Abstract | ||
---|---|---|
This paper presents a tactics using fuzzy logic mediator that selects proper robot action depending on the positions and the roles of adjacent two robots. Conventional Q-learning algorithm, where the number of states increases exponentially with the number of robots, is not suitable for a robot soccer system, because it needs so much calculation that processing cannot be accomplished in real time. A modular Q-learning algorithm reduces a number of states by partitioning the concerned area, where mediator algorithm for cooperation of robots is used additionally. The proposed scheme not only reduces a number of a calculation but also combines a robot action selection with robot cooperation by means of fuzzy logic system. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1007/11596448_18 | CIS (1) |
Keywords | Field | DocType |
robot cooperation,robot action selection,fuzzy logic mediator,conventional q-learning algorithm,states increases exponentially,fuzzy logic system,mediator algorithm,robot soccer system,proper robot action,modular q-learning algorithm,action selection,fuzzy logic,real time | Motion planning,Robot control,Computer science,Fuzzy logic,Artificial intelligence,Fuzzy control system,Robot,Action selection,Robotics,Fuzzy rule | Conference |
Volume | ISSN | ISBN |
3801 | 0302-9743 | 3-540-30818-0 |
Citations | PageRank | References |
3 | 0.40 | 3 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeongjun Lee | 1 | 3 | 0.40 |
Dongmin Ji | 2 | 3 | 0.40 |
Wonchang Lee | 3 | 7 | 1.60 |
Geuntaek Kang | 4 | 7 | 1.26 |
Moon G. Joo | 5 | 61 | 2.83 |