We present a novel approach for using industrial grade ultrasonic sensors to perform echolocation by detecting ultrasonic echoes in a noisy environment using machine learning. Autonomous driving is expected to become a huge market and among other technical challenges, environmental perception will be the most critical one. For high automation level, classical technologies are limited. On the other hand automotive is cost sensitive. The main part of the lecture starts with state of the art technology and then explains how we have used machine learning approaches to train a net for several classifications tasks: Distinguish whether the ultrasonic echo comes from the sensor or another noise source, distinguish whether the echo is relevant or not and finally a height classification. Results are presented in the form of F1-Score. In addition to this, a method will be presented to use CNN for noise suppression in real time. We demonstrate the potential of using the “bat principle” for perception and prove that by that we also achieve the low cost targets.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Improved Ultrasonic Sensing Using Machine Learning


    Weitere Titelangaben:

    Proceedings


    Beteiligte:

    Kongress:

    International ATZ Conference ; 2022 ; Wiesbaden, Deutschland April 05, 2022 - April 06, 2022


    Erschienen in:

    Automatisiertes Fahren 2022 ; Kapitel : 4 ; 41-43


    Erscheinungsdatum :

    2024-07-02


    Format / Umfang :

    3 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Deutsch




    Improved Ultrasonic Sensing Using Machine Learning

    Gotzig, Heinrich / Mohamed, Mohamed-Elamir / Zoellner, Raoul et al. | VDE-Verlag | 2022


    Robot Guidance using Ultrasonic Sensing

    Wykes, C. / Webb, P. / Gibson, I. | British Library Conference Proceedings | 1994


    Improved machine learning

    QIU SHIQI / SONAWANE KALPANA PAVAN / TSENG FLYNN FINN et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Driver Passenger Detection Using Ultrasonic Sensing

    ISAAC EMAD | Europäisches Patentamt | 2022

    Freier Zugriff

    ULTRASONIC SYSTEM AND METHOD FOR CLASSIFYING OBSTACLES USING MACHINE LEARNING ALGORITHM

    ABINAYA KUMAR / FABIO CECCHI / JAYANTA KUMAR DUTTA et al. | Europäisches Patentamt | 2022

    Freier Zugriff