Designing a mixed-initiative decision-support system for multi-UAS mission planning

Sylvain Bruni, Nathan Schurr, Nancy Cooke, Brian Riordan, Jared Freeman

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

Abstract

Aptima and the Cognitive Engineering Research Institute are developing a mixed-initiative decisionsupport system for planning multi-Unmanned Aerial System (UAS) missions. The prototype capability is called MIMIC: Mixed Initiative Machine for Instructed Computing. At the core of the system is a model that employs machine learning algorithms to learn from operators during mission planning, and to use what is learned to aid subsequent mission planning tasks. This paper reports on the design of the prototype algorithms, the early interface design, and a series of three experiments performed to support the design of the system. First, machine learning algorithms were implemented that use Markov Decision Processes (MDPs) and Bayesian inference to learn a model of the human operator's strategies. Second, a mission planning graphical user interface was designed to enable an operator to conduct basic multi-UAS mission planning, and to allow MIMIC to easily capture operator actions. Finally, three experiments were conducted (1) to identify typical operator planning priorities, in order to define the model's features and to gather planning data to train the algorithms, (2) to evaluate the model by comparing its outputs to operators' selfassessments of priorities and goals, and (3) to test the model's ability to predict what an operator's next actions will be, and compare the predictions to the actual operator actions. The MIMIC project represents a step toward increasing levels of UAS autonomy allowing for multi-UAS control by single operators.

Original languageEnglish (US)
Title of host publicationProceedings of the Human Factors and Ergonomics Society
Pages21-25
Number of pages5
DOIs
StatePublished - 2011
Externally publishedYes
Event55th Human Factors and Ergonomics Society Annual Meeting, HFES 2011 - Las Vegas, NV, United States
Duration: Sep 19 2011Sep 23 2011

Other

Other55th Human Factors and Ergonomics Society Annual Meeting, HFES 2011
CountryUnited States
CityLas Vegas, NV
Period9/19/119/23/11

Fingerprint

Decision support systems
Antennas
Planning
planning
Learning algorithms
planning data
Learning systems
Mathematical operators
system control
experiment
research facility
user interface
Engineering research
learning
Graphical user interfaces
autonomy
engineering
Experiments
Control systems
ability

ASJC Scopus subject areas

  • Human Factors and Ergonomics

Cite this

Bruni, S., Schurr, N., Cooke, N., Riordan, B., & Freeman, J. (2011). Designing a mixed-initiative decision-support system for multi-UAS mission planning. In Proceedings of the Human Factors and Ergonomics Society (pp. 21-25) https://doi.org/10.1177/1071181311551004

Designing a mixed-initiative decision-support system for multi-UAS mission planning. / Bruni, Sylvain; Schurr, Nathan; Cooke, Nancy; Riordan, Brian; Freeman, Jared.

Proceedings of the Human Factors and Ergonomics Society. 2011. p. 21-25.

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

Bruni, S, Schurr, N, Cooke, N, Riordan, B & Freeman, J 2011, Designing a mixed-initiative decision-support system for multi-UAS mission planning. in Proceedings of the Human Factors and Ergonomics Society. pp. 21-25, 55th Human Factors and Ergonomics Society Annual Meeting, HFES 2011, Las Vegas, NV, United States, 9/19/11. https://doi.org/10.1177/1071181311551004
Bruni S, Schurr N, Cooke N, Riordan B, Freeman J. Designing a mixed-initiative decision-support system for multi-UAS mission planning. In Proceedings of the Human Factors and Ergonomics Society. 2011. p. 21-25 https://doi.org/10.1177/1071181311551004
Bruni, Sylvain ; Schurr, Nathan ; Cooke, Nancy ; Riordan, Brian ; Freeman, Jared. / Designing a mixed-initiative decision-support system for multi-UAS mission planning. Proceedings of the Human Factors and Ergonomics Society. 2011. pp. 21-25
@inproceedings{c5fbc84d019e475481bb72b72edea7ee,
title = "Designing a mixed-initiative decision-support system for multi-UAS mission planning",
abstract = "Aptima and the Cognitive Engineering Research Institute are developing a mixed-initiative decisionsupport system for planning multi-Unmanned Aerial System (UAS) missions. The prototype capability is called MIMIC: Mixed Initiative Machine for Instructed Computing. At the core of the system is a model that employs machine learning algorithms to learn from operators during mission planning, and to use what is learned to aid subsequent mission planning tasks. This paper reports on the design of the prototype algorithms, the early interface design, and a series of three experiments performed to support the design of the system. First, machine learning algorithms were implemented that use Markov Decision Processes (MDPs) and Bayesian inference to learn a model of the human operator's strategies. Second, a mission planning graphical user interface was designed to enable an operator to conduct basic multi-UAS mission planning, and to allow MIMIC to easily capture operator actions. Finally, three experiments were conducted (1) to identify typical operator planning priorities, in order to define the model's features and to gather planning data to train the algorithms, (2) to evaluate the model by comparing its outputs to operators' selfassessments of priorities and goals, and (3) to test the model's ability to predict what an operator's next actions will be, and compare the predictions to the actual operator actions. The MIMIC project represents a step toward increasing levels of UAS autonomy allowing for multi-UAS control by single operators.",
author = "Sylvain Bruni and Nathan Schurr and Nancy Cooke and Brian Riordan and Jared Freeman",
year = "2011",
doi = "10.1177/1071181311551004",
language = "English (US)",
isbn = "9780945289395",
pages = "21--25",
booktitle = "Proceedings of the Human Factors and Ergonomics Society",

}

TY - GEN

T1 - Designing a mixed-initiative decision-support system for multi-UAS mission planning

AU - Bruni, Sylvain

AU - Schurr, Nathan

AU - Cooke, Nancy

AU - Riordan, Brian

AU - Freeman, Jared

PY - 2011

Y1 - 2011

N2 - Aptima and the Cognitive Engineering Research Institute are developing a mixed-initiative decisionsupport system for planning multi-Unmanned Aerial System (UAS) missions. The prototype capability is called MIMIC: Mixed Initiative Machine for Instructed Computing. At the core of the system is a model that employs machine learning algorithms to learn from operators during mission planning, and to use what is learned to aid subsequent mission planning tasks. This paper reports on the design of the prototype algorithms, the early interface design, and a series of three experiments performed to support the design of the system. First, machine learning algorithms were implemented that use Markov Decision Processes (MDPs) and Bayesian inference to learn a model of the human operator's strategies. Second, a mission planning graphical user interface was designed to enable an operator to conduct basic multi-UAS mission planning, and to allow MIMIC to easily capture operator actions. Finally, three experiments were conducted (1) to identify typical operator planning priorities, in order to define the model's features and to gather planning data to train the algorithms, (2) to evaluate the model by comparing its outputs to operators' selfassessments of priorities and goals, and (3) to test the model's ability to predict what an operator's next actions will be, and compare the predictions to the actual operator actions. The MIMIC project represents a step toward increasing levels of UAS autonomy allowing for multi-UAS control by single operators.

AB - Aptima and the Cognitive Engineering Research Institute are developing a mixed-initiative decisionsupport system for planning multi-Unmanned Aerial System (UAS) missions. The prototype capability is called MIMIC: Mixed Initiative Machine for Instructed Computing. At the core of the system is a model that employs machine learning algorithms to learn from operators during mission planning, and to use what is learned to aid subsequent mission planning tasks. This paper reports on the design of the prototype algorithms, the early interface design, and a series of three experiments performed to support the design of the system. First, machine learning algorithms were implemented that use Markov Decision Processes (MDPs) and Bayesian inference to learn a model of the human operator's strategies. Second, a mission planning graphical user interface was designed to enable an operator to conduct basic multi-UAS mission planning, and to allow MIMIC to easily capture operator actions. Finally, three experiments were conducted (1) to identify typical operator planning priorities, in order to define the model's features and to gather planning data to train the algorithms, (2) to evaluate the model by comparing its outputs to operators' selfassessments of priorities and goals, and (3) to test the model's ability to predict what an operator's next actions will be, and compare the predictions to the actual operator actions. The MIMIC project represents a step toward increasing levels of UAS autonomy allowing for multi-UAS control by single operators.

UR - http://www.scopus.com/inward/record.url?scp=81855186996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=81855186996&partnerID=8YFLogxK

U2 - 10.1177/1071181311551004

DO - 10.1177/1071181311551004

M3 - Conference contribution

AN - SCOPUS:81855186996

SN - 9780945289395

SP - 21

EP - 25

BT - Proceedings of the Human Factors and Ergonomics Society

ER -