The goal of the new DARPA COORDINATOR program is to develop technology to help fielded human units (e.g., soldiers, tactical teams) adapt their mission plans online in response to change. Coordination support will enable fielded units to respond more rapidly and more accurately to the dynamics of the situation while incurring less cognitive load and performing with a greater degree of coordinated action. Hard research problems include distributed coordination over large interconnected mission structures that change dynamically, supporting coordination of large-scale operations where units may have roles in multiple missions, learning to support the units better by automating decision making when data is potentially sparse, responding in "real time" to changes, and reasoning about military decision-making policies and procedures during coordination.
DARPA has selected TAEMS, the Task Analysis, Environment Modeling, and
Simulation language, as the one to be used to specify test scenarios
for COORDINATORS. This talk will give some personal perspective on
coordination as it led to the development of TAEMS, a TAEMS primer, and
a presentation of an initial set of challenge problems for the first 9
months of the program.