In this paper, we describe the use of Genetic Programming (GP) techniques to learn a visual feature detection for a mobile robot navigation task. We provide experimental results across a number of different environments, each with different characteristics, and draw conclusions about the performance of the learned feature detector. We also explore the utility of seeding the initial population with a previously evolved individual, and discuss the performance of the resulting individuals.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Visual Feature Detectors for Obstacle Avoidance using Genetic Programming


    Beteiligte:


    Erscheinungsdatum :

    2003-06-01


    Format / Umfang :

    243457 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Self-Supervised Learning for Visual Obstacle Avoidance : Technical report

    van Dijk, Tom | GWLB - Gottfried Wilhelm Leibniz Bibliothek | 2022

    Freier Zugriff

    Self-Supervised Learning for Visual Obstacle Avoidance : Technical report

    van Dijk, Tom | GWLB - Gottfried Wilhelm Leibniz Bibliothek | 2022

    Freier Zugriff


    Visual obstacle avoidance mechanism of large workboat

    JI HUI / YIN KEHUI / DAI SHUMIN et al. | Europäisches Patentamt | 2024

    Freier Zugriff