Task decomposition support to reactive scheduling

This paper describes the development of an intelligent tasking model which has been designed to enable complex systems, human agents and software agents, to be tasked and controlled within a reactive workflow management paradigm. The task models exploit recent advances within the AI community in reactive control, scheduling and continuous execution. The Dynamic Execution Order Scheduler (DEOS) extends the current workflow paradigm to allow tasking in dynamic and uncertain environments by viewing the planning and scheduling tasks as being integrated and evolving entities. DEOS is being applied to the domains of Air Campaign Planning (ACP) and Intelligence, Surveillance and Reconnaissance (ISR) management. These are highly reactive domains in which new tasks and priorities are identified continuously and plans and schedules are generated and updated within a temporal and resource constrained setting.