Autonomous driving demands robust and precise vehicle localization in complex environments with limited on-board computational resources. Incorporating reliable semantic information with localization algorithms can increase accuracy remarkably, however, the process of extracting semantic information from LiDAR point clouds and matching it to semantic maps is computationally intensive. Moreover, pure semantic localization cannot achieve the robustness requirements for safe self-driving as the necessary quantity of semantic landmarks cannot be guaranteed under extreme conditions. In this paper, we present a lightweight semantic-aided localization method that improves upon traditional techniques in two ways. First, we propose a highly efficient pipeline to extract three semantic classes from a LiDAR scan. Second, instead of semantic 3D point cloud registration, map matching is performed through 2D key point matching. We then integrate these two functions into a dynamic semantic aided localization framework. Our on-road experiments demonstrate that the proposed method achieves both the high accuracy of semantic localization and the robustness of non-semantic localization. With our algorithm consuming under 10% of CPU resources, we observe reduced positioning error, especially peak error, when comparing to non-semantic counterparts.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Lightweight Semantic-Aided Localization With Spinning LiDAR Sensor


    Beteiligte:
    Ren, Yuan (Autor:in) / Liu, Bingbing (Autor:in) / Cheng, Ran (Autor:in) / Agia, Christopher (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.01.2023


    Format / Umfang :

    3595253 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Lidar Mapping Optimization Based on Lightweight Semantic Segmentation

    Zhao, Zhihao / Zhang, Wenquan / Gu, Jianfeng et al. | IEEE | 2019


    Cooperative LiDAR-Aided Self-localization of CAVs in Real Urban Scenario

    Adas, Akif / Barbieri, Luca / Morri, Pietro et al. | Springer Verlag | 2024

    Freier Zugriff

    LISEG: LIGHTWEIGHT ROAD-OBJECT SEMANTIC SEGMENTATION IN 3D LIDAR SCANS FOR AUTONOMOUS DRIVING

    Zhang, Wenquan / Zhou, Chancheng / Yang, Junjie et al. | British Library Conference Proceedings | 2018


    LiSeg: Lightweight Road-object Semantic Segmentation In 3D LiDAR Scans For Autonomous Driving

    Zhang, Wenquan / Zhou, Chancheng / Yang, Junjie et al. | IEEE | 2018


    DYNAMIC POWER THROTTLING OF SPINNING LIDAR

    VETS ROBERT | Europäisches Patentamt | 2021

    Freier Zugriff