Task models for human-computer collaboration in supervisory control of teams of autonomous systems

Douglas S. Lange, Robert S. Gutzwiller, Phillip Verbancsics, Terence Sin

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

4 Citations (Scopus)

Abstract

Supervisory control of complex teams of autonomous systems, itself may require levels of autonomous decision making. A single human operator or a small number of operators attempting to maintain situational awareness and control over a large number of autonomous units may require automated assistance in overseeing such a team. This assistance may range from attention management services to outright automated control. We are developing such a capability to assist human controllers of automated vehicles. The core of the capability lies in a task model that includes information about the computer's ability to perform a task as well as the ability of the human operator. Including risk of automation in the calculation allows us to trade off risk and capability. Values can be learned through simulation and live operations. This paper describes the task models being used, the measure of automation risk, the composite metric used to make trade-off decisions and briefly describes the process of learning the critical values.

Original languageEnglish (US)
Title of host publication2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014
PublisherIEEE Computer Society
Pages97-102
Number of pages6
ISBN (Print)9781479935642
DOIs
StatePublished - Jan 1 2014
Externally publishedYes
Event2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014 - San Antonio, TX, United States
Duration: Mar 3 2014Mar 6 2014

Publication series

Name2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014

Conference

Conference2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014
CountryUnited States
CitySan Antonio, TX
Period3/3/143/6/14

Fingerprint

Automation
Mathematical operators
Decision making
Controllers
Composite materials

Keywords

  • autonomies
  • autonomous systems
  • supervisory control
  • task model

ASJC Scopus subject areas

  • Software

Cite this

Lange, D. S., Gutzwiller, R. S., Verbancsics, P., & Sin, T. (2014). Task models for human-computer collaboration in supervisory control of teams of autonomous systems. In 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014 (pp. 97-102). [6816547] (2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014). IEEE Computer Society. https://doi.org/10.1109/CogSIMA.2014.6816547

Task models for human-computer collaboration in supervisory control of teams of autonomous systems. / Lange, Douglas S.; Gutzwiller, Robert S.; Verbancsics, Phillip; Sin, Terence.

2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014. IEEE Computer Society, 2014. p. 97-102 6816547 (2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014).

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

Lange, DS, Gutzwiller, RS, Verbancsics, P & Sin, T 2014, Task models for human-computer collaboration in supervisory control of teams of autonomous systems. in 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014., 6816547, 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014, IEEE Computer Society, pp. 97-102, 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014, San Antonio, TX, United States, 3/3/14. https://doi.org/10.1109/CogSIMA.2014.6816547
Lange DS, Gutzwiller RS, Verbancsics P, Sin T. Task models for human-computer collaboration in supervisory control of teams of autonomous systems. In 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014. IEEE Computer Society. 2014. p. 97-102. 6816547. (2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014). https://doi.org/10.1109/CogSIMA.2014.6816547
Lange, Douglas S. ; Gutzwiller, Robert S. ; Verbancsics, Phillip ; Sin, Terence. / Task models for human-computer collaboration in supervisory control of teams of autonomous systems. 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014. IEEE Computer Society, 2014. pp. 97-102 (2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014).
@inproceedings{75a555f15f984908a5a21bddfd143520,
title = "Task models for human-computer collaboration in supervisory control of teams of autonomous systems",
abstract = "Supervisory control of complex teams of autonomous systems, itself may require levels of autonomous decision making. A single human operator or a small number of operators attempting to maintain situational awareness and control over a large number of autonomous units may require automated assistance in overseeing such a team. This assistance may range from attention management services to outright automated control. We are developing such a capability to assist human controllers of automated vehicles. The core of the capability lies in a task model that includes information about the computer's ability to perform a task as well as the ability of the human operator. Including risk of automation in the calculation allows us to trade off risk and capability. Values can be learned through simulation and live operations. This paper describes the task models being used, the measure of automation risk, the composite metric used to make trade-off decisions and briefly describes the process of learning the critical values.",
keywords = "autonomies, autonomous systems, supervisory control, task model",
author = "Lange, {Douglas S.} and Gutzwiller, {Robert S.} and Phillip Verbancsics and Terence Sin",
year = "2014",
month = "1",
day = "1",
doi = "10.1109/CogSIMA.2014.6816547",
language = "English (US)",
isbn = "9781479935642",
series = "2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014",
publisher = "IEEE Computer Society",
pages = "97--102",
booktitle = "2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014",

}

TY - GEN

T1 - Task models for human-computer collaboration in supervisory control of teams of autonomous systems

AU - Lange, Douglas S.

AU - Gutzwiller, Robert S.

AU - Verbancsics, Phillip

AU - Sin, Terence

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Supervisory control of complex teams of autonomous systems, itself may require levels of autonomous decision making. A single human operator or a small number of operators attempting to maintain situational awareness and control over a large number of autonomous units may require automated assistance in overseeing such a team. This assistance may range from attention management services to outright automated control. We are developing such a capability to assist human controllers of automated vehicles. The core of the capability lies in a task model that includes information about the computer's ability to perform a task as well as the ability of the human operator. Including risk of automation in the calculation allows us to trade off risk and capability. Values can be learned through simulation and live operations. This paper describes the task models being used, the measure of automation risk, the composite metric used to make trade-off decisions and briefly describes the process of learning the critical values.

AB - Supervisory control of complex teams of autonomous systems, itself may require levels of autonomous decision making. A single human operator or a small number of operators attempting to maintain situational awareness and control over a large number of autonomous units may require automated assistance in overseeing such a team. This assistance may range from attention management services to outright automated control. We are developing such a capability to assist human controllers of automated vehicles. The core of the capability lies in a task model that includes information about the computer's ability to perform a task as well as the ability of the human operator. Including risk of automation in the calculation allows us to trade off risk and capability. Values can be learned through simulation and live operations. This paper describes the task models being used, the measure of automation risk, the composite metric used to make trade-off decisions and briefly describes the process of learning the critical values.

KW - autonomies

KW - autonomous systems

KW - supervisory control

KW - task model

UR - http://www.scopus.com/inward/record.url?scp=84902095949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84902095949&partnerID=8YFLogxK

U2 - 10.1109/CogSIMA.2014.6816547

DO - 10.1109/CogSIMA.2014.6816547

M3 - Conference contribution

AN - SCOPUS:84902095949

SN - 9781479935642

T3 - 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014

SP - 97

EP - 102

BT - 2014 IEEE International Inter-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support, CogSIMA 2014

PB - IEEE Computer Society

ER -