Using optical flow calculations and a multilayer perceptron Artificial Neural Network (ANN), a methodology has been tried for mobile-robot obstacle detection and avoidance behavior. The study of the methodology has been supported by experimental results that were obtained from Matlab simulation environments. The images of the views were taken from a real navigation environment and then optical flow calculations for all images were obtained via Matlab simulink blocks created in advance, as an algorithm which can calculate optical flows from stereo visions. As optical flows of each pair of stereo views were derived, a database was constituted to train the multilayer perceptron. Using the data set and the Levenberg-Marquardt learning algorithm, a neural network was created that was well trained in Matlab environment in order to detect the presence of obstacles. Experimental results, obtained during the study have strengthened the ideas which have supported the usage of the optical flow via an ANN in mobile robotics for obstacle detection and avoidance behaviors.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Optical Flow-based obstacle detection and avoidance behaviors for mobile robots used in unmaned planetary exploration


    Beteiligte:
    Dur, Erdogan (Autor:in)


    Erscheinungsdatum :

    2009-06-01


    Format / Umfang :

    2726140 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Mobile Robots with Dynamic Obstacle Avoidance

    Ali, Maram / Das, Saptarshi | IEEE | 2023


    Mobile robots for planetary exploration

    Schilling, K. / Jungius, C. | Tema Archiv | 1996


    Obstacle Avoidance for Autonomous Mobile Robots Based on Mapping Method

    Nguyen, Anh-Tu / Vu, Cong-Thanh | Springer Verlag | 2022


    Vision based obstacle avoidance and navigation system for mobile robots

    Srinivasa, Santhosh | BASE | 2020

    Freier Zugriff