Klaus Dorer
Albert-Ludwigs-Universität Freiburg, Germany
Ladda ner artikel
Ingår i: RobocCup-99 Team Descriptions. Simulation League
Linköping Electronic Conference Proceedings 4:17, s. 79-83
Linköping Electronic Articles in Computer and Information Science vol. 4 4:17, p. 79-83
Publicerad: 1999-12-15
ISBN:
ISSN: 1650-3686 (tryckt), 1650-3740 (online)
In this paper we descibe the process of action control used by the agents of the magmaFreiburg team. It is based on extended behavior networks; which add situation-dependent motivational influence on the agent and extend original behavior networks to exploit information from continuous domains. Advantages of the original networks; such as reactivity; planning capabilities; robustness; accountance for multiple goals and its cheap and distributed calculations are maintained.
[1] Agre; Ph.; and Chapman; D. (1987). Pengi: An Implementation of a Theory of Activity. In: Proceedings of the Sixth National Conference on Artificial Intelligence; AAAI-87; Morgan Kaufmann; Los Altos.
[2] Dorer; K. (1999). Behavior Networks for Continous Domains using Situation-Dependent Motivations. To appear in: Proceedings of the 16th International Joint Conference on Arti cial Intelligence; Morgan Kaufmann; Stockholm.
[3] Goetz; Ph. (1997). Attractors in Recurrent Behavior Networks. PhD thesis; State University of New York;Buffalo
[4] Maes; P. (1989). The Dynamics of Action Selection. In Proceedings of the International Joint Conference on Artificial Intelligence-’89 ; Morgan Kaufmann; Detroit.
[5] Maes; P. (1990). Situated Agents Can Have Goals. In Journal for Robotics and Autonomous Systems; Vol. 6; No 1; pages 49-70; North- Holland.
[6] Maes; P. (1992). Learning Behavior Networks from Experience. In Varela; F. and Bourgine; P. Proceedings of the First European Conference on Artificial Life; pages 48-57; MIT-Press; Paris.
[7] Noda; I. (1995). Soccer server: a simulator of robocup. In Proceedings of AI symposium ’95; pages 29-34; Japanese Society for Artificial Intelligence.
