Agent-based Team Aiding in a Time Critical Task

In this paper we evaluate the effectiveness of agent-based aiding in support of a time-critical team-planning task for teams of both humans and heterogeneous software agents. The team task consists of human subjects playing the role of military commanders and cooperatively planning to move their respective units to a common rendezvous point, given time and resource constraints. The objective of the experiment was to compare the effectiveness of agent-based aiding for individual and team tasks as opposed to the baseline condition of manual route planning. There were two experimental conditions: the Aided condition, where a Route Planning Agent (RPA) finds a least cost plan between the start and rendezvous points for a given composition of force units; and the Baseline condition, where the commanders determine initial routes manually, and receive basic feedback about the route. We demonstrate that the Aided condition provides significantly better assistance for individual route planning and team-based re-planning.