MokSAF: How Should We Support Teamwork in Human-Agent Teams?
Terri L. Lenox, Terry R. Payne, Susan Estabrooks Hahn, Michael Anthony Lewis, Katia P. Sycara · 1999
In this paper, we describe an interface agent, two different route planning agents and a pilot study which examined whether these agents could support a team planning task. The MokSAF interface agent links an Artificial Intelligence (AI) route-planning agent to a Geographic Information System (GIS). The user specifies a start and an end point and the route-planning agent finds a minimum cost path between the points. The user is allowed to define additional “intangible” constraints (not due to terrain characteristics) corresponding to geographic regions, which can be used to steer the agent’s behavior in a desired direction. A second agent (the naive route planning agent, or Naive RPA) has access to the same knowledge of the terrain and cost functions available to the Autonomous RPA, but uses this knowledge to critique paths specified by the user. We hypothesize that as the complexity of intangible aspects of a planning problem increase, the Naive RPA will improve in relative performance. The reported study found advantages across the board for the Autonomous RPA in a team-planning task.