In this paper, an action selection mechanism (ASM) is proposed for each agent given its role in a multiagent system for robot soccer. The robot soccer game has very dynamic and uncertain characteristics. Furthermore, there exist competitions between agents. The soccer-playing robot should take an appropriate action according to its given role such as striker or sweeper. A computational mechanism for such action selection is essential in this regard. Initially, a relatively simple ASM is designed for a situation with no opponents. Then, the mechanism incorporates some additional action selection schemes considering the opponents' behaviors. Particularly, a multilayer perceptron (MLP) is used to learn how a human being selects an action given a situation. The effectiveness of the proposed ASM is demonstrated through a real robot soccer game of S-MIROSOT (single-robot micro-robot world cup soccer tournament).
[1]
Peter Stone.
Broad Learning from Narrow Training: A Case Study in Robotic Soccer
,
1995
.
[2]
Jong-Hwan Kim,et al.
A cooperative multi-agent system and its real time application to robot soccer
,
1997,
Proceedings of International Conference on Robotics and Automation.
[3]
Lynne E. Parker,et al.
Adaptive action selection for cooperative agent teams
,
1993
.
[4]
Toby Tyrrell,et al.
Computational mechanisms for action selection
,
1993
.
[5]
Toby Tyrell,et al.
The use of hierarchies for action selection
,
1993
.
[6]
François Michaud,et al.
Fuzzy selection and blending of behaviors for situated autonomous agent
,
1996,
Proceedings of IEEE 5th International Fuzzy Systems.