Communication and Coordination among heterogeneous Mid-Size Players: ART99
Distributed coordination among robotic soccer agents has been considered in the recent years within the framework offered by the RoboCup competitions, mostly in the simulation and F-180 leagues. In this paper we describe the methods and the results achiev
- PDF / 220,904 Bytes
- 10 Pages / 451 x 677.3 pts Page_size
- 55 Downloads / 192 Views
Claudio Castelpietra1 , Luca Iocchi1 , Daniele Nardi1 , Maurizio Piaggio2, Alessandro Scalzo2 and Antonio Sgorbissa2 1 2
Dipartimento di Informatica e Sistemistica Universita \La Sapienza", Roma, Italy Dipartimento di Informatica, Sistemistica e Telematica Universita di Genova, Italy
Distributed coordination among robotic soccer agents has been considered in the recent years within the framework o ered by the RoboCup competitions, mostly in the simulation and F-180 leagues. In this paper we describe the methods and the results achieved in coordinating the players of the ART team participating in the F-2000 league. The team is formed by several heterogeneous robots having di erent mechanics, di erent sensors, di erent control software, and, in general, di erent abilities for playing soccer. The coordination framework we have developed has been successfully applied during the 1999 oÆcial competitions allowing both for a signi cant improvement of the overall team performance and for a complete interchangeability of all the robots. Abstract.
1
Introduction
Distributed coordination of robotic agents [7] has been considered as one of the central research issues in the RoboCup competitions [2, 4]. In a highly dynamic and uncertain environment such as the one provided by RoboCup games, the centralized coordination of activities underlying much of the work in Robotics does not seem to be adequate. In particular, the possible communication failures as well as the diÆculty of constructing a global reliable view of the environment, require full autonomy on each robot. The coordination problem in the context of RoboCup was rst faced in the simulation league [6, 8], where it plays a central role because of the high number of players (11). In the small size league coordination can take advantage of the availability of global information on the game status, since a centralized vision system and elaboration is used [12]. In the F-2000 (middle size) league, although the number of players is 4 (including the goal keeper), coordination among the players is still a critical issue because the dynamics of the game make it necessary to avoid interferences among players' actions. However, the distinguishing feature of the F-2000 league is the diÆculty of reconstructing global information about the environment and thus coordination needs to be achieved without laying down drastic prerequisites on the knowledge of the single players. The implementation of cooperative strategies for a team of robots can be addressed by relying on explicit communication [13] or by exploiting implicit P. Stone, T. Balch, and G. Kraetzschmar (Eds.): RoboCup 2000, LNAI 2019, pp. 86-95, 2001. c Springer-Verlag Berlin Heidelberg 2001
Communication and Coordination among Heterogeneous Mid-size Players: ART99
87
communication and emergent behaviors [5]. Our choice has been to rely on explicit communication for implementing cooperative strategies; however, due to the frequent communication failures the robots must depend neither on communication, nor on inf
Data Loading...
