Techniques for implementing a vehicle computing device to determine a time horizon for a prediction are described herein. For example, the techniques may include the vehicle computing device receiving sensor data from a sensor and using the sensor data to determine an amount of time in the future to make a prediction associated with an autonomous vehicle in a real-world environment or a simulated environment. The vehicle computing device can select or otherwise determine to use a model that is associated with a time period similar to the time horizon and output the prediction using the model. The vehicle computing device can transition between models as the autonomous vehicle navigates in an environment to predict potential interactions with an object in the environment as various times in the future.


    Access

    Download


    Export, share and cite



    Title :

    DETERMINING PREDICTION TIMES FOR A MODEL


    Contributors:

    Publication date :

    2024-05-30


    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



    DETERMINING SUPER FRAME PACKET GENERATION TIMES

    XHAFA ARITON E / VEDANTHAM RAMANUJA / TORRES BARDALES JESUS DANIEL | European Patent Office | 2023

    Free access


    DeepTrip: A Deep Learning Model for the Individual Next Trip Prediction With Arbitrary Prediction Times

    Zhang, Pengfei / Koutsopoulos, Haris N. / Ma, Zhenliang | IEEE | 2023

    Free access

    Prediction of Pushback Times and Ramp Taxi Times for Departures at Charlotte Airport

    Lee, Hanbong / Coupe, William J. / Jung, Yoon C. | NTRS | 2019