IBM ITA: Human-Agent Teamwork Models

Mailing address:
Carnegie Mellon University
Robotics Institute
5000 Forbes Avenue
Pittsburgh, PA 15213
Associated center: CIMDS
Associated lab/group: Intelligent Software Agents

Project Description

The focus of this project is to develop models of human-agent teamwork for implementation in software agent systems. Both human collaboration and software agent collaboration have been thoroughly studied, but there is relatively little prior work on hybrid human-agent teamwork. Some research has identified the roles that agents could play in hybrid teams (e.g. supporting individual team members, being a teammate, or supporting the team as a whole). Some other work has investigated trust concepts as the fundamental building block for effective human-agent teamwork, or posited the types of shared knowledge that promote mutual understanding between cooperating humans and agents. However many of the facets of human agent teamwork models, such as communication protocols for forming mutual intelligibility, performing team monitoring to assess progress, forming joint goals, addressing task interdependencies in hybrid teamwork, are still unexplored. This project is part of IBM's International Technology Alliance in Network and Information Sciences (ITA), a consortium of leading academic and industry partners performing research in network-centric systems.

Publications

G. Sukthankar and K. Sycara, "Efficient Plan Recognition for Dynamic Multi-agent Teams," in Proceedings of the Grace Hopper Conference, October 2007.

G. Sukthankar, K. Sycara, J.A. Giampapa, C. Burnett, and A. Preece, "Towards a Model of Agent-Assisted Team Search," in Proceedings of the Annual Conference of the International Technology Alliance in Network and Information Science, September 2007.

G. Sukthankar and K. Sycara, "Policy Recognition for Multi-Player Tactical Scenarios," in Proceedings of the Sixth International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), May 2007.

K. Sycara and G. Sukthankar, "Literature Review of Teamwork Models," Tech. Report CMU-RI-TR-06-50, Robotics Institute, Carnegie Mellon University, November 2006.

Personnel

Current Personnel:
Katia Sycara
Joseph A. Giampapa
Martin Kollingbaum

Past Personnel:
Gita Sukthankar
Christopher Burnett