Solving disagreements in a Multi-Agent System performing Situation Assessment

Situation Assessment and decision making mirossi@selex-si.comin monitoring and surveillance scenarios are evolvingfrom centralized models to high-level, reasoning oriented,net-centric models, according to new information fusionparadigms proposed by recent research.In this paper, we propose the design of a multi-agent architecturefor Situation Assessment, where situations areclassified through agent collaboration, in order to providehuman operators with a synthetic vision, that points out theelements of the scenario that require human intervention.Specifically, our approach provides for: i) high level classificationof situations based on OWL ontology reasoning; ii)distributed assessment by a protocol which solves disagreementspossibly arising among agents’ conclusions.Experiments in a real maritime surveillance scenarioshow that the proposed approach approximates the resultsof a centralized architecture, while preserving independencyof decision makers and dramatically reducing the amount ofcommunication required.