Probabilistic Plan Recognition for Proactive Assistant Agents - Robotics Institute Carnegie Mellon University

Probabilistic Plan Recognition for Proactive Assistant Agents

Jean Hyaejin Oh, Felipe Meneguzzi, and Katia Sycara
Book Section/Chapter, Plan, Activity, and Intent Recognition: Theory and Practice, pp. 275 - 288, February, 2014

Abstract

Human users dealing with multiple objectives in a complex environment (e.g., military planners or emergency response operators) are subject to a high level of cognitive load. When this load is excessive, it can severely impair the quality of the plans that are created. Plan recognition, which refers to the task of identifying the user’s high-level goals (or intentions) by observing the user’s current activities, is a crucial capability for intelligent assistant systems that are intended to be incorporated into the user’s computing environment. This chapter discusses how we use plan recognition to develop a software agent that can proactively assist human users in time-stressed environments.

Notes
http://store.elsevier.com/Plan-Activity-and-Intent-Recognition/isbn-9780123985323/

BibTeX

@incollection{Oh-2014-7834,
author = {Jean Hyaejin Oh and Felipe Meneguzzi and Katia Sycara},
title = {Probabilistic Plan Recognition for Proactive Assistant Agents},
booktitle = {Plan, Activity, and Intent Recognition: Theory and Practice},
publisher = {Elsevier},
chapter = {11},
editor = {G. Sukthankar, R. P. Goldman, C. Geib, D. V. Pynadath, H. H. Bui},
year = {2014},
month = {February},
pages = {275 - 288},
keywords = {plan recognition, probabilistic approach, assistant agents, decision theoretic approach},
}