FC Portugal 2004 Team: Strategic Positioning for 3D Soccer Nuno Lau 1,3 , Luís Paulo Reis 2,4 , Hugo Marques 1,3 , Hugo Penedones 2,4 , Rui Ferreira 2,4 , Rui Sampaio 2,4 lau@det.ua.pt, lpreis@fe.up.pt 1 DET – Electronics and Telecommunications Department, University of Aveiro, Portugal 2 FEUP –Faculty of Engineering of the University of Porto, Portugal 3 IEETA – Institute of Electronics and Telematics Engineering of Aveiro, Portugal 4 LIACC – Artificial Intelligence and Computer Science Lab., University of Porto, Portugal http://www.ieeta.pt/robocup 1. Introduction FC Portugal 2004 3D team is strongly based on FC Portugal 2D simulation league team [1, 2, 3]. In our 2D teams, which participated in RoboCup since 2000, we have introduced several concepts and algorithms covering a broad spectrum of the soccer simulation research challenges. From coordination techniques such as Tactics, Formations, Dynamic Positioning and Role Exchange, Situation Based Strategic Positioning and Intelligent Perception to Optimization based low-level skills, Visual Debugging and Coaching, the number of research aspects FC Portugal has been working on is quite extensive [1, 3]. The research-oriented development of our team has been pushing it to be one of the most competitive over the years (World champion in 2000 and Coach champion in 2002, European champion in 2000 and 2001 and always in the top five places in all major world competitions since 2000). FC Portugal 3D team develops on the previous 2D team in several ways. It has an identical high-level structure [1, 3], adapted to the 3D specificities and completely rewritten low- level skills, still being developed and far from being effective 1 . 2. Current Status The current status of our team is quite simple at the moment. Agent’s individual behavior is focused on intercepting the ball and kicking it to the opponent goal. Team behavior is basically defined by maintaining a simple 4x3x3 formation that moves smoothly on the field depending on ball position. 2.1 Agent Behavior Agent’s individual behavior is composed by two low-level skills: • Move_to_Point(X,Y) – Agent movement to point (X,Y) starts by accelerating the player at full speed but depending on distance to target, player velocity is decreased so that the player may arrive to its destination at a reduced speed. • Kick_to_Point(X,Y) – When near the ball, the agent positions itself in a point that enables it to kick the ball in the right direction 2 and sends a kick command to the server. Although our low-level skills are still quite simple, one of our agents following this approach is capable of scoring goals against the sample agent team. 1 Soccer Server 3D is still far from being a stable and documented platform and thus, low-level skill development is still a hard and cumbersome task. 2 In our current binary, agent’s kick the ball always to the opponent’s goal.