Human social motor solutions for human-machine interaction in dynamical task contexts

Patrick Nalepka, Maurice Lamb, Rachel W. Kallen, Kevin Shockley, Anthony Chemero, Elliot Saltzman, Michael J. Richardson

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Multiagent activity is commonplace in everyday life and can improve the behavioral efficiency of task performance and learning. Thus, augmenting social contexts with the use of interactive virtual and robotic agents is of great interest across health, sport, and industry domains. However, the effectiveness of human-machine interaction (HMI) to effectively train humans for future social encounters depends on the ability of artificial agents to respond to human coactors in a natural, human-like manner. One way to achieve effective HMI is by developing dynamical models utilizing dynamical motor primitives (DMPs) of human multiagent coordination that not only capture the behavioral dynamics of successful human performance but also, provide a tractable control architecture for computerized agents. Previous research has demonstrated how DMPs can successfully capture human-like dynamics of simple nonsocial, single-actor movements. However, it is unclear whether DMPs can be used to model more complex multiagent task scenarios. This study tested this human-centered approach to HMI using a complex dyadic shepherding task, in which pairs of coacting agents had to work together to corral and contain small herds of virtual sheep. Human-human and human-artificial agent dyads were tested across two different task contexts. The results revealed (i) that the performance of human-human dyads was equivalent to those composed of a human and the artificial agent and (ii) that, using a "Turing-like" methodology, most participants in the HMI condition were unaware that they were working alongside an artificial agent, further validating the isomorphism of human and artificial agent behavior.
LanguageEnglish
Pages1437-1446
Number of pages10
JournalProceedings of the National Academy of Sciences
Volume116
Issue number4
DOIs
Publication statusPublished - 22 Jan 2019

Fingerprint

Sports
Robotics
Health
Industry

Cite this

@article{a3e6cffa662a49a3a4e9847671bab976,
title = "Human social motor solutions for human-machine interaction in dynamical task contexts",
abstract = "Multiagent activity is commonplace in everyday life and can improve the behavioral efficiency of task performance and learning. Thus, augmenting social contexts with the use of interactive virtual and robotic agents is of great interest across health, sport, and industry domains. However, the effectiveness of human-machine interaction (HMI) to effectively train humans for future social encounters depends on the ability of artificial agents to respond to human coactors in a natural, human-like manner. One way to achieve effective HMI is by developing dynamical models utilizing dynamical motor primitives (DMPs) of human multiagent coordination that not only capture the behavioral dynamics of successful human performance but also, provide a tractable control architecture for computerized agents. Previous research has demonstrated how DMPs can successfully capture human-like dynamics of simple nonsocial, single-actor movements. However, it is unclear whether DMPs can be used to model more complex multiagent task scenarios. This study tested this human-centered approach to HMI using a complex dyadic shepherding task, in which pairs of coacting agents had to work together to corral and contain small herds of virtual sheep. Human-human and human-artificial agent dyads were tested across two different task contexts. The results revealed (i) that the performance of human-human dyads was equivalent to those composed of a human and the artificial agent and (ii) that, using a {"}Turing-like{"} methodology, most participants in the HMI condition were unaware that they were working alongside an artificial agent, further validating the isomorphism of human and artificial agent behavior.",
keywords = "multiagent coordination, human–machine interaction, task-dynamic modeling, dynamical motor primitives, shepherding",
author = "Patrick Nalepka and Maurice Lamb and Kallen, {Rachel W.} and Kevin Shockley and Anthony Chemero and Elliot Saltzman and Richardson, {Michael J.}",
year = "2019",
month = "1",
day = "22",
doi = "10.1073/pnas.1813164116",
language = "English",
volume = "116",
pages = "1437--1446",
journal = "Proceedings of the National Academy of Sciences",
issn = "0027-8424",
publisher = "NATL ACAD SCIENCES",
number = "4",

}

Human social motor solutions for human-machine interaction in dynamical task contexts. / Nalepka, Patrick; Lamb, Maurice; Kallen, Rachel W.; Shockley, Kevin; Chemero, Anthony; Saltzman, Elliot; Richardson, Michael J.

In: Proceedings of the National Academy of Sciences, Vol. 116, No. 4, 22.01.2019, p. 1437-1446.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Human social motor solutions for human-machine interaction in dynamical task contexts

AU - Nalepka,Patrick

AU - Lamb,Maurice

AU - Kallen,Rachel W.

AU - Shockley,Kevin

AU - Chemero,Anthony

AU - Saltzman,Elliot

AU - Richardson,Michael J.

PY - 2019/1/22

Y1 - 2019/1/22

N2 - Multiagent activity is commonplace in everyday life and can improve the behavioral efficiency of task performance and learning. Thus, augmenting social contexts with the use of interactive virtual and robotic agents is of great interest across health, sport, and industry domains. However, the effectiveness of human-machine interaction (HMI) to effectively train humans for future social encounters depends on the ability of artificial agents to respond to human coactors in a natural, human-like manner. One way to achieve effective HMI is by developing dynamical models utilizing dynamical motor primitives (DMPs) of human multiagent coordination that not only capture the behavioral dynamics of successful human performance but also, provide a tractable control architecture for computerized agents. Previous research has demonstrated how DMPs can successfully capture human-like dynamics of simple nonsocial, single-actor movements. However, it is unclear whether DMPs can be used to model more complex multiagent task scenarios. This study tested this human-centered approach to HMI using a complex dyadic shepherding task, in which pairs of coacting agents had to work together to corral and contain small herds of virtual sheep. Human-human and human-artificial agent dyads were tested across two different task contexts. The results revealed (i) that the performance of human-human dyads was equivalent to those composed of a human and the artificial agent and (ii) that, using a "Turing-like" methodology, most participants in the HMI condition were unaware that they were working alongside an artificial agent, further validating the isomorphism of human and artificial agent behavior.

AB - Multiagent activity is commonplace in everyday life and can improve the behavioral efficiency of task performance and learning. Thus, augmenting social contexts with the use of interactive virtual and robotic agents is of great interest across health, sport, and industry domains. However, the effectiveness of human-machine interaction (HMI) to effectively train humans for future social encounters depends on the ability of artificial agents to respond to human coactors in a natural, human-like manner. One way to achieve effective HMI is by developing dynamical models utilizing dynamical motor primitives (DMPs) of human multiagent coordination that not only capture the behavioral dynamics of successful human performance but also, provide a tractable control architecture for computerized agents. Previous research has demonstrated how DMPs can successfully capture human-like dynamics of simple nonsocial, single-actor movements. However, it is unclear whether DMPs can be used to model more complex multiagent task scenarios. This study tested this human-centered approach to HMI using a complex dyadic shepherding task, in which pairs of coacting agents had to work together to corral and contain small herds of virtual sheep. Human-human and human-artificial agent dyads were tested across two different task contexts. The results revealed (i) that the performance of human-human dyads was equivalent to those composed of a human and the artificial agent and (ii) that, using a "Turing-like" methodology, most participants in the HMI condition were unaware that they were working alongside an artificial agent, further validating the isomorphism of human and artificial agent behavior.

KW - multiagent coordination

KW - human–machine interaction

KW - task-dynamic modeling

KW - dynamical motor primitives

KW - shepherding

UR - http://www.scopus.com/inward/record.url?scp=85060308746&partnerID=8YFLogxK

U2 - 10.1073/pnas.1813164116

DO - 10.1073/pnas.1813164116

M3 - Article

VL - 116

SP - 1437

EP - 1446

JO - Proceedings of the National Academy of Sciences

T2 - Proceedings of the National Academy of Sciences

JF - Proceedings of the National Academy of Sciences

SN - 0027-8424

IS - 4

ER -