Reactive and deliberative control and cooperation in multi-agent system based process automation

An approach to intelligent process automation based on a society of BDI-agents is presented in this paper. According to this approach a higher-level multi-agent systems based automation layer supervises an ordinary process automation system. The purpose of the agent layer is to monitor the operation of the lower-level automation system and semi-autonomously reconfigure its control logic when needed. The agent layer operates as a multi-agent system consisting of BDI-agents, which cooperatively create and run reconfiguration sequences on the ordinary automation system in order to adapt its control logic to various situations. The adaptation process may take place both in reactive and deliberative fashion. In this way the approach aims to increase the flexibility and responsiveness properties of the automation system. The approach is demonstrated with a laboratory test process where process startup and fault recovery experiments have been performed. Results from the experiments are described.