Techniques are discussed herein for determining a prediction of a top-down representation of an environment based on vehicle actions. A sensor of a first vehicle (e.g., an autonomous vehicle) may capture sensor data of an environment, which may include an object (e.g., a vehicle or pedestrian) separate from the first vehicle. A multi-channel image representing a top-down view of the object and environment may be generated based on sensor data, map data, and/or motion data. Environmental data (object range, speed, lane position, pedestrian crosswalk, etc.) may be encoded in the image. The motion data may represent a target lane, trajectory, etc. of the first vehicle. A plurality of images representing the environment over time may be generated and input into a prediction system configured to output predicted probabilities associated with possible locations of the object in the future based on actions of the autonomous vehicle.

    本文讨论了用于基于车辆动作来确定环境的自上而下表示的预测的技术。第一车辆(例如,自主车辆)的传感器可以捕获环境的传感器数据,该环境可以包括与第一车辆分开的对象(例如,车辆或行人)。可以基于传感器数据、地图数据和/或动作数据来生成表示对象和环境的自上而下视图的多通道图像。可以在图像中对环境数据(对象范围、速度、车道位置、人行横道等)进行编码。动作数据可以表示第一车辆的目标车道、轨迹等。可以生成表示环境随时间推移的多个图像并将其输入到预测系统中,该预测系统被配置为可以基于自主车辆的动作来输出与对象在未来的可能的位置相关联的预测概率。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Top-down scene prediction based on motion data


    Weitere Titelangaben:

    基于动作数据的自上而下场景预测


    Beteiligte:

    Erscheinungsdatum :

    2022-03-25


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G05D SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES , Systeme zum Steuern oder Regeln nichtelektrischer veränderlicher Größen / 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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Top-down scene prediction based on object motion

    MORALES MORALES ANGEL GUADALUPE / KOBILAROV MARIN / GARIMELLA GIANNI et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Relation-based Motion Prediction using Traffic Scene Graphs

    Zipfl, Maximilian / Hertlein, Felix / Rettinger, Achim et al. | IEEE | 2022


    TOP-DOWN SCENE DISCRIMINATION

    BAGSCHIK GERRIT / CREGO ANDREW SCOTT / GARIMELLA GOWTHAM et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    TOP-DOWN SCENE GENERATION

    BAGSCHIK GERRIT / CREGO ANDREW SCOTT / GARIMELLA GOWTHAM et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Top-down scene discrimination

    BAGSCHIK GERRIT / CREGO ANDREW SCOTT / GARIMELLA GOWTHAM et al. | Europäisches Patentamt | 2024

    Freier Zugriff