The Research Center for Team-Based Agents aims to develop agents with "team intelligence", which enables them to support and enhance collaborative activities of teams, which may include both human users and software agents. The center's research will build on the findings and theories about effective human team behaviors and incorporate them into intelligent agent technologies. Psychologists who study human teamwork have pointed out that intelligent team behaviors rely on overlapping shared mental models among team members. For example, a competent human team member can anticipate the needs of teammates, offer relevant information proactively, and avoid overloading teammates by assessing current load levels.

      Therefore, a focus of the Research Center for Team-Based Agents is to develop technologies that enable agents in a team to exhibit intelligent team behavior using a computational shared mental model.  To launch our research we have developed a team-based agent architecture called CAST (Collaborative Agents for Simulating Teamwork).  CAST agents anticipate information needs of teammates based on their knowledge about the structure and process of the team, as well as their beliefs about their teammates and the environment. 

      Current research projects of the Research Center for Team-Based Agents investigate formal foundations, extensions, and applications of CAST. These projects are supported by the Air Force Office of Scientific Research (MURI), National Science Foundation (ITR), the Army Research Office, and the Army Research Lab.

-- John Yen
Director,
Research Center for
Team-based Agents