AUTONOMOUS NAVIGATION ROBOTIC SYSTEM TO RECOGNIZE IRREGULAR PATTERNS

Danny Dos Santos, Rafael Peñalver, Wílmer Pereira

Abstract

This paper presents an approximation of navigation problem under unknown environment using reinforcement learning. The motivation is to represent a robot that can move in a world with streets and intersections. Each intersection has a different quantity of streets (irregular blocks). The selected algorithms were Q-Learning and Value Iteration. The robot was programmed only with Q-Learning and we developed a simulation with both of them. This simulation allows making comparisons in order to determinate in which situation each algorithm is appropriate.

References

  1. Bagnall, B. 2002, CORE Lego MindstormsTM Programming. Edit. Prentice Hall PTR. New York, United States of America.
  2. Ferrari, G., Gombos, A. Hilmer, S., Stuber, J., Porter, M., Waldinger, J. and Laverde, D. 2002, Programming Lego MindstormsTM with Java. Edit. Sysgress. United States America.
  3. Russel, S. and Norvig, P. 1996, Artificial Intelligence A modern approach. First edition. Edit. Prentice Hall, 1996.
  4. Carrasquero Z., Oscar H. and McMaster F., Eduardo 2002, Design and a robot's construction with the module RCX 1.0 for not predetermined worlds (Thesis of Engineer in Computer, Catholic University Andrés Bello).
  5. Bagnall, Bryan 2001, LejOS: Java for the RCX. [web page on-line] Consulted in 10/5/2003 Available in http://lejos.sourceforge.net /.
  6. Dartmouth College Computer Science Department (2001). Robbery-Rats Locomotion: Dual Differential Drive. [web page on-line] Consulted in 20/5/2003 Available in http://www.cs.dartmouth.edu/robotlab/robotlab/cour ses/cs54-2001s/dualdiff.html
  7. Gross M., Stephan V. and Boehme J. 1996, Sensory based robot navigation using self-organizing networks and Q-Learning. [document on-line] Consulted in 12/9/2003 Available in http://citeseer.nj.nec.com/gross96sensorybased.htm
  8. Mance E. Harmon and Stephanie S. Harmon (s.f.). Reinforcement Learning: A Tutorial. [ document online] Consulted in 20/9/2003 Available in http://www.nada.kth.se/kurser/kth/2D1432/2003/rltut orial.pdf.
  9. Touzet, Claude F. 1999, Neural Networks and Q-Learning for Robotics. [document on-line] Consulted in 3/9/2003 Available in http://avalon.epm.ornl.gov/touzetc/Publi/Touzet_IJC NN_Tut.pdf.
  10. Zou Yi, Ho Yeong Khing, Chua Chin Seng and Zhou Xiao Wei 2003, Evidence method in ultrasonic sensor coalition for mobile robots. [document on-line] Consulted in 10/8/2003 Available in http://www.duke.edu/yz21/research/YZ_IASTEDMIC2000.pdf.
Download


Paper Citation


in Harvard Style

Dos Santos D., Peñalver R. and Pereira W. (2004). AUTONOMOUS NAVIGATION ROBOTIC SYSTEM TO RECOGNIZE IRREGULAR PATTERNS . In Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO, ISBN 972-8865-12-0, pages 295-301. DOI: 10.5220/0001145902950301


in Bibtex Style

@conference{icinco04,
author={Danny Dos Santos and Rafael Peñalver and Wílmer Pereira},
title={AUTONOMOUS NAVIGATION ROBOTIC SYSTEM TO RECOGNIZE IRREGULAR PATTERNS},
booktitle={Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,},
year={2004},
pages={295-301},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001145902950301},
isbn={972-8865-12-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the First International Conference on Informatics in Control, Automation and Robotics - Volume 2: ICINCO,
TI - AUTONOMOUS NAVIGATION ROBOTIC SYSTEM TO RECOGNIZE IRREGULAR PATTERNS
SN - 972-8865-12-0
AU - Dos Santos D.
AU - Peñalver R.
AU - Pereira W.
PY - 2004
SP - 295
EP - 301
DO - 10.5220/0001145902950301