DISTRIBUTED TEAM FORMATION FOR HUMANOID ROBOT SOCCER

Onuralp Ulusoy, Sanem Sariel-Talay

2012

Abstract

In this paper, we propose an adaptive team formation strategy for humanoid robot soccer. The proposed strategy involves distributed cooperative decisions through both communication and observations. Two agent groups, namely defenders and attackers, are formed by a case-based group formation method. Attackers are formed for constructing an attacking formation around the ball and scoring a goal whenever possible while defenders are for blocking and constructing a defensive obstacle against the opponent team. Cooperative decisions are made using communication among team members. Distribution of agents on the field is ensured by Voronoi cell construction of each agent through observations in a distributed manner. Experiments are set in the RoboCup 3D Soccer Simulation League environment where our method is compared to earlier team formation methods. The results illustrate that a distributed Voronoi cell construction method combined with a case-based grouping algorithm outperforms the others. Furthermore, it has been shown that our method is also robust to communication failures.

References

  1. Aamodt A. and Plaza E., 1994. Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. Artificial Intelligence Communications 7:1, pp. 39-52.
  2. Aldebaran Robotics Official Website, 2011. http://www.aldebaran-robotics.com/
  3. Arkin, R., 1998. Behavior-Based Robotics. MIT Press, Cambridge, Massachusetts.
  4. Asta, S., Sonmez T., Ulusoy O., Alimoglu A., Ersen M., Sozmen O. and Sariel-Talay S., 2011. beeStanbul RoboCup 3D Simulation League Team Description Paper 2011. RoboCup 2011, Istanbul 5-11, July, 2011.
  5. Asta, S. and Sariel-Talay S., 2011. Nature-Inspired Optimization for Biped Robot Locomotion and Gait Planning. The 6th European Event on Nature-inspired Techniques in Scheduling, Planning and Timetabling, Torino, Italy, 27-29 April, 2011, pp. 434-443.
  6. Ayanian, N., Kumar, V. and Koditschek, D., 2011. Synthesis of Controllers to Create, Maintain, and Reconfigure Robot Formations with Communication Constraints. Springer Tracts in Advanced Robotics, Volume 70/2011, pp. 625-642.
  7. Burkhard, H. D., Krause, T., Mellmann, H., Ritter, C. N., Xu, Y., Scheunemann, M., Schneider, M. and Holzhauer, F., 2011. NaoTH 2011 The RoboCup Team of Humboldt-Universitat zu Berlin. RoboCup 2011, Istanbul 5-11, July, 2011.
  8. Candea, C., Hu, H., Iocchi, L., Nardi, D. and Piaggio, M., 2001. Coordination in multi-agent RoboCup teams. Robotics and Autonomous Systems, Volume 36, Issues 2-3, pp. 67-86.
  9. Balch, T. and Arkin, R., 2000. Behavior-Based Formation Control for Multirobot Teams. Proceedings of Fourth International Conference on Multi-Agent Systems, pp. 363-364.
  10. Dashti, H. T., Aghaeepour, N., Asadi, S., Bastani, M., Delafkar, Z., Disfani, F.M., Ghaderi, S.M., Kamali, S., Pashami, S. and Siahpirani, A.F., 2006. Dynamic Positioning based on Voronoi Cells. RoboCup 2005. LNCS (LNAI), vol. 4020, pp. 219-229.
  11. de Berg, M., van Kreveld, M., Overmars, M. and Schwarzkopf, O., 2000. Computational Geometry. Springer-Verlag, New York, 2000.
  12. Nair, R., Tambe, M. and Marsella, S., 2003. Team Formation for Reformation in Multiagent Domains Like RoboCupRescue. RoboCup 2002: Robot Soccer World Cup VI, Lecture Notes in Computer Science, Volume 2752/2003, pp. 150-161.
  13. Nakanishi, R., Murakami, K. and Naruse, T., 2008. Dynamic Positioning Method Based on Dominant Region Diagram to Realize Successful Cooperative Play. RoboCup 2007: Robot Soccer World Cup XI Lecture Notes in Computer Science, Volume 5001/2008, pp. 488-495.
  14. Reis L. P., Lau N., Oliveira E.C., 2001. Situation Based Strategic Positioning for Coordinating a Team of Homogeneous Agents. Springer's Lecture Notes in Artificial Intelligence, Vol.2103, Berlin, pp. 175-197.
  15. Ros, R., Arcos, J. L., de Mantaras, R. L. and Veloso, M., 2009. A case-based approach for coordinated action selection in robot soccer. Artificial Intelligence, v.173 n.9-10, pp. 1014-1039.
  16. Röfer, T., 2003. An Architecture for a National RoboCup Team. RoboCup 2002: Robot Soccer World Cup VI, Lecture Notes in Computer Science, Volume 2752/2003, pp. 417-425.
  17. Simspark Official Website, 2011. http://simspark. sourceforge.net/
  18. Stoecker, J. and Visser, U., 2011. RoboViz: Programmable Visualization for Simulated Soccer. RoboCup 2011, Istanbul 5-11, July, 2011.
  19. Stone, P. and Veloso, M., 1999. Task Decomposition and Dynamic Role Assignment for Real-Time Strategic Teamwork. Intelligent Agents V: Agents Theories, Architectures, and Languages, Lecture Notes in Computer Science, Volume 1555/1999, pp. 293-308.
Download


Paper Citation


in Harvard Style

Ulusoy O. and Sariel-Talay S. (2012). DISTRIBUTED TEAM FORMATION FOR HUMANOID ROBOT SOCCER . In Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012) ISBN 978-989-8425-95-9, pages 605-613. DOI: 10.5220/0003881006050613


in Bibtex Style

@conference{ssir12,
author={Onuralp Ulusoy and Sanem Sariel-Talay},
title={DISTRIBUTED TEAM FORMATION FOR HUMANOID ROBOT SOCCER},
booktitle={Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012)},
year={2012},
pages={605-613},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003881006050613},
isbn={978-989-8425-95-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 4th International Conference on Agents and Artificial Intelligence - Volume 1: SSIR, (ICAART 2012)
TI - DISTRIBUTED TEAM FORMATION FOR HUMANOID ROBOT SOCCER
SN - 978-989-8425-95-9
AU - Ulusoy O.
AU - Sariel-Talay S.
PY - 2012
SP - 605
EP - 613
DO - 10.5220/0003881006050613