Abstract
In this chapter, we present one approach to designing mixed-initiative systems, focusing on clarifying how a system might reason about taking the initiative to interact with a user. The procedure for reasoning about interaction weighs the perceived benefits of interaction against the perceived costs, in a quantitative evaluation. It is intended to be applied by a system that has been engaged by a user to carry out a problem solving task. This reasoning process is one where an agent decides to adjust its own autonomy, delegating authority to another party. We discuss in more detail how this work contrasts with other research in the field of adjustable autonomy, including work that projects the benefit of a future path and work that characterizes how to reason about limiting one’s own autonomy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Reference
D. Anderson, E. Anderson, N. Lesh, J. Marks, B. Mirtich, D. Ratajczak and K. Ryall (2000). Human-Guided Simple Search Proceedings of AAAI-2000 AAAI Press, 209–216
L. Ardissono and D. Sestero (1996). Using Dynamic User Models in the Recognition of the Plans of the User. User Modeling and User Adapated Interaction 5: 2,157–190.
K.S. Barber (2002). In this volume.
G. Boella and L. Lesmo (2002). In this volume.
T. Bohnenberger and A. Jameson (2001). When Policies are Better Than Plans: Decision-Theoretic Planning of Recommendation Sequences. IUI2001: International Conference on Intelligent User Interfaces, 21–24.
S. Brainov and H. Hexmoor (2002). In this volume.
S. Carberry (1997). Discourse Initiative: Its Role in Intelligent Tutoring Systems. Papers from the 1997 AAAI Symposium on Computational Models for Mixed Initiative Interaction, AAAI Press, 10–15.
J. Chu-Carroll and M.K. Brown (1998). An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions. User Modeling and User-Adapted Interaction 8: 3–4, 215-253.
J. Chu-Carroll and M. Brown (1999). Tracking Initiative in Collaborative Dialogue Interactions. Proceedings of ACL 99, 262–269
R. Cohen, C. Allaby, C. Cumbaa, M. Fitzgerald, K. Ho, B. Hui, C. Latulipe, F. Lu, N. Moussa, D. Pooley, A. Qian and S. Siddiqi (1998). What is Initiative? User Modeling and User-Adapted Interaction 8: 3–4, 171-214.
R. Falcone and C. Castelfranchi (2002). In this volume.
M. Fleming and R. Cohen (1999). User Modeling in the Design of Interactive Interface Agents. Proceedings of the Seventh International Conference on User Modeling, Banff, Alberta, Canada, 67–76.
M. Fleming and R. Cohen (2000). System initiative influenced by underlying representations in mixed-initiative planning systems. In Papers from the 2000 AAAI Workshop on Representational Issues for Real-World Planning Systems, pages 18–21.
M. Fleming and R. Cohen (2001). A User Modeling Approach to Determining System Initiative in Mixed-Initiative AI Systems. In Proceedings of the Eighth International Conference on User Modeling, pages 54–63.
A. Glass and B. Grosz (2000). Socially Conscious Decision-Making. Proceedings of Agents 2000, 217–224.
E. Horvitz (1999). Principles of Mixed-Initiative User Interfaces. Proceedings of CHI ′99, ACM SIGCHI Conference on Human Factors in Computing Systems, Pittsburgh, PA, ACM Press, 159–166.
E. Horvitz, A. Jacobs and D. Hovel (1999). Attention-Sensitive Alerting. In Proceedings of UAI ′99, Conference on Uncertainty and Artificial Intelligence, pages 305–313.
D. Kortenkamp, R.P. Bonasso, D. Ryan and D. Schreckenghost (1997). Traded Control with Autonomous Robots as Mixed-Initiative Interaction. Papers from the 1997 AAAI Symposium on Computational Models for Mixed Initiative Interaction, AAAI Press, 89–94.
D. Litman and S. Pan (1999). Empirically Evaluating an Adaptable Spoken Dialogue System. Proceedings of UM′99, 55–64.
D. Litman, S. Pan and M. Walker (1998). Evaluating Response Strategies in a Web-Based Spoken Dialogue Agent. Proceedings of ACL-COLING 98, 780–786.
K. Myers and D. Morley (2002). In this volume.
C. Paris (1991). The role of the user’s domain knowledge in generation. Computational Intelligence 7: 2, 71–93.
D. Pynadeth and M. Tambe (2002). In this volume.
C. Rich and C.L. Sidner (1998). COLLAGEN: A Collaboration Manager for Software Interface Agents. User Modeling and User-Adapted Interaction 8:3–4, 315–350.
F. Shah and M. Evens (1997). Student Initiatives and Tutor Responses in a Medical Tutoring System. In S. Haller and S. McRoy (eds.), Papers from the 1997 AAAI Symposium on Computational Models for Mixed Initiative Interaction, Stanford, CA, AAAI Press, 138–144.
D. Sullivan, B. Grosz and S. Kraus (2000). Intention Reconciliation by Collaborative Agents. Proceedings of ICMAS-2000, IEEE Computer Society Press, 293–300.
P. van Beek, R. Cohen and K. Schmidt (1993). From Plan Critiquing to Clarification Dialogue for Cooperative Response Generation. Computational Intelligence 9: 2, 132–154.
M. Walker, J. Fromer and S. Narayanan (1998). Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email. Proceedings of the 17th International Conference on Computational Linguistics, 1345–1351.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer Science+Business Media New York
About this chapter
Cite this chapter
Cohen, R., Fleming, M. (2003). Adjusting the Autonomy in Mixed-initiative Systems by Reasoning about Interaction. In: Hexmoor, H., Castelfranchi, C., Falcone, R. (eds) Agent Autonomy. Multiagent Systems, Artificial Societies, and Simulated Organizations, vol 7. Springer, Boston, MA. https://doi.org/10.1007/978-1-4419-9198-0_7
Download citation
DOI: https://doi.org/10.1007/978-1-4419-9198-0_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-4833-7
Online ISBN: 978-1-4419-9198-0
eBook Packages: Springer Book Archive