COOPERATIVE MULTI-ROBOT SYSTEM FOR INFRASTRUCTURE SECURITY TASKS

Erik Hernandez, Antonio Barrientos, Claudio Rossi, Jaime del Cerro

2012

Abstract

As a result of terrorist attacks in the last years, new efforts have raised trying to solve challenges related to security task automation using robotic platforms. In this paper we present the results of a cooperative multi-robot approach for infrastructure security applications at critical facilities. We formulate our problem using a Ms. Pac-Mac like environment. In this implementation, multiple robotic agents define policies with the objective to increase the number of explored states in a grid world. This is through the application of the off-policy learning algorithm from reinforcement learning area, known as Q-learning. We validate experimentally our approach with a group of agents learning a patrol task and we present results obtained in simulated environments.

References

  1. Chevaleyre, Y. (2004). Theoretical analysis of the multi-agent patrolling problem. In Intelligent Agent Technology, 2004.(IAT 2004). Proceedings. IEEE/WIC/ACM International Conference on, pages 302-308. IEEE.
  2. Elmaliach, Y., Agmon, N., and Kaminka, G. (2007). Multirobot area patrol under frequency constraints. Annals of Mathematics and Artificial Intelligence.
  3. Everett, H. (2003). Robotic security systems. Instrumentation & Measurement Magazine, IEEE.
  4. Kaelbling, L., Littman, M., and Moore, A. (1996). Reinforcement learning: A survey. Arxiv preprint cs/9605103.
  5. Khamis, A., Kamel, M., and Salichs, M. (2006). Cooperation: concepts and general typology. In Systems, Man and Cybernetics, 2006. SMC'06. IEEE International Conference on, volume 2, pages 1499-1505. IEEE.
  6. Luo, R. and Lin, T. (2009). Multisensor based security robot system for intelligent building. Robotics and Autonomous Systems.
  7. Oates, R., Milford, M., and Wyeth, G. (2009). The implementation of a novel, bio-inspired, robotic security system. , 2009. ICRA'09.
  8. Puterman, M. (1994). Markov decision processes: discrete stochastic dynamic programming. John Wiley & Sons, Inc.
  9. Roman-Ballesteros, I. (2006). A framework for cooperative multi-robot surveillance tasks. Robotics and Electronics.
  10. Sutton, R. and Barto, A. (1998). Reinforcement learning: An introduction, volume 116. Cambridge Univ Press.
  11. Watkins, C. and Dayan, P. (1992). Q-Learning. Machine learning, 8(3):279-292.
Download


Paper Citation


in Harvard Style

Hernandez E., Barrientos A., Rossi C. and del Cerro J. (2012). COOPERATIVE MULTI-ROBOT SYSTEM FOR INFRASTRUCTURE SECURITY TASKS . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-8425-96-6, pages 313-316. DOI: 10.5220/0003721403130316


in Bibtex Style

@conference{icaart12,
author={Erik Hernandez and Antonio Barrientos and Claudio Rossi and Jaime del Cerro},
title={COOPERATIVE MULTI-ROBOT SYSTEM FOR INFRASTRUCTURE SECURITY TASKS},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2012},
pages={313-316},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003721403130316},
isbn={978-989-8425-96-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - COOPERATIVE MULTI-ROBOT SYSTEM FOR INFRASTRUCTURE SECURITY TASKS
SN - 978-989-8425-96-6
AU - Hernandez E.
AU - Barrientos A.
AU - Rossi C.
AU - del Cerro J.
PY - 2012
SP - 313
EP - 316
DO - 10.5220/0003721403130316