Conflict Negotiation Among Personal Calendar Agents
by Berry, P. M. and Albright, C. and Bowring, E. and Conley, K. and Nitz, K. and Pearce, J. P. and Peintner, B. and Saadati, S. and Tambe, M. and Uribe, T. and Yorke-Smith, N.
in Proceedings of AAMAS06 Demonstration Track pp. 15641571,Address: Hakodate, Japan
This paper reports on our ongoing practical experience 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 efforts provide 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 users 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.
As part of DARPAs Personalized Assistant that Learns (PAL) program, SRI and team members are working on developing a next-generation "Cognitive Agent that Learns and Organizes" (CALO).
|Berry, Pauline M||Alumnus|
|Conley, Kenneth W||Alumnus|
|Nitz, Ken||SR. Software Engineer|
|Peintner, Bart||Sr. Computer Scientist|
|Saadati, Shahin||Software Engineer|
|Uribe, Tomas E||Computer Scientist|
|Yorke-Smith, Neil||Computer Scientist|