Deploying a personalized time management agent

ABSTRACT

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.

References

1. D. Azuma. Glow AP1 version 1.0 reference. July 2000.
2. P. Berry, M. Gervasio, B. Peintner, T. Uribe, and N. Yorke-Smith. Multi-criteria evaluation in user-centric distributed scheduling agents. In Proc. of the AAA1 2006 Spring Symposium on Distributed Plan and Schedule Management, Mar. 2006.
3. P. Berry, M. Gervasio, T. E. Uribe, and N. Yorke-Smith. Mixed-initiative issues for a personalized time management assistant. In Proc. of ICAPS'05 Workshop on Mixed-Initiative Planning and Scheduling, pages 12--17, Monterey, CA, June 2005.
4. A. Cheyer and D. Martin. The Open Agent Architecture. J. Autonomous Agents and Multi-Agent Systems, 4(1):143--148, 2001.
5. A. Cheyer, J. Park, and R. Giuli. IRIS: Integrate. Relate. Infer. Share. In Proc. of Fourth Intl. Semantic Web Conference Workshop on the Semantic Desktop, Galway, Ireland, Nov. 2005.
6. A. H. W. Chun, D. W. M. Yeung, G. P. S. Lam, D. Lai, R. Keefe, J. Lam, and H. Chan. Scheduling engineering works for the MTR Corporation in Hong Kong. In Proc. of AAAI-05, 2005.
7. F. Dawson, D. Stenerson, and E. H. Durfee. RFC:2445. Internet Engineering Task Force, Network Working Group, 1998.
8. E. Ephrati, G. Zlotkin, and J. Rosenschein. A non-manipulable meeting scheduling system. In Proc. of the Thirteenth Intl. Distributed Artificial Intelligence Workshop, Seattle, WA, 1994.
9. A. Faulring and B. A. Myers. Enabling rich human-agent interaction for a calendar scheduling agent. In Proc. of CHI-05, 2005.
10. M. S. Franzin, F. Rossi, E. C. Freuder, and R. Wallace. Multi-agent constraint systems with preferences: Efficiency, solution quality, and privacy loss. Computational Intelligence, 20:264--286, May 2004.
11. M. T. Gervasio, M. D. Moffitt, M. E. Pollack, J. M. Taylor, and T. E. Uribe. Active preference learning for personalized calendar scheduling assistance. In Proc. of IUI'05, San Diego, CA, Jan. 2005.
12. N. R. Jennings and A. J. Jackson. Agent-based meeting scheduling: A design and implementation. IEE Electronics Letters Journal, 31(5):350--352, 1995.
13. T. Joachims. Making large-scale SVM learning practical. In B. Schlkopf, C. Burges, and A. Smola, editors, Advances in Kernel Methods---Support Vector Learning. MIT Press, 1999.
14. E. Junker. QuickXplain: Preferred explanations and relaxations for over-constrained problems. In Proc. of AAAI-04, 2004.
15. W. Mark and R. Perrault. CALO: Cognitive Assistant that Learns and Organizes. www.ai.sri.com/project/CALO, 2005.
16. P. J. Modi, W. Shen, M. Tambe, and M. Yokoo. ADOPT: Asynchronous distributed constraint optimization with quality guarantees. Artificial Intelligence, 161(1--2):149--180, 2005.
17. P. J. Modi, M. M. Veloso, S. F. Smith, and J. Oh. CMRadar: A personal assistant agent for calendar management. In Proc. of Agent-Oriented Information Systems (AOIS 2004), LNCS 3508, pages 169--181, Riga, Latvia, June 2004.
18. M. D. Moffitt, B. Peintner, and M. E. Pollack. Augmenting disjunctive temporal problems with finite-domain constraints. In Proc. of AAAI-05, pages 1187--1192, Pittsburgh, PA, July 2005.
19. D. Morley and K. Myers. The SPARK agent framework. In Proc. of AAMAS'04, pages 714--721, New York, NY, July 2004.
20. K. L. Myers and D. N. Morley. Human directability of agents. In Proc. of First Intl. Conf. on Knowledge Capture, Victoria, BC, 2001.
21. J. Oh and S. F. Smith. Learning calendar scheduling preferences in hierarchical organizations. In CP'04 Workshop on Preferences and Soft Constraints (Soft'04), Toronto, Canada, Sept. 2004.
22. L. Palen. Social, individual and technological issues for groupware calendar systems. In Proc. of CHI-99, pages 17--24, 1999.
23. R. Payne, R. Singh, and K. Sycara. Rcal: A case study on semantic web agents. In Proc. of AAMAS'02, pages 802--803, 2002.
24. C. Rich and C. Sidner. COLLAGEN: A collaboration manager for software interface agents. User Modeling and User-Adapted Interaction, 8(3/4):315--350, 1998.
25. S. Sandip and E. Durfee. A formal study of distributed meeting scheduling. J. Group Decision and Negotiation, 7:265--298, 1998.
26. H. M. Sheini, B. Peintner, K. A. Sakallah, and M. E. Pollack. On solving soft temporal constraints using SAT techniques. In Proc. of CP'05, pages 607--621, Sitges, Spain, Oct. 2005.
27. SICS. SICStus Prolog User Manual Version 3.12, Oct. 2005.
28. P. Viappiani, B. Faltings, V. S. Zuber, and P. Pu. Stimulating preference expression using suggestions. In AAAI 2005 Fall Symposium on Mixed-Initiative Problem-Solving Assistants, Arlington, VA, Nov. 2005.