Počet záznamů: 1

Mobile robot motion planner via neural network

  1. 1.
    0359501 - UT-L 2012 RIV CZ eng C - Konferenční příspěvek (zahraniční konf.)
    Krejsa, Jiří - Věchet, Stanislav
    Mobile robot motion planner via neural network.
    Engineering Mechanics 2011. Prague: Institute of Thermomechanics AS CR, v. v. i., 2011 - (Fuis, V.), s. 327-330. ISBN 978-80-87012-33-8.
    [Engineering Mechanics 2011 /17./. Svratka (CZ), 09.05.2011-12.05.2011]
    Výzkumný záměr: CEZ:AV0Z20760514
    Klíčová slova: mobile robot * motion planning * neural network
    Kód oboru RIV: JD - Využití počítačů, robotika a její aplikace

    Motion planning is essential for mobile robot successful navigation. There are many algorithms for motion planning under various constraints. However, in some cases the human can still do a better job, therefore it would be advantageous to create a planner based on data gathered from the robot simulation when humans do the planning. The paper presents the method of using the neural network to transfer the previously gained knowledge into the machine learning based planner. In particular the neural network task is to mimic the planner based on finite state machine. The tests proved that neural network can successfully learn to navigate in constrained environment.
    Trvalý link: http://hdl.handle.net/11104/0197282