We have developed intelligent agent technology for automating functions of mission critical human teams (e.g. military or civilian crisis action C2 teams), such as information gathering and filtering, mission planning, and execution monitoring. The operating environments of such teams are distributed, time stressed, uncertain and open. An open environment is one where new tasks and goals arrive dynamically, where information sources, communication links and agents dynamically appear and disappear.

During a crisis, military commanders and their staff waste precious hours manipulating information systems, sifting through huge quantities of information for critical bits and pieces, manually specifying details, and performing manually routine tasks in order to assess the situation, form, evaluate and execute plans. Technology based on teams of intelligent agents that act autonomously to perform delegated tasks on behalf of users offers great potential for easing, automating and speeding many of these jobs.

The potential impact of the successful development and deployment of agent technology to aid mission critical teams is manifold and measurable: (1) reduce time for a C2 team to arrive at a decision, (2) allow C2 teams to consider a broader range of alternatives, (3) allow a C2 team to flexibly manage contingencies by replanning, (4) reduce time for a C2 team to form a shared situational model, (5) reduce individual and team errors, (6) support team cohesion and (7) increase overall team performance.

The successful incorporation of intelligent agents into human teams would have far reaching implications, not only for the military but for many additional domains, such as civilian emergency response teams, concurrent engineering, health-care, and education.

Multidisciplinary University Research Initiative (MURI)
Principal Investigator: Katia Sycara
Sponsored by: Office of Naval Research (ONR)
ONR Contact: Michael Shneier
© 1998 Carnegie Mellon Robotics Institute