bao, Lixia (Autor:in) / Wang, Qiulan (Autor:in) / Xiao, Guangnian (Autor:in) / Ni, Anning (Autor:in)

    Kongress:

    13th Asia Pacific Transportation Development Conference ; 2020 ; Shanghai, China (Conference Cancelled)



    Erscheinungsdatum :

    2020-06-29




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Determining the Influence of Auto-Driving on Urban Road Traffic Conditions Anning Ni

    Bao, Lixia / Wang, Qiulan / Xiao, Guangnian et al. | TIBKAT | 2021


    Auto-calibration for road traffic prediction

    JOSEPH JOJO / NAIR RAGHUNATH E | Europäisches Patentamt | 2016

    Freier Zugriff

    AUTO-CALIBRATION FOR ROAD TRAFFIC PREDICTION

    JOSEPH JOJO / NAIR RAGHUNATH E | Europäisches Patentamt | 2015

    Freier Zugriff


    Auto-calibration for road traffic prediction

    JOSEPH JOJO / NAIR RAGHUNATH E | Europäisches Patentamt | 2016

    Freier Zugriff