Adjustable autonomy in real-world multi-agent environments

ABSTRACT

Through {\em adjustable autonomy} (AA), an agent can dynamically vary the degree to which it acts autonomously, allowing it to exploit human abilities to improve its performance, but without becoming overly dependent and intrusive in its human interaction. AA research is critical for successful deployment of multi-agent systems in support of important human activities. While most previous AA work has focused on individual agent-human interactions, this paper focuses on {\em teams} of agents operating in real-world human organizations. The need for agent teamwork and coordination in such environments introduces novel AA challenges. First, agents must be more judicious in asking for human intervention, because, although human input can prevent erroneous actions that have high team costs, one agent's inaction while waiting for a human response can lead to potential miscoordination with the other agents in the team. Second, despite appropriate local decisions by individual agents, the overall team of agents can potentially make global decisions that are unacceptable to the human team. Third, the diversity in real-world human organizations requires that agents gradually learn individualized models of the human members, while still making reasonable decisions even before sufficient data are available. We address these challenges using a multi-agent AA framework based on an adaptive model of users (and teams) that reasons about the uncertainty, costs, and constraints of decisions at {\em all} levels of the team hierarchy, from the individual users to the overall human organization. We have implemented this framework through Markov decision processes, which are well suited to reason about the costs and uncertainty of individual and team actions. Our approach to AA has proven essential to the success of our deployed multi-agent Electric Elves system that assists our research group in rescheduling meetings, choosing presenters, tracking people's locations, and ordering meals.

REFERENCES

• 1: John Collins , Corey Bilot , Maria Gini, Mixed-initiative decision support in agent-based automated contracting, Proceedings of the fourth international conference on Autonomous agents, p.247-254, June 03-07, 2000, Barcelona, Spain [doi>10.1145/336595.337464]
• 2: G. A. Dorais, R. P. Bonasso, D. Kortenkamp, B. Pell, and D. Schreckenghost. Adjustable autonomy for human-centered autonomous systems on mars. In Proc. of the First Int. Conf. of the Mars Society, 1998.
• 3: G. Ferguson, J. Allen, and B. Miller. TRAINS-95 : towards a mixed initiative planning assistant. In Proc. of the Third Conference on Artificial Intelligence Planning Systems, pages 70-77, May 1996.
• 4: Call for Papers. AAAI spring symposium on adjustable autonomy. www.aaai.org, 1999.
• 5: J. P. Gunderson and W. N. Martin. Effects of uncertainty on variable autonomy in maintenence robots. In Proc. of Agents'99, Workshop on Autonomy Control Software, 1999.
• 6: T. Hartrum and S. Deloach. Design issues for mixed-initiative agent systems. In Proc. of the AAAI workshop on mixed-initiative intelligence, 1999.
• 7: E. Horvitz, A. Jacobs, and D. Hovel. Attention-sensitive alerting. In Proc. of UAI'99, 1999.
• 8: V. Lesser, M. Atighetchi, B. Benyo, et al. A multi-agent system for intelligent environment control. In Proc. of Agents'99, 1999.
• 9: Tom M. Mitchell , Rich Caruana , Dayne Freitag , John McDermott , David Zabowski, Experience with a learning personal assistant, Communications of the ACM, v.37 n.7, p.80-91, July 1994 [doi>10.1145/176789.176798]
• 10: M. L. Puterman. Markov Decision Processes. John Wiley & Sons, 1994.
• 11: D. V. Pynadath, M. Tambe, H. Chalupsky, Y. Arens, et al. Electric elves: Immersing an agent organization in a human organization. In Proc. of the AAAI Fall Symposium on Socially Intelligent Agents, 2000.
• 12: Stuart J. Russell , Peter Norvig, Artificial intelligence: a modern approach, Prentice-Hall, Inc., Upper Saddle River, NJ, 1995
• 13: J. Ross Quinlan, C4.5: programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993
• 14: M. Tambe. Towards flexible teamwork. Journal of Artificial Intelligence Research, 7:83-124, 1997.
• 15: Adaptive Agent Integration Architectures for Heterogeneous Team Members, Proceedings of the Fourth International Conference on MultiAgent Systems (ICMAS-2000), p.301, July 10-12, 2000

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
        I.2.11 Distributed Artificial Intelligence
            Subjects: Multiagent systems

Additional Classification:
  H. Information Systems
  H.4 INFORMATION SYSTEMS APPLICATIONS
      H.4.2 Types of Systems
          Subjects: Decision support (e.g., MIS)

General Terms:
Design, Management, Measurement, Performance, Theory