Human team formation, where one or more teams must be constructed from a large heterogeneous pool of candidates, is one area where DCOP can be applied to practical use. While this can be formulated as centralized COP as well, using k-optimal assignment methods within DCOP is a logical choice to ensure a diverse set of choices, which would be optimal within a group of similar team choices.
The Automated Mission Scheduler (AMS) will automatically create a mission plan for heterogeneous, multiple unmanned vehicles performing joint actions under the control of collaborating operators. The objective is to support dynamic mission scheduling in response to high-level mission objectives, priorities, constraints. Accordingly, the plans will include allocation of required mission tasks, including specific assignments to vehicles as well as sequencing of individual vehicle and mission tasks to achieve the collective objectives. Output of AMS will be used as a decision aid to the collaborating operators as well as for direct control as a component of evolving mixed initiative interface modules concepts. Our team has already made significant progress toward achieving the project goals, and our system is based on work to apply Distributed Constraint Optimization to optimally allocate multi-vehicle tasks in collaborative control of Unmanned Vehicles.
