A simulation of autonomous robot movement directed by reinforcement learning

Andrew Greasley*

*Corresponding author for this work

Research output: Chapter in Book/Published conference outputConference publication

Abstract

As companies embrace Industry 4.0 and embed intelligent robots and other intelligent facilities in their factories, decision making can be derived from machine learning algorithms and so if we are to simulate these systems we need to model these algorithms too. This article presents a discrete-event simulation (DES) that incorporates the use of a reinforcement learning (RL) algorithm which determines an approximate best route for robots in a factory moving from one physical location to another whilst avoiding collisions with fixed barriers. The study shows how the object oriented and graphical facilities of an industry ready commercial off-the-shelf (COTS) DES software package enables an RL capability without the need to use program code or require an interface with external RL software. Thus the article aims to contribute to the methodology of simulation practitioners who wish to implement AI techniques as a supplement to their input modelling approaches.

Original languageEnglish
Title of host publication32nd European Modeling and Simulation Symposium, EMSS 2020
EditorsMichael Affenzeller, Agostino G. Bruzzone, Francesco Longo, Antonella Petrillo
Pages10-15
Number of pages6
ISBN (Electronic)9788885741454
DOIs
Publication statusPublished - 18 Sep 2020
Event32nd European Modeling and Simulation Symposium, EMSS 2020 - Virtual, Online
Duration: 16 Sep 202018 Sep 2020

Publication series

Name32nd European Modeling and Simulation Symposium, EMSS 2020

Conference

Conference32nd European Modeling and Simulation Symposium, EMSS 2020
CityVirtual, Online
Period16/09/2018/09/20

Keywords

  • Autonomous robots
  • Discrete-event simulation
  • Reinforcement learning

Fingerprint

Dive into the research topics of 'A simulation of autonomous robot movement directed by reinforcement learning'. Together they form a unique fingerprint.

Cite this