Fuzzy Prolog as Cognitive Layer in RoboCupSoccer

RoboCupSoccer domain has several leagues which varies in the rule of play such as specification of players, number of players, field size, and time length. Nevertheless, each RoboCup league is a variant of a soccer league and therefore they are based on some basic rules of soccer. A layered design of agents system presented in the work of Garcia et al. (2004) shows a modular approach to build control for a team of robots participating in RoboCupSoccer E-League. Based on this design, we propose a generalized architecture offering flexibility to switch between leagues and programming language while maintaining Prolog as cognitive layer. Prolog is a very convenient tool to design strategies for soccer players using simple rules close to human reasoning. Sometimes this reasoning needs to deal with uncertainty, fuzziness or incompleteness of the information. In these cases it is useful Fuzzy Prolog (Guadarrama et al., 2004), (Munoz-Hernandez and Vaucheret, 2005), (Munoz-Hernandez and Gomez-Perez, 2005), (Munoz-Hernandez and Vaucheret, 2006). In this paper we propose to use a combination of Prolog (that is crisp) and Fuzzy Prolog to implement the cognitive layer in RoboCupSoccer, which has the advantage of incorporating as conventional logic as fuzzy logic in this layer. A prototype of a team based on this architecture has been build for RoboCup soccer simulator, and we show that this approach provides a convenient way of incorporating a team strategy in high level (human-like) manner, where technical details are encapsulated and fuzzy information is represented