Robotic soccer is a very good example of a PTS domain: teams can coordinate before the game, at half-time, and at other break points, but communication is limited during play [10, 12]. Robotic soccer systems have been recently developed both in simulation [14, 24, 25] and with real robots [1, 9, 19, 20, 28]. The research presented in this paper was first developed in simulation and it has also been successfully used on our real robot team.
The soccer server [16], version 3 of which serves as the substrate simulator for the research reported in this paper, captures enough real-world complexities to be a very challenging domain. This simulator is realistic in many ways: (i) the players' vision is limited; (ii) the players can communicate by posting to a blackboard that is visible (but not necessarily intelligible) to all players; (iii) each player is controlled by a separate process; (iv) each team has 11 members; (v) players have limited stamina; (vi) actuators and sensors are noisy; (vii) dynamics and kinematics are modelled; and (viii) play occurs in real time: the agents must react to their sensory inputs at roughly the same speed as human or robotic soccer players. The Soccer Server was successfully used as the basis for the RoboCup-97 simulator competition in which 29 teams participated [10].
One approach to task decomposition in the Soccer Server is to assign
fixed positions to agents.
Such an approach leads to several problems: i) short-term
inflexibility in that the players cannot adapt their positions to the
ball's location on the field; ii) long-term inflexibility in that the
team cannot adapt to opponent strategy; and iii) local inefficiency in
that players often get tired running across the field back to their
positions after chasing the ball. Our formations allow for flexible
teamwork and combat these problems. (As the term ``position'' is
often used to denote the concept of ``role'' in the soccer domain, in
this section we use the two terms interchangeably.)