Agent Support for Policy-driven Mission Planning Under Constraints

Murat Sensoy, Daniele Masato, Timothy J Norman, Katia Sycara, Martin Kollingbaum, Jean Oh, Christopher Burnett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Forming ad-hoc coalitions between military forces and humanitarian organizations is crucial in mission-critical scenarios. Very often coalition parties need to operate according to planning constraints and regulations, or policies. Therefore, they find themselves not only in need to consider their own goals, but also to support coalition partners to the extent allowed by such regulations. In time-stressed conditions, this is a challenging and cognition-intensive task. In this paper, we present intelligent agents that support human planners and ease their cognitive burden by detecting and giving advice about the violation of policies and constraints. Through a series of experiments conducted with human subjects, we compare and contrast the agents' performance on a number of metrics in three conditions: agent support, transparent policy enforcement, and neither support nor enforcement.
Original languageEnglish
Title of host publicationProceedings of the First Proactive Assistant Agents Symposium
PublisherAAAI Press
Pages44-50
Number of pages7
Publication statusPublished - 2010

Publication series

NameFall Symposium Series
PublisherAAAI

Fingerprint

Intelligent agents
Planning
Experiments

Keywords

  • Multiagent Systems
  • Semantic Web

Cite this

Sensoy, M., Masato, D., Norman, T. J., Sycara, K., Kollingbaum, M., Oh, J., & Burnett, C. (2010). Agent Support for Policy-driven Mission Planning Under Constraints. In Proceedings of the First Proactive Assistant Agents Symposium (pp. 44-50). (Fall Symposium Series). AAAI Press.

Agent Support for Policy-driven Mission Planning Under Constraints. / Sensoy, Murat; Masato, Daniele; Norman, Timothy J; Sycara, Katia; Kollingbaum, Martin; Oh, Jean; Burnett, Christopher.

Proceedings of the First Proactive Assistant Agents Symposium. AAAI Press, 2010. p. 44-50 (Fall Symposium Series).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sensoy, M, Masato, D, Norman, TJ, Sycara, K, Kollingbaum, M, Oh, J & Burnett, C 2010, Agent Support for Policy-driven Mission Planning Under Constraints. in Proceedings of the First Proactive Assistant Agents Symposium. Fall Symposium Series, AAAI Press, pp. 44-50.
Sensoy M, Masato D, Norman TJ, Sycara K, Kollingbaum M, Oh J et al. Agent Support for Policy-driven Mission Planning Under Constraints. In Proceedings of the First Proactive Assistant Agents Symposium. AAAI Press. 2010. p. 44-50. (Fall Symposium Series).
Sensoy, Murat ; Masato, Daniele ; Norman, Timothy J ; Sycara, Katia ; Kollingbaum, Martin ; Oh, Jean ; Burnett, Christopher. / Agent Support for Policy-driven Mission Planning Under Constraints. Proceedings of the First Proactive Assistant Agents Symposium. AAAI Press, 2010. pp. 44-50 (Fall Symposium Series).
@inproceedings{d09195a7922b4956ba2f3f31710a40f5,
title = "Agent Support for Policy-driven Mission Planning Under Constraints",
abstract = "Forming ad-hoc coalitions between military forces and humanitarian organizations is crucial in mission-critical scenarios. Very often coalition parties need to operate according to planning constraints and regulations, or policies. Therefore, they find themselves not only in need to consider their own goals, but also to support coalition partners to the extent allowed by such regulations. In time-stressed conditions, this is a challenging and cognition-intensive task. In this paper, we present intelligent agents that support human planners and ease their cognitive burden by detecting and giving advice about the violation of policies and constraints. Through a series of experiments conducted with human subjects, we compare and contrast the agents' performance on a number of metrics in three conditions: agent support, transparent policy enforcement, and neither support nor enforcement.",
keywords = "Multiagent Systems, Semantic Web",
author = "Murat Sensoy and Daniele Masato and Norman, {Timothy J} and Katia Sycara and Martin Kollingbaum and Jean Oh and Christopher Burnett",
year = "2010",
language = "English",
series = "Fall Symposium Series",
publisher = "AAAI Press",
pages = "44--50",
booktitle = "Proceedings of the First Proactive Assistant Agents Symposium",

}

TY - GEN

T1 - Agent Support for Policy-driven Mission Planning Under Constraints

AU - Sensoy, Murat

AU - Masato, Daniele

AU - Norman, Timothy J

AU - Sycara, Katia

AU - Kollingbaum, Martin

AU - Oh, Jean

AU - Burnett, Christopher

PY - 2010

Y1 - 2010

N2 - Forming ad-hoc coalitions between military forces and humanitarian organizations is crucial in mission-critical scenarios. Very often coalition parties need to operate according to planning constraints and regulations, or policies. Therefore, they find themselves not only in need to consider their own goals, but also to support coalition partners to the extent allowed by such regulations. In time-stressed conditions, this is a challenging and cognition-intensive task. In this paper, we present intelligent agents that support human planners and ease their cognitive burden by detecting and giving advice about the violation of policies and constraints. Through a series of experiments conducted with human subjects, we compare and contrast the agents' performance on a number of metrics in three conditions: agent support, transparent policy enforcement, and neither support nor enforcement.

AB - Forming ad-hoc coalitions between military forces and humanitarian organizations is crucial in mission-critical scenarios. Very often coalition parties need to operate according to planning constraints and regulations, or policies. Therefore, they find themselves not only in need to consider their own goals, but also to support coalition partners to the extent allowed by such regulations. In time-stressed conditions, this is a challenging and cognition-intensive task. In this paper, we present intelligent agents that support human planners and ease their cognitive burden by detecting and giving advice about the violation of policies and constraints. Through a series of experiments conducted with human subjects, we compare and contrast the agents' performance on a number of metrics in three conditions: agent support, transparent policy enforcement, and neither support nor enforcement.

KW - Multiagent Systems

KW - Semantic Web

M3 - Conference contribution

T3 - Fall Symposium Series

SP - 44

EP - 50

BT - Proceedings of the First Proactive Assistant Agents Symposium

PB - AAAI Press

ER -