Joccasta

 

 

 

 

Watch a video of the Joccasta Demo

Click here to go directly to our MURI Project Page.

In order to increase team decision making in the area of joint mission planning, we are incorporating intelligent software assistants into human teams. This Multidisciplinary University Research Initiative (MURI) brings together the Software Agents Group at Carnegie Mellon University, the Software Engineering Institute's research on multimedia information delivery, the Performance Studies Team at the Naval Air Warfare Training Systems Division, the University of Pittsburgh, and the NRL.

Software assistants can anticipate the information needs of their human team members, prepare and communicate task information, adapt to changes in situation and changes to the capabilities of other team members, and effectively support team member mobility. We are working on constructing software agents that can:

  1. Integrate information retrieval with user-centered problem solving and decision support;

  1. Monitor and cache environmental information actively;
  2. Form adaptive human and software agent teams as needed, depending on task and information requirements;
  3. Develop greater capacities for modeling users, situations, and their own performance and capabilities;
  4. Use their awareness of task and team interdependencies to work together more effectively.

We are drawing on cognitive science and human factors research to understand how individuals and teams represent tasks. Given that the goals of a team mission are often implicit, it is crucial that team and individual tasks are represented formally and explicitly. This will ensure that software assistants are integrated smoothly into human teams. Thus, key activities include identifying team and individual tasks, allocating roles and functions for performing those tasks, and defining task and role models for humans and their intelligent assistants.

Co-training is a key component of this research, which means that while humans are adapting to the capabilities, rationales, and behaviors of their software assistants, the software assistants are learning to anticipate the informational needs of particular human team members.

Finally, our RETSINA agents enable successful teamwork, as outlined in human factors research. The agents we are developing support team situation assessment, enhance team-supporting behaviors, enable more effective leadership, make possible more efficient communication among team members, and assist in conflict negotiation.

This research has implications for other types of planning teams that comprise multidisciplinary experts, including civilian emergency response teams, management teams, and single service military teams.

Related Pages:
Messenger
Tie-3 Demo


Robotics Institute Project Page

 

 

Copyright 2006 - 2012 © Advanced Agent-Robotics Technology Lab - The Robotics Institute - Carnegie Mellon University


Internal Site (Restricted Access).