Agent-oriented Incremental Team and Activity Recognition

Daniele Masato; Timothy J Norman; Wamberto Weber Vasconcelos; Katia Sycara

doi:10.5591/978-1-57735-516-8/IJCAI11-237

Agent-oriented Incremental Team and Activity Recognition

Daniele Masato, Timothy J Norman, Wamberto Weber Vasconcelos, Katia Sycara

Carnegie Mellon University

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

9 Citations (Scopus)

Abstract

Monitoring team activity is beneficial when human teams cooperate in the enactment of a joint plan. Monitoring allows teams to maintain awareness of each other's progress within the plan and it enables anticipation of information needs. Humans find this difficult, particularly in time-stressed and uncertain environments. In this paper we introduce a probabilistic model, based on Conditional Random Fields, to automatically recognise the composition of teams and the team activities in relation to a plan. The team composition and activities are recognised incrementally by interpreting a stream of spatio-temporal observations.

Original language	English
Title of host publication	Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence
Editors	Toby Walsh
Place of Publication	Menlo Park, California
Publisher	AAAI Press
Pages	1402-1407
Number of pages	6
ISBN (Electronic)	978-1-57735-516-8
ISBN (Print)	978-1-57735-512-0, 978-1-57735-514-4
DOIs	https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-237
Publication status	Published - 2011

Access to Document

10.5591/978-1-57735-516-8/IJCAI11-237

http://ijcai.org/papers11/contents.php

Cite this

Agent-oriented Incremental Team and Activity Recognition. / Masato, Daniele; Norman, Timothy J; Vasconcelos, Wamberto Weber et al.
Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence. ed. / Toby Walsh. Menlo Park, California: AAAI Press, 2011. p. 1402-1407.

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

@inproceedings{9b1d2e9e5b624b16a5e5df1ee76a9be4,

title = "Agent-oriented Incremental Team and Activity Recognition",

abstract = "Monitoring team activity is beneficial when human teams cooperate in the enactment of a joint plan. Monitoring allows teams to maintain awareness of each other's progress within the plan and it enables anticipation of information needs. Humans find this difficult, particularly in time-stressed and uncertain environments. In this paper we introduce a probabilistic model, based on Conditional Random Fields, to automatically recognise the composition of teams and the team activities in relation to a plan. The team composition and activities are recognised incrementally by interpreting a stream of spatio-temporal observations.",

author = "Daniele Masato and Norman, {Timothy J} and Vasconcelos, {Wamberto Weber} and Katia Sycara",

year = "2011",

doi = "10.5591/978-1-57735-516-8/IJCAI11-237",

language = "English",

isbn = "978-1-57735-512-0",

pages = "1402--1407",

editor = "Toby Walsh",

booktitle = "Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence",

publisher = "AAAI Press",

}

TY - GEN

T1 - Agent-oriented Incremental Team and Activity Recognition

AU - Masato, Daniele

AU - Norman, Timothy J

AU - Vasconcelos, Wamberto Weber

AU - Sycara, Katia

PY - 2011

Y1 - 2011

N2 - Monitoring team activity is beneficial when human teams cooperate in the enactment of a joint plan. Monitoring allows teams to maintain awareness of each other's progress within the plan and it enables anticipation of information needs. Humans find this difficult, particularly in time-stressed and uncertain environments. In this paper we introduce a probabilistic model, based on Conditional Random Fields, to automatically recognise the composition of teams and the team activities in relation to a plan. The team composition and activities are recognised incrementally by interpreting a stream of spatio-temporal observations.

AB - Monitoring team activity is beneficial when human teams cooperate in the enactment of a joint plan. Monitoring allows teams to maintain awareness of each other's progress within the plan and it enables anticipation of information needs. Humans find this difficult, particularly in time-stressed and uncertain environments. In this paper we introduce a probabilistic model, based on Conditional Random Fields, to automatically recognise the composition of teams and the team activities in relation to a plan. The team composition and activities are recognised incrementally by interpreting a stream of spatio-temporal observations.

U2 - 10.5591/978-1-57735-516-8/IJCAI11-237

DO - 10.5591/978-1-57735-516-8/IJCAI11-237

M3 - Published conference contribution

SN - 978-1-57735-512-0

SN - 978-1-57735-514-4

SP - 1402

EP - 1407

BT - Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence

A2 - Walsh, Toby

PB - AAAI Press

CY - Menlo Park, California

ER -

Agent-oriented Incremental Team and Activity Recognition

Abstract

Access to Document

Fingerprint

Cite this