Original title: Mobile robot motion planner via neural network
Authors: Krejsa, Jiří ; Věchet, Stanislav
Document type: Papers
Conference/Event: Engineering Mechanics 2011 /17./, Svratka (CZ), 2011-05-09 / 2011-05-12
Year: 2011
Language: eng
Abstract: 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.
Keywords: mobile robot; motion planning; neural network
Project no.: CEZ:AV0Z20760514 (CEP)
Host item entry: Engineering Mechanics 2011, ISBN 978-80-87012-33-8

Institution: Institute of Thermomechanics AS ČR (web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences.
Original record: http://hdl.handle.net/11104/0197282

Permalink: http://www.nusl.cz/ntk/nusl-55918


The record appears in these collections:
Research > Institutes ASCR > Institute of Thermomechanics
Conference materials > Papers