In various examples, a multi-sensor fusion machine learning model, such as a deep neural network (DNN), may be deployed to fuse data from multiple individual machine learning models. Thus, the multi-sensor fusion network may generate a fused output using outputs from a plurality of machine learning models as inputs, the fused output representing data from a field of view or sensory field of each sensor providing the machine learning models, at the same time, associations between boundaries or overlap regions of various fields of view of the learned source sensor are considered. In this manner, the fused output may be less likely to include duplicated, inaccurate, or noisy data relating to objects or features in the environment, since the fusion network may be trained to interpret multiple instances of the same object appearing in different input representations.

    在各个示例中,可以部署多传感器融合机器学习模型——例如深度神经网络(DNN)——来融合来自多个单独机器学习模型的数据。因此,多传感器融合网络可以使用来自多个机器学习模型的输出作为输入来生成融合输出,该融合输出表示来自提供机器学习模型的每个传感器的视场或感觉场的数据,同时考虑学习的源传感器的各个视场的边界或重叠区域之间的关联。通过这种方式,融合的输出可能不太可能包括与环境中的对象或特征有关的重复、不准确或噪声数据,因为可以训练融合网络来解释出现在不同输入表示中的相同对象的多个实例。


    Access

    Download


    Export, share and cite



    Title :

    Sensor fusion for autonomous machine applications using machine learning


    Additional title:

    使用机器学习的用于自主机器应用的传感器融合


    Contributors:

    Publication date :

    2022-06-14


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / 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 / G01S RADIO DIRECTION-FINDING , Funkpeilung / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / G06V



    SENSOR FUSION FOR AUTONOMOUS MACHINE APPLICATIONS USING MACHINE LEARNING

    PARK MINWOO / KWON JUNGHYUN / KOCAMAZ MEHMET K et al. | European Patent Office | 2021

    Free access

    Sensor fusion for autonomous machine applications using machine learning

    PARK MINWOO / KWON JUNGHYUN / KOCAMAZ MEHMET K et al. | European Patent Office | 2023

    Free access

    SENSOR FUSION FOR AUTONOMOUS MACHINE APPLICATIONS USING MACHINE LEARNING

    PARK MINWOO / KWON JUNGHYUN / KOCAMAZ MEHMET K et al. | European Patent Office | 2023

    Free access


    TRAINING CONFIGURATION-AGNOSTIC MACHINE LEARNING MODELS USING SYNTHETIC DATA FOR AUTONOMOUS MACHINE APPLICATIONS

    DEGIRMENCI ALPEREN / HONG WON / BOJARSKI MARIUSZ et al. | European Patent Office | 2023

    Free access