DEVS-Based Endomorphic Agents: Control Through Deliberative and Reactive Planning

A DEVS-based Endomorphic Agent employs models of the environment and itself to achieve autonomy in various way. In this paper, we present a framework for an agent able to flexibly reprogram itself under changing objectives or constraints such as might be provided in a flexible manufacturing environment. We show how the agent is able to employ its DEVS-models to develop control schemes for given objectives and constraints. The schemes can then be revised as required when a change in the desired objectives or constraints occurrs. The systems model knowledge representation thus gives the agent greater flexibility and autonomy than is possible with purely rective planners or supervisory controllers.