An approach to mixed-initiative management of heterogeneous software agent teams

The rapid growth in research and development of agent-based software systems has led to concerns about how human users will control the activities of teams of agents that must actively collaborate. We believe that practical multi-agent systems developed will often be comprised of small teams of heterogeneous agents, under direct supervision by users acting as "team leaders". We are now developing an environment for investigating approaches to controlling small to medium-sized groups of agents as coordinated teams. This environment will be used to explore mixed-initiative approaches to planning for the activities of agent teams and managing them during execution. Our approach arises out of a long-standing interest in mixed-initiative planning systems. In this paper, we discuss our approach to mixed-initiative agent team management, some representational issues involved in identifying compatible agent team members and the capabilities needed to monitor team execution.

[1]  Thomas W. Malone,et al.  MODELING COORDINATION IN ORGANIZATIONS AND MARKETS**Accepted by Richard M. Burton; received August 27, 1986. This paper has been with the author 2 months for 1 revision. , 1988 .

[2]  Jay M. Tenenbaum,et al.  An intelligent agent framework for enterprise integration , 1991, IEEE Trans. Syst. Man Cybern..

[3]  Alice M. Mulvehill,et al.  Rationale-Supported Mixed-Initiative Case-Based Planning , 1997, AAAI/IAAI.

[4]  Drew McDermott,et al.  Issues in the Development of Human-Computer Mixed Initiative Planning , 1994 .

[5]  Carl Hewitt,et al.  DAI betwixt and between: from 'intelligent agents' to open systems science , 1991, IEEE Trans. Syst. Man Cybern..

[6]  Daniel S. Weld,et al.  Intelligent Agents on the Internet: Fact, Fiction, and Forecast , 1995, IEEE Expert.

[7]  Nicholas R. Jennings,et al.  Agent Theories, Architectures, and Languages: A Survey , 1995, ECAI Workshop on Agent Theories, Architectures, and Languages.

[8]  Kristian J. Hammond,et al.  CHEF: A Model of Case-Based Planning , 1986, AAAI.

[9]  Alice M. Mulvehill.  Reusing Force Deployment Plans , 1995 .

[10]  Donald A. Norman.  How People Might Interact with Agents , 1997 .

[11]  G. Abrett.  Planning by autonomous agents with many concurrent goals in an elaborate simulated world , 1991, [1991] Proceedings. The Second Annual Conference on AI, Simulation and Planning in High Autonomy Systems.

[12]  Michael Wooldridge.  What agents aren't: a discussion paper , 1996 .

[13]  E. Salas,et al.  Toward an understanding of team performance and training. , 1992 .

[14]  Craig A. Knoblock,et al.  Retrieving and Integrating Data from Multiple Information Sources , 1993, Int. J. Cooperative Inf. Syst..

[15]  Michael Wooldridge,et al.  Understanding the Emergence of Conventions in Multi-Agent Systems , 1995, ICMAS.

[16]  E. Salas,et al.  Team decision making in complex environments. , 1993 .

[17]  Gul A. Agha,et al.  ACTORS - a model of concurrent computation in distributed systems , 1985, MIT Press series in artificial intelligence.

[18]  Manuela Veloso.  Learning by analogical reasoning in general problem-solving , 1992 .

[19]  Marie desJardins,et al.  The Common Prototyping Environment: A Framework for Software Technology Integration, Evaluation, and Transition , 1995, IEEE Expert.

[20]  Craig A. Knoblock,et al.  New Directions: Agents for Information Gathering , 1997, IEEE Expert.

[21]  Stephen Deutsch,et al.  The Operator-Model Architecture and its Psychological Framework , 1995 .

[22]  David Leake,et al.  Case-Based Reasoning: Experiences, Lessons and Future Directions , 1996 .

[23]  Ben Shneiderman,et al.  Direct manipulation versus agents: paths to predictable, controllable, and comprehensible interfaces , 1997 .

[24]  Craig A. Knoblock.  1 Agents for Information Gathering , 1997 .