next up previous
Next: Overview Up: Multiagent Systems: A Survey Previous: Further Learning Opportunities

Robotic Soccer


Several multiagent domains have been mentioned throughout the course of this survey, including design, planning, entertainment, games, air-traffic control, air combat, personal assistants, load-balancing, and robotic leg control. In this section a single domain which embodies most multiagent issues is presented.

Robotic soccer is a particularly good domain for studying MAS. Originated by Alan Mackworth [70], it has been gaining popularity in recent years, with several international competitions taking place [43, 44, 33]. It is also the subject of an official IJCAI-97 Challenge [45]. It can be used to evaluate different MAS techniques in a direct manner: teams implemented with different techniques can play against each other.

Although the pursuit domain serves us well for purposes of illustration, robotic soccer is much more complex and interesting as a general testbed for MAS. Even with many predators and several prey, the pursuit domain is not complex enough to simulate the real world. Although robotic soccer is a game, most real-world complexities are retained. A key aspect of soccer's complexity is the need for agents not only to control themselves, but also to control the ball which is a passive part of the environment.

Peter Stone
Wed Sep 24 11:54:14 EDT 1997