Example embodiments relate to self-supervisory and automatic response techniques and systems. A computing system may use sensor data from an autonomous vehicle sensor to detect an object in the environment of the vehicle as the vehicle navigates a path. The computing system may then determine a detection distance between the object and the sensor responsive to detecting the object. The computing system may then perform a comparison between the detection distance and a baseline detection distance that depends on one or more prior detections of given objects that are in the same classification group as the object. The computing system may then adjust a control strategy for the vehicle based on the comparison.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Methods and Systems for Automatic Introspective Perception


    Beteiligte:
    CALLEIJA MARK (Autor:in) / KUNZ CLAYTON (Autor:in) / LANGFORD MATTHEW (Autor:in) / HUKKERI RAMADEV (Autor:in) / ROTHENBERG DANIEL (Autor:in)

    Erscheinungsdatum :

    29.08.2024


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Englisch


    Klassifikation :

    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




    Introspective autonomous vehicle operational management

    SVEGLIATO JUSTIN / WITWICKI STEFAN / WRAY KYLE HOLLINS et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Introspective Autonomous Vehicle Operational Management

    SVEGLIATO JUSTIN / WITWICKI STEFAN / WRAY KYLE HOLLINS et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Prior Learning in Introspective VAEs

    Athanasiadis, Ioannis / Lindsten, Fredrik / Felsberg, Michael | ArXiv | 2024

    Freier Zugriff

    IntroVAE: Introspective Variational Autoencoders for Photographic Image Synthesis

    Huang, Huaibo / Li, Zhihang / He, Ran et al. | ArXiv | 2018

    Freier Zugriff