Publication Details

Mixed-Initiative Issues for a Personalized Time Management Assistant

by Berry, P. and Gervasio, M. and Uribe, T. and Yorke-Smith, N.

in Proceedings of ICAPS’05 Workshop on Mixed-Initiative Planning and Scheduling pp. 12-17,

Abstract

This paper explores the mixed-initiative issues arising in the Personalized Time Manager (PTIME) system. PTIME is a persistent assistant that builds on our previous work on a personalized calendar agent (PCalM) (Berry et al. 2004). In order to persist and be useful, an intelligent agent that includes collaborative human/agent decision processes must learn and adapt to the user’s changing needs. PTIME is intended to support a richer dialogue between the user and the system, which should be useful to both. If the system can reliably lean the user’s preferences and practices, trust between user and assistant will be established, decreasing the system’s reliance on mundane user interaction over time. The enabling technologies include soft constraint satisfaction, multicriteria optimization, a rich process framework, learning, and advice.

Electronic Copies

Adobe PDF

BibTeX

EndNote

Associated Projects

Cognitive Assistant that Learns and Organizes As part of DARPA’s Personalized Assistant that Learns (PAL) program, SRI and team members are working on developing a next-generation "Cognitive Agent that Learns and Organizes" (CALO).

AIC Personnel

	Name	Title	E-mail
	Berry, Pauline M	Alumnus
	Gervasio, Melinda	Senior Computer Scientist
	Uribe, Tomas E	Computer Scientist
	Yorke-Smith, Neil	Computer Scientist