Deploying a personalized time management agent

We report on our ongoing practical experience in designing, implementing, and deploying PTIME, a personalized agent for time management and meeting scheduling in an open, multi-agent environment. In developing PTIME as part of a larger assistive agent called CALO, we have faced numerous challenges, including usability, multi-agent coordination, scalable constraint reasoning, robust execution, and unobtrusive learning. Our research advances basic solutions to the fundamental problems; however, integrating PTIME into a deployed system has raised other important issues for the successful adoption of new technology. As a personal assistant, PTIME must integrate easily into a user's real environment, support her normal workflow, respect her authority and privacy, provide natural user interfaces, and handle the issues that arise with deploying such a system in an open environment.

[1]  Makoto Yokoo,et al.  Adopt: asynchronous distributed constraint optimization with quality guarantees , 2005, Artif. Intell..

[2]  Stephen F. Smith,et al.  CMRadar: A Personal Assistant Agent for Calendar Management , 2004, AAAI.

[3]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[4]  Karen L. Myers,et al.  The SPARK agent framework , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[5]  Tomás E. Uribe,et al.  Mixed-Initiative Issues for a Personalized Time Management Assistant , 2005 .

[6]  Tomás E. Uribe,et al.  Active preference learning for personalized calendar scheduling assistance , 2005, IUI.

[7]  Paolo Viappiani,et al.  Stimulating preference expression using suggestions , 2005, IJCAI 2005.

[8]  Leysia Palen,et al.  Social, individual and technological issues for groupware calendar systems , 1999, CHI '99.

[9]  Tomás E. Uribe,et al.  Multi-Criteria Evaluation in User-Centric Distributed Scheduling Agents , 2006, AAAI Spring Symposium: Distributed Plan and Schedule Management.

[10]  Jeffrey S. Rosenschein,et al.  A Non-manipulable Meeting Scheduling System , 1994 .

[11]  Karen L. Myers,et al.  Human directability of agents , 2001, K-CAP '01.

[12]  Richard Keefe,et al.  Scheduling Engineering Works for the MTR Corporation in Hong Kong , 2005, AAAI.

[13]  Ulrich Junker,et al.  QUICKXPLAIN: Preferred Explanations and Relaxations for Over-Constrained Problems , 2004, AAAI.

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

[15]  Ray Perrault,et al.  CALO: Cognitive Assistant that Learns and Organizes , 2005 .

[16]  Martha E. Pollack,et al.  On Solving Soft Temporal Constraints Using SAT Techniques , 2005, CP.

[17]  Rahul Singh,et al.  RCal: a case study on semantic web agents , 2002, AAMAS '02.

[18]  Francesca Rossi,et al.  Multi‐Agent Constraint Systems with Preferences: Efficiency, Solution Quality, and Privacy Loss , 2004, Comput. Intell..

[19]  Adam Cheyer,et al.  The Open Agent Architecture , 1997, Autonomous Agents and Multi-Agent Systems.

[20]  Nicholas R. Jennings,et al.  Agent-based meeting scheduling: a design and implementation , 1995 .

[21]  Edmund H. Durfee,et al.  A Formal Study of Distributed Meeting Scheduling , 1998 .

[22]  Alan Macfarlane,et al.  Social , 1994, Schizophrenia Research.

[23]  Stephen F. Smith,et al.  Learning Calendar Scheduling Preferences in Hierarchical Organizations , 2004 .

[24]  Brad A. Myers,et al.  Enabling rich human-agent interaction for a calendar scheduling agent , 2005, CHI EA '05.

[25]  Jack Park,et al.  IRIS: Integrate. Relate. Infer. Share , 2005, Semantic Desktop Workshop.

[26]  Martha E. Pollack,et al.  Augmenting Disjunctive Temporal Problems with Finite-Domain Constraints , 2005, AAAI.