Abstract
We are interested in developing models of and support for mixed-initiative human control of software agent teams, especially in the larger context of dynamic, real world organizations. In this paper, we describe a model for the establishment of cooperative information sharing among agents on teams formed dynamically for particular purposes within such organizations. We argue that effective information sharing in the presence of such teams requires the active dissemination of descriptions of current and future information needs to both local teammates and to the larger organization. Only by this mechanism can one avoid having to make explicit at design time who will provide each bit of the information. We consider how information sharing within the organization can be promoted not only for the immediate goals shared by a tightly coordinated team, but some of the likely information needs of the larger organization going forward. We illustrate the model by describing its application to a large-scale agent-based simulation of the US Military's disaster relief response to the devastation caused in Central America by Hurricane Mitch in 1998. The demonstration was developed in conjunction with a large group of researchers representing eight different institutions.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
D.A. Norman, “How people might interact with agents,” in Software Agents, edited by J. Bradshaw, MIT Press: Cambridge, MA, 1997, pp. 49-55.
M.H. Burstein, G. Ferguson, and J. Allen, “Integrating agentbased mixed-initiative control with an existing multi-agent planning system,” in Proc. Int. Conf. On MultiAgent Systems, 2000.
3. M. Burstein and D. McDermott, “Issues in the development of human-computer mixed-initiative planning systems,” in Cognitive Technology, edited by B. Gorayska and J.L. Mey, Elsever Science, 1996, pp. 285-303.
M.H. Burstein, A.M. Mulvehill, and S. Deutsch, “An approach to mixed-initiative management of heterogeneous software agent teams,” in Proc. 32nd Hawaii Int. Conf. on System Sciences, 1998.
T. Winograd and F. Flores, Understanding Computers and Cognition: A New Foundation for Design, Addison-Wesley: Reading, MA, 1987.
K.L. Myers and P.M. Berry, “At the boundary of workflow and AI,” in Proc. AAAI 1999 Workshop on Agent-Based Systems in The Business Context, 1999.
R.J. Firby, “Task networks for controlling continuous processes,” in Proc. Int. Conf. AI Plannng Systems, Meno Park, CA, 1994.
M. Tambe, “Towards flexible teamwork,” J. Artif. Intell. Research, vol. 7, pp. 83-124, 1997.
B.J. Grosz and S. Kraus, ”Collaborative plans for complex group action,” Artif. Intell., vol. 86, pp. 269-357, 1996.
B.J. Grosz and S. Kraus, “The evolution of SharedPlans,” in Foundations and Theories of Rational Agency, edited by M. Wooldridge and A. Rao, 1999, pp. 227-262.
M. Burstein and T. Emerson, “Development of a constraintbased airlift scheduler by program synthesis from formal specifications,” in Proceedings of the 1999 Conf. on Automated Software Engineering, Orlando, FL, 1999.
A. Mulvehill and J. Caroli, “JADE: A tool for rapid crisis action planning,” in Proc. of the 1999 Command and Control Research and Technology Symposium, US Naval War College, Newport, RI, 1999.
S.E. Deutsch, “Interdisciplinary foundations for multiple-task human performance modeling in OMAR,” in Proc. Cognitive Science Society, Madison, WI, 1998.
K.L. Myers, “User's guide for the procedural reasoning system,” Artif. Intell. Center, SRI International: Menlo Park, CA, 1993.
GITI/ISX Grid Vision Team, “The CoABS Grid: Technical Vision,” http://coabs.gobalinfotek.com, 2000.
K. Arnold, B. O'Sullivan, R.W. Schiefler, J. Waldo, and A. Wollrath, The Jini Specification. The Jini Technology Series, Addison-Wesley: Reading, MA, 1999.
M. Tambe and W. Zhang, “Towards flexible teamwork in persistent teams: Extended report,” Autonomous Agents and Multiagent Systems, vol. 3, pp. 159-183, 2000.
P.R. Cohen and H.J. Levesque, ”Teamwork,” Nous 25(4), Special Issue on Cognitive Science and Artif. Intell., pp. 487-512, 1991.
P.R. Cohen, H.R. Levesque, and I. Smith, “On team formation,” in Contemporary Action Theory, edited by J. Hintikka and R. Tuomela, Synthese, 1997
J.M. Bradshaw, S. Dutfield, P. Benoit, and J.D.Woolley, “KAoS: Toward an industrial-strength open agent architecture,” in Software Agents, edited by J. Bradshaw, Cambridge,MA: MIT Press, 1997, pp. 375-418.
G. Ferguson and J. Allen, “TRIPS: An integrated intelligent problem-solving assistant,” in Proc. National Conf. Artif. Intell., Madison, WI, 1998, pp. 567-573.
K.L. Myers, “Advisable planning systems,” in Advanced Planning Technology, edited by A. Tate, AAAI Press: Menlo Park, CA 1996.
K. Decker, K. Sycara, A. Pannu, and M.Williamson, “Designing behaviors for information agents,” in Proc. of the First International Conference on Autonomous Agents, Feb. 1997.
A. Cheyer and D. Martin, “The open agent architecture” JAMS, vol. 4, no. 1-2, pp. 143-148, 2001.
M. Klein and C. Dellarocas, “Exception handling in agent systems,” in Proc. Third Int. Conf. on Autonomous Agents, Seattle, WA, May, 1999.
M. Klein and C. Dellarocas, “A knowledge-based approach to handling exceptions in workflow systems,” J. Computer-Supported CollaborativeWork. Special Issue on AdaptiveWork-flow Systems, vol. 9, 2000.
L. Birnbaum, G. Collins, M. Freed, and B. Krulwich, “Mode-lbased diagnosis of planning failures,” in Proc. Eighth National Conf. on Artif. Intell., 1990.
Rights and permissions
About this article
Cite this article
Burstein, M.H., Diller, D.E. A Framework for Dynamic Information Flow in Mixed-Initiative Human/Agent Organizations. Applied Intelligence 20, 283–298 (2004). https://doi.org/10.1023/B:APIN.0000021419.19822.a2
Issue Date:
DOI: https://doi.org/10.1023/B:APIN.0000021419.19822.a2