Adjusting the Autonomy in Mixed-initiative Systems by Reasoning about Interaction

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.

[1]  Joe Marks,et al.  Human-Guided Simple Search , 2000, AAAI/IAAI.

[2]  Dan Ryan,et al.  Traded Control with Autonomous Robots as Mixed Initiative Interaction , 1997 .

[3]  Candace L. Sidner,et al.  COLLAGEN: A Collaboration Manager for Software Interface Agents , 1998, User Modeling and User-Adapted Interaction.

[4]  Eric Horvitz,et al.  Attention-Sensitive Alerting , 1999, UAI.

[5]  Shimei Pan,et al.  Empirically Evaluating an Adaptable Spoken Dialogue System , 1999, ArXiv.

[6]  Liliana Ardissono,et al.  Using dynamic user models in the recognition of the plans of the user , 2005, User Modeling and User-Adapted Interaction.

[7]  Marilyn A. Walker,et al.  Evaluating Response Strategies in a Web-Based Spoken Dialogue Agent , 1998, ACL.

[8]  Jennifer Chu-Carroll,et al.  An Evidential Model for Tracking Initiative in Collaborative Dialogue Interactions , 1998, User Modeling and User-Adapted Interaction.

[9]  Peter van Beek,et al.  FROM PLAN CRITIQUING TO CLARIFICATION DIALOGUE FOR COOPERATIVE RESPONSE GENERATION * , 1993, Comput. Intell..

[10]  Cécile Paris,et al.  The role of the user's domain knowledge in generation , 1991, Comput. Intell..

[11]  Barbara J. Grosz,et al.  Socially Conscious Decision-Making , 2003, Autonomous Agents and Multi-Agent Systems.

[12]  Eric Horvitz,et al.  Principles of mixed-initiative user interfaces , 1999, CHI '99.

[13]  Bowen Hui,et al.  What is Initiative? , 1998, User Modeling and User-Adapted Interaction.

[14]  Marilyn A. Walker,et al.  Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email , 1998, COLING-ACL.

[15]  Robin Cohen,et al.  System initiative influenced by underlying representations in mixed-initiative planning systems , 2000 .

[16]  Robin Cohen,et al.  A User Modeling Approach to Determining System Initiative in Mixed-Initiative AI Systems , 2001, User Modeling.

[17]  Sarit Kraus,et al.  Intention reconciliation by collaborative agents , 2000, Proceedings Fourth International Conference on MultiAgent Systems.

[18]  Martha W. Evens,et al.  Student Initiatives and Tutor Responses in a Medical Tutoring System , 1998 .

[19]  Jennifer Chu-Carroll,et al.  Tracking Initiative in Collaborative Dialogue Interactions , 1997, ACL.

[20]  Robin Cohen,et al.  User modeling in the design of interactive interface agents , 1999 .

[21]  Anthony Jameson,et al.  When policies are better than plans: decision-theoretic planning of recommendation sequences , 2001, IUI '01.