End User Specification of RoboCup Teams
Creating complex agents for simulation environments has long been the exclusive realm of AI experts. However it is far more desirable that experts in the particular application domain, rather than AI experts, are empowered to specify agent behavior. In this paper an approach is presented that allows domain experts to specify the high-level team strategies of agents for RoboCup. The domain experts’ specifications are compiled into behavior based agents.
The 1999 RoboCup World Cup provided an interesting basis for evaluation of the approach. We found that for RoboCup it is not necessary to allow a user to change low level aspects of the agents’ behavior in order for them to create a range of different, interesting teams. We also found that the modular nature of behavior based architectures make them an ideal target architecture for compiling enduser specifications.
KeywordsDomain Expert Speci Cation Team Behavior High Level Behavior Team Strategy
Unable to display preview. Download preview PDF.
- 1.Bruce Blumberg and Tinsley Galyean. Multi-level control of autonomous animated creatures for real-time virtual environments. In Siggraph’ 95 Proceedings, pages 295–304, New York, 1995. ACM Press.Google Scholar
- 2.Rodney Brooks. Intelligence without reason. In Proceedings 12th International Joint Conference on AI, pages 569–595, Sydney, Australia, 1991.Google Scholar
- 3.Hiraoki Kitano, Minoru Asada, Yasuo Kuniyoshi, and et. al. RoboCup: A challenge problem for AI. AI Magazine, 18(1):73–85, Spring 1997.Google Scholar
- 4.Paul Scerri, Silvia Coradeschi, and Anders Törne. A user oriented system for developing behavior based agents. In Proceedings of RoboCup’98, Paris, 1998.Google Scholar