Multi-Agent Systems Assisting Operators to Mastering Automation Systems

Abstract Multi Agent Systems (MAS) are software tools where in individual agents are cooperating for exchanging the knowledge of their specific domain. They are part of the concept of Distributed Artificial Intelligence (DAI). MAS can do decisions automatically without intervention of human operators or they can assist the human operators to mastering automation systems. In principle agents can learn what is called machine learning, but it is emphasized that it could be done co-operatively with the human operators of automation systems. A general consideration of the structure of decision supporting and assistance systems are also discussed.