Scheduling of tasks for a future space mission under joint management by distributed control centers responsible for different components of the mission objective will be faced with different priorities, release dates, deadlines, inter dependencies, and even conflicting demands on instruments, communication channels, and expendable resources. This project investigates a neural-network-based sequencer for the generation and continuous optimization of task schedules which, taking into account resource constraints, internal states, and external dynamics, balances the requirements of distributed control centers. The central innovation of this dynamic sequencer is an optimizing scheduling loop. The heart of this loop is a modified Hopfield network whose many-termed energy function is constructed to reflect task priority, processing expenditure (time and resources), communication requirements, resource constraints, and time dependencies.
Potential Commercial Applications: An optimizing planner is a key element in manufacturing systems such as just-in-time manufacturing and factory automation for improved productivity.STATUS: Phase I Only
