A Distributed Multiagent Architecture for Temasek Robocup Team (TPots).

Abstract

Temasek Robocup team ( TPots ) started with the organiza- tion of the 1998 Pacic Rim Series Robocup competition in Singapore. That was our rst participation to robotic soccer game competition. Since then we have been working on the development of a control architecture distribut- ed among the physical robots and the workstation. This paper describes the overall design with an emphasis on the on board robot agents and o board agents. Robocup small league competition is considered by many AI pro- fessionals as an ideal platform for testing distributed articial intelligence techniques. Among these techniques are multiagent systems, since its debut in the late 80's it has been used in several multi robot systems. Ranging from cellular robot systems ( Fukuda et al ) (1) to a team of trash-collecting robots ( Arkin et al ) (2). In this paper we will present a distributed approach in implementing the multiagents architecture of Temasek Robocup team.