Abstract

ABSTRACT Distributed Artificial Intelligence (DAI) systems in which multiple problem solving agents cooperate to achieve a common objective is a rapidly emerging and promising technology. However, as yet, there have been relatively few reported cases of such systems being employed to tackle real-world problems in realistic domains. One of the reasons for this is that DAI researchers have given virtually no consideration to the process of incorporating pre-existing systems into a community of cooperating agents. Yet reuse is a primary consideration for any organisation with a large software base. To redress the balance, this paper reports on an experiment undertaken at the CERN laboratories in which two pre-existing and standalone expert systems for diagnosing faults in a particle accelerator were transformed into a community of cooperating agents. The experiences and insights gained during this process provide a valuable first step towards satisfying the needs of potential users of DAI technology -identifying the types of changes required for cooperative problem solving, quantifying the effort involved in transforming standalone systems to ones suitable for cooperation and highlighting the benefits of a cooperating systems approach in a realistic industrial application.