Beliefs and Conflicts in a Real World Multiagent System

Malheiro, Benedita and Varga, László Zsolt and Oliveira, Eugenio (1998) Beliefs and Conflicts in a Real World Multiagent System. In: Proceedings of the International ICSC Symposium on Engineering of Intelligent Systems (EIS’98): University of La Laguna, Tenerife, Spain, February 11-13, 1998. International Computer Science Conventions Academic Press, Millet, Alta, pp. 322-329. ISBN 3-906454-11-8

Preview

Text 1149266.pdf Download (51kB) | Preview

Abstract

In a real world multiagent system, where the agents are faced with partial, incomplete and intrinsically dynamic knowledge, conflicts are inevitable. Frequently, different agents have goals or beliefs that cannot hold simultaneously. Conflict resolution methodologies have to be adopted to overcome such undesirable occurrences. In this paper we investigate the application of distributed belief revision techniques as the support for conflict resolution in the analysis of the validity of the candidate beams to be produced in the CERN particle accelerators. This CERN multiagent system contains a higher hierarchy agent, the Specialist agent, which makes use of meta-knowledge (on how the conflicting beliefs have been produced by the other agents) in order to detect which beliefs should be abandoned. Upon solving a conflict, the Specialist instructs the involved agents to revise their beliefs accordingly. Conflicts in the problem domain are mapped into conflicting beliefs of the distributed belief revision system, where they can be handled by proven formal methods. This technique builds on well established concepts and combines them in a new way to solve important problems. We find this approach generally applicable in several domains.

Actions (login required)

Edit Item