A method learns unsupervised world models for autonomous driving via discrete diffusion. The method includes encoding an observation of an actor for a geographic region using an encoder to generate a prior frame of prior tokens. The method further includes processing the prior frame with a spatio-temporal transformer to generate a predicted frame of predicted tokens. The spatio-temporal transformer includes a spatial transformer and a temporal transformer. The method further includes processing the predicted frame to generate a predicted action for the actor. The method further includes decoding the predicted frame to generate a predicted observation of the geographic region.


    Access

    Download


    Export, share and cite



    Title :

    LEARNING UNSUPERVISED WORLD MODELS FOR AUTONOMOUS DRIVING VIA DISCRETE DIFFUSION


    Contributors:
    ZHANG LUNJUN (author) / XIONG YUWEN (author) / YANG ZE (author) / CASAS ROMERO SERGIO (author) / URTASUN RAQUEL (author)

    Publication date :

    2025-03-27


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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



    Transition to unsupervised autonomous driving mode of ADS

    HARDA PETER / BRANSTROM MATTIAS | European Patent Office | 2023

    Free access


    Offline Reinforcement Learning for Autonomous Driving with Real World Driving Data

    Fang, Xing / Zhang, Qichao / Gao, Yinfeng et al. | IEEE | 2022



    TRANSITIONING TO AN UNSUPERVISED AUTONOMOUS DRIVING MODE OF AN ADS

    HARDÅ PETER / BRÄNNSTRÖM MATTIAS | European Patent Office | 2023

    Free access