In a recent French robotic contest, the objective was to develop a multi-robot system able to autonomously map and explore an unknown area while also detecting and localizing objects. As a participant in this challenge, we proposed a new decentralized Markov decision process (Dec-MDP) resolution based on distributed value functions (DVF) to compute multi-robot exploration strategies. The idea is to take advantage of sparse interactions by allowing each robot to calculate locally a strategy that maximizes the explored space while minimizing robots interactions. In this paper, we propose an adaptation of this method to improve also object recognition by integrating into the DVF the interest in covering explored areas with photos. The robots will then act to maximize the explored space and the photo coverage, ensuring better perception and object recognition.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    DECENTRALIZED MULTI-ROBOT PLANNING TO EXPLORE AND PERCEIVE


    Beteiligte:

    Erscheinungsdatum :

    30.06.2015


    Anmerkungen:

    doi:10.14311/AP.2015.55.0169
    Acta Polytechnica; Vol 55, No 3 (2015); 169-176 ; 1805-2363 ; 1210-2709



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629




    Path Planning for a Multi-robot System with Decentralized Control Architecture

    Metoui, Fethi / Boussaid, Boumedyen / Abdelkrim, Mohamed Naceur | Springer Verlag | 2020



    BICYCLE ENABLE TO PERCEIVE OBSTACLE

    KIM HOON / LEE KWANG BOK | Europäisches Patentamt | 2017

    Freier Zugriff

    A Route Planning of Multiple Mobile Robot for Autonomous Decentralized System

    Sakida, T. / ITS Congress Association | British Library Conference Proceedings | 2000