A guardian agent approach to safety in medical multi-agent systems

Abstract

We present an overview of current work on argumentation based reasoning to ensure safety in medical multi-agent systems. In particular, we describe deployment of a specialised Guardian agent engaging in argumentation based reasoning about safety, and argumentation based dialogues with other agents to cooperatively ensure that agent activities are safe. The work is being conducted as part of a project aiming at development of theoretical models of argumentation, and their implementation in software components for deployment in agent technologies. The project has established a medical multi-agent scenario requiring deployment of the Guardian agent. This scenario provides a focus both for theoretical work and the eliciting of technical requirements. In this paper we describe the scenario and discuss the theoretical issues being addressed. © 2009 Springer Berlin Heidelberg.