|
Digital Library of the
European Council for Modelling and Simulation |
Title: |
Robot Soccer - Strategy Description And Game
Analysis |
Authors: |
Jan Martinovič, Václav Snáńel, Elińka Ochodková, Lucie Ņołtá, Jie Wu, Ajith Abraham |
Published in: |
(2010).ECMS
2010 Proceedings edited by A Bargiela S A Ali D Crowley E J H Kerckhoffs.
European Council for Modeling and Simulation. doi:10.7148/2010 ISBN:
978-0-9564944-1-2 24th
European Conference on Modelling and Simulation, Simulation Meets Global Challenges Kuala
Lumpur, June 1-4 2010 |
Citation
format: |
Martinovic, J., Snasel, V.,
Ochodkova, E., Zolta, L., Wu, J., & Abraham, A. (2010). Robot Soccer -
Strategy Description And Game Analysis. ECMS 2010 Proceedings edited by A
Bargiela S A Ali D Crowley E J H Kerckhoffs (pp. 265-270). European Council
for Modeling and Simulation. doi:10.7148/2010-0265-0270 |
DOI: |
http://dx.doi.org/10.7148/2010-0265-0270 |
Abstract: |
The
robot soccer game, as a part of standard applications of distributed system
control in real time, provides nu- merous opportunities for the application
of AI. Real-time dynamic strategy description and strategy learning possi-
bility based on game observation are important to dis- cover opponent’s
strategies, search tactical group move- ments and synthesize proper
counter-strategies. In this paper, the game is separated into physical part
and logi- cal part including strategy level and abstract level. Corre-
spondingly, the game strategy description and prediction of ball motion are
built up. The way to use this descrip- tion, such as learning rules and
adapting team strategies to every single opponent, is also discussed. Cluster
anal- ysis is used to validate the strategy extraction. |
Full
text: |