Multi-robot coordination using Setplays in the middle-size and simulation leagues

Strategic planning and multi-agent coordination are major research topics in the domain of RoboCup. Innovations in these areas are, however, often developed and applied to only a single RoboCup league and/or one domain, without proper generalization. Moreover, the more technical leagues, like middle-size and humanoid, tend to focus development on low-level skills, that often suffice to gain a competitive edge over other teams. In these leagues, the development of high-level cooperation is secondary. Although the importance of the concept of Setplay, to structure a robotic soccer team behaviour, has been acknowledged by many researchers, no general framework for the development and execution of generic Setplays has been introduced in the context of RoboCup. This paper presents such a framework for high-level Setplay definition and execution, applicable to any RoboCup cooperative league and similar domains. The framework is based on a flexible, standard and league-independent language, which defines Setplays that are interpreted and executed at run-time, using inter-robot communication. An initial major step in the development of the Setplay framework was its usage and testing in the scope of the FCPortugal team, which participates in the RoboCup 2D-simulation and 3D-simulation leagues, where it won several titles both in the 2D and 3D leagues. This framework was also recently implemented in the middle-size team CAMBADA. This team has, in the recent past and with previous versions of the control software, ranked first and third in RoboCup's 2008 and 2009 editions. The implementation is described with concrete examples of Setplay definition and execution, which shows the usefulness of this approach and motivate its use as a major coordination tool for teams participating in the simulation, small-size, middle-size, standard platform and humanoid leagues of RoboCup. (C) 2010 Elsevier Ltd. All rights reserved.