The present invention relates to a method and apparatus for estimating a road surface type by using an ultrasonic signal and, more particularly, to a method for estimating a road surface type by using an artificial neural network model machine-learned with respect to a reflected ultrasonic signal and an apparatus for performing same. According to the present invention, provided are a method and apparatus for providing highly accurate road surface information at low cost, by machine-learning both characteristics of an ultrasonic signal reflected from a road surface and a road surface state, establishing a model between the two, and then estimating the type of the road surface by utilizing the model. In particular, even a road surface where thin ice, that is, black ice, is formed, which was not detectable in the conventional method for estimating a road-surface friction coefficient, may be accurately estimated, thereby contributing to safer driving.

    La présente invention concerne un procédé et un appareil pour estimer un type de surface de route à l'aide d'un signal ultrasonore et, plus précisément, un procédé pour estimer un type de surface de route à l'aide d'un modèle de réseau neuronal artificiel appris par machine par rapport à un signal ultrasonore réfléchi et un appareil pour la mise en œuvre de ce procédé. L'invention concerne un procédé et un appareil pour fournir des informations de surface de route hautement précises à faible coût, par apprentissage machine à la fois de caractéristiques d'un signal ultrasonore réfléchi à partir d'une surface de route et d'un état de surface de route, établissement d'un modèle entre les deux, puis estimation du type de surface de route en utilisant le modèle. En particulier, même une surface de route où de la glace mince est formée, c'est-à-dire de la glace noire, laquelle n'était pas détectable dans le procédé classique pour estimer un coefficient de frottement de surface de route, peut être estimée avec précision, ce qui contribue à une conduite plus sûre.

    본 발명은 초음파 신호를 이용한 노면 종류 추정 방법 및 장치에 관한 것으로서, 반사된 초음파 신호에 대하여 기계학습(machine learning)된 인공신경망 모델을 이용하여 노면의 종류를 추정하는 방법 및 이를 수행하는 장치에 관한 것이다. 본 발명에 의하면, 노면에서 반사된 초음파 신호의 특성과 노면 상태를 머신 러닝하여 그 둘 간의 모델을 확립하고 이를 활용하여 노면의 종류를 추정함으로써, 저렴한 비용으로 매우 정확한 노면 정보를 제공하는 방법 및 장치를 제공한다. 특히, 종래 노면 마찰계수 추정 방법에서는 파악할 수 없었던 얇은 얼음이 형성된 도로면(black ice)까지도 정확하게 추정해 냄으로써 더욱 안전 운전에 기여하게 되는 효과가 있다.


    Access

    Download


    Export, share and cite



    Title :

    METHOD AND APPARATUS FOR ESTIMATING ROAD SURFACE TYPE BY USING ULTRASONIC SIGNAL


    Additional title:

    PROCÉDÉ ET APPAREIL POUR ESTIMER UN TYPE DE SURFACE DE ROUTE À L'AIDE D'UN SIGNAL ULTRASONORE
    초음파 신호를 이용한 노면 종류 추정 방법 및 장치


    Contributors:
    CHOI SEI-BUM (author) / KIM MIN-HYUN (author) / PARK JIN-RAK (author) / SHIN SEUNG-IN (author) / PARK JONG-CHAN (author)

    Publication date :

    2020-03-05


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Korean


    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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    METHOD AND APPARATUS FOR ESTIMATING ROAD SURFACE TYPE BY USING ULTRASONIC SIGNAL

    CHOI SEI-BUM / KIM MIN-HYUN / PARK JIN-RAK et al. | European Patent Office | 2022

    Free access

    Method and apparatus for estimation road surface type using ultrasonic signal

    CHOI SEI-BUM / KIM MIN-HYUN / PARK JIN-RAK et al. | European Patent Office | 2024

    Free access


    Method and apparatus for estimation of tire-road type by using ultrasonic signal

    CHOI SEI BUM / KIM MIN HYUN / PARK JIN RAK et al. | European Patent Office | 2020

    Free access

    APPARATUS AND METHOD FOR ESTIMATING ROAD SURFACE TYPE USING SOUND WAVE SIGNALS

    KIM MIN HYUN | European Patent Office | 2023

    Free access