Disclosed herein are system, method, and computer program product embodiments for clustering lane segments of a roadway in order to improve and simplify autonomous vehicle behavior testing. The approaches disclosed herein provide a hybrid methodology of dividing lane segments into hard features and soft features, and using a metric learning model trained in a supervised process on the entirety of lane segment features to cluster the lane segments based on the soft features. These clustered lane segments can then be assigned to what is termed as protolanes, where a single set of tests applied to a given protolane is considered valid across all of the lane segments assigned to the protolane.


    Access

    Download


    Export, share and cite



    Title :

    LANE SEGMENT CLUSTERING USING HYBRID DISTANCE METRICS


    Contributors:

    Publication date :

    2023-12-28


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G01C Messen von Entfernungen, Höhen, Neigungen oder Richtungen , MEASURING DISTANCES, LEVELS OR BEARINGS / G06V



    Determining Lane Use Distributions Using Basic Freeway Segment Density Measures

    Lee, J. / Park, B.B. | British Library Online Contents | 2012



    Lane detection and tracking using a new lane model and distance transform

    Ruyi, J. | British Library Online Contents | 2011


    Lane detection and tracking using a new lane model and distance transform

    Jiang, Ruyi / Reinhard, Klette / Tobi, Vaudrey et al. | Tema Archive | 2011


    3D Segment Matching using the Hausdorff Distance

    Guerra, C. / Pascucci, V. / Institution of Electrical Engineers et al. | British Library Conference Proceedings | 1999