Probabilistic plan recognition for intelligent information agents: Towards proactive software assistant agents

Jean Oh; Felipe Meneguzzi; Katia Sycara

Probabilistic plan recognition for intelligent information agents: Towards proactive software assistant agents

Jean Oh^*, Felipe Meneguzzi, Katia Sycara

^*Corresponding author for this work

Carnegie Mellon University

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

10 Citations (Scopus)

Abstract

In this paper, we present a software assistant agent that can proactively manage information on behalf of cognitively overloaded users. We develop an agent architecture, known here as ANTicipatory Information and Planning Agent (ANTIPA), to provide the user with relevant information in a timely manner. In order both to recognize user plans unobtmsively and to reason about time constraints, ANTIPA integrates probabilistic plan recognition with constraint-based information gathering. This paper focuses on our probabilistic plan prediction algorithm inspired by a decision theory that human users make decisions based on long-term outcomes. A proof of concept user study shows a promising result.

Original language	English
Title of host publication	ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence
Pages	281-287
Number of pages	7
Volume	2
Publication status	Published - 2011
Externally published	Yes
Event	3rd International Conference on Agents and Artificial Intelligence, ICAART 2011 - Rome, Italy Duration: 28 Jan 2011 → 30 Jan 2011

Conference

Conference	3rd International Conference on Agents and Artificial Intelligence, ICAART 2011
Country/Territory	Italy
City	Rome
Period	28/01/11 → 30/01/11

Bibliographical note

3rd International Conference on Agents and Artificial Intelligence, ICAART 2011 28 January 2011 through 30 January 2011 Code 85505

Keywords

Agent architecture
Information agents
Proactive assistant agents
Probabilistic plan recognition

Cite this

Probabilistic plan recognition for intelligent information agents: Towards proactive software assistant agents. / Oh, Jean; Meneguzzi, Felipe; Sycara, Katia.
ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence. Vol. 2 2011. p. 281-287.

Research output: Chapter in Book/Report/Conference proceeding › Published conference contribution

Oh, J, Meneguzzi, F & Sycara, K 2011, Probabilistic plan recognition for intelligent information agents: Towards proactive software assistant agents. in ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence. vol. 2, pp. 281-287, 3rd International Conference on Agents and Artificial Intelligence, ICAART 2011, Rome, Italy, 28/01/11.

@inproceedings{4c43176799084747a1cea81358779af3,

title = "Probabilistic plan recognition for intelligent information agents: Towards proactive software assistant agents",

abstract = "In this paper, we present a software assistant agent that can proactively manage information on behalf of cognitively overloaded users. We develop an agent architecture, known here as ANTicipatory Information and Planning Agent (ANTIPA), to provide the user with relevant information in a timely manner. In order both to recognize user plans unobtmsively and to reason about time constraints, ANTIPA integrates probabilistic plan recognition with constraint-based information gathering. This paper focuses on our probabilistic plan prediction algorithm inspired by a decision theory that human users make decisions based on long-term outcomes. A proof of concept user study shows a promising result.",

keywords = "Agent architecture, Information agents, Proactive assistant agents, Probabilistic plan recognition",

author = "Jean Oh and Felipe Meneguzzi and Katia Sycara",

note = "3rd International Conference on Agents and Artificial Intelligence, ICAART 2011 28 January 2011 through 30 January 2011 Code 85505; 3rd International Conference on Agents and Artificial Intelligence, ICAART 2011 ; Conference date: 28-01-2011 Through 30-01-2011",

year = "2011",

language = "English",

isbn = "9789898425416",

volume = "2",

pages = "281--287",

booktitle = "ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence",

}

TY - GEN

T1 - Probabilistic plan recognition for intelligent information agents

T2 - 3rd International Conference on Agents and Artificial Intelligence, ICAART 2011

AU - Oh, Jean

AU - Meneguzzi, Felipe

AU - Sycara, Katia

N1 - 3rd International Conference on Agents and Artificial Intelligence, ICAART 2011 28 January 2011 through 30 January 2011 Code 85505

PY - 2011

Y1 - 2011

N2 - In this paper, we present a software assistant agent that can proactively manage information on behalf of cognitively overloaded users. We develop an agent architecture, known here as ANTicipatory Information and Planning Agent (ANTIPA), to provide the user with relevant information in a timely manner. In order both to recognize user plans unobtmsively and to reason about time constraints, ANTIPA integrates probabilistic plan recognition with constraint-based information gathering. This paper focuses on our probabilistic plan prediction algorithm inspired by a decision theory that human users make decisions based on long-term outcomes. A proof of concept user study shows a promising result.

AB - In this paper, we present a software assistant agent that can proactively manage information on behalf of cognitively overloaded users. We develop an agent architecture, known here as ANTicipatory Information and Planning Agent (ANTIPA), to provide the user with relevant information in a timely manner. In order both to recognize user plans unobtmsively and to reason about time constraints, ANTIPA integrates probabilistic plan recognition with constraint-based information gathering. This paper focuses on our probabilistic plan prediction algorithm inspired by a decision theory that human users make decisions based on long-term outcomes. A proof of concept user study shows a promising result.

KW - Agent architecture

KW - Information agents

KW - Proactive assistant agents

KW - Probabilistic plan recognition

UR - http://www.scopus.com/inward/record.url?scp=79960141764&partnerID=8YFLogxK

M3 - Published conference contribution

AN - SCOPUS:79960141764

SN - 9789898425416

VL - 2

SP - 281

EP - 287

BT - ICAART 2011 - Proceedings of the 3rd International Conference on Agents and Artificial Intelligence

Y2 - 28 January 2011 through 30 January 2011

ER -

Probabilistic plan recognition for intelligent information agents: Towards proactive software assistant agents

Abstract

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this