Building a Synthetic Task Environment to Support Artificial Social Intelligence Research

Christopher C. Corral; Keerthi Shrikar Tatapudi; Verica Buchanan; Lixiao Huang; Nancy J. Cooke

doi:10.1177/1071181321651354a

Building a Synthetic Task Environment to Support Artificial Social Intelligence Research

Christopher C. Corral, Keerthi Shrikar Tatapudi, Verica Buchanan, Lixiao Huang, Nancy J. Cooke

Engineering, Ira A. Fulton Schools of (IAFSE)

Research output: Contribution to journal › Conference article › peer-review

7 Scopus citations

Abstract

To support research on artificial social intelligence for successful teams (ASIST), an urban search and rescue task (USAR) was simulated within Minecraft to serve as a Synthetic Task Environment (STE). The goal for the development of the present STE was to create an environment that provides ample opportunities to allow ASI agents to demonstrate the theory of mind by making inferences and predictions of humans’ states and actions in the USAR task environment, and in the future to intervene to improve teamwork in real-time. This paper describes the STE design background, design potentials and considerations, rich data collection opportunities, and potential usage for more broad research.

Original language	English (US)
Pages (from-to)	660-664
Number of pages	5
Journal	Proceedings of the Human Factors and Ergonomics Society
Volume	65
Issue number	1
DOIs	https://doi.org/10.1177/1071181321651354a
State	Published - 2021
Event	65th Human Factors and Ergonomics Society Annual Meeting, HFES 2021 - Baltimore, United States Duration: Oct 3 2021 → Oct 8 2021

Keywords

Artificial Social Intelligence
Minecraft
Synthetic Task Environment
Theory of Mind
Urban Search and Rescue

ASJC Scopus subject areas

Human Factors and Ergonomics

Access to Document

10.1177/1071181321651354a

Cite this

@article{0698b9a02c2041608e6675f63a4fd48e,

title = "Building a Synthetic Task Environment to Support Artificial Social Intelligence Research",

abstract = "To support research on artificial social intelligence for successful teams (ASIST), an urban search and rescue task (USAR) was simulated within Minecraft to serve as a Synthetic Task Environment (STE). The goal for the development of the present STE was to create an environment that provides ample opportunities to allow ASI agents to demonstrate the theory of mind by making inferences and predictions of humans{\textquoteright} states and actions in the USAR task environment, and in the future to intervene to improve teamwork in real-time. This paper describes the STE design background, design potentials and considerations, rich data collection opportunities, and potential usage for more broad research.",

keywords = "Artificial Social Intelligence, Minecraft, Synthetic Task Environment, Theory of Mind, Urban Search and Rescue",

author = "Corral, {Christopher C.} and Tatapudi, {Keerthi Shrikar} and Verica Buchanan and Lixiao Huang and Cooke, {Nancy J.}",

note = "Publisher Copyright: {\textcopyright} 2021 by Human Factors and Ergonomics Society. All rights reserved.; 65th Human Factors and Ergonomics Society Annual Meeting, HFES 2021 ; Conference date: 03-10-2021 Through 08-10-2021",

year = "2021",

doi = "10.1177/1071181321651354a",

language = "English (US)",

volume = "65",

pages = "660--664",

journal = "Proceedings of the Human Factors and Ergonomics Society",

issn = "1071-1813",

publisher = "SAGE Publications Inc.",

number = "1",

}

TY - JOUR

T1 - Building a Synthetic Task Environment to Support Artificial Social Intelligence Research

AU - Corral, Christopher C.

AU - Tatapudi, Keerthi Shrikar

AU - Buchanan, Verica

AU - Huang, Lixiao

AU - Cooke, Nancy J.

PY - 2021

Y1 - 2021

N2 - To support research on artificial social intelligence for successful teams (ASIST), an urban search and rescue task (USAR) was simulated within Minecraft to serve as a Synthetic Task Environment (STE). The goal for the development of the present STE was to create an environment that provides ample opportunities to allow ASI agents to demonstrate the theory of mind by making inferences and predictions of humans’ states and actions in the USAR task environment, and in the future to intervene to improve teamwork in real-time. This paper describes the STE design background, design potentials and considerations, rich data collection opportunities, and potential usage for more broad research.

AB - To support research on artificial social intelligence for successful teams (ASIST), an urban search and rescue task (USAR) was simulated within Minecraft to serve as a Synthetic Task Environment (STE). The goal for the development of the present STE was to create an environment that provides ample opportunities to allow ASI agents to demonstrate the theory of mind by making inferences and predictions of humans’ states and actions in the USAR task environment, and in the future to intervene to improve teamwork in real-time. This paper describes the STE design background, design potentials and considerations, rich data collection opportunities, and potential usage for more broad research.

KW - Artificial Social Intelligence

KW - Minecraft

KW - Synthetic Task Environment

KW - Theory of Mind

KW - Urban Search and Rescue

UR - http://www.scopus.com/inward/record.url?scp=85131390427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85131390427&partnerID=8YFLogxK

U2 - 10.1177/1071181321651354a

DO - 10.1177/1071181321651354a

M3 - Conference article

AN - SCOPUS:85131390427

SN - 1071-1813

VL - 65

SP - 660

EP - 664

JO - Proceedings of the Human Factors and Ergonomics Society

JF - Proceedings of the Human Factors and Ergonomics Society

IS - 1

T2 - 65th Human Factors and Ergonomics Society Annual Meeting, HFES 2021

Y2 - 3 October 2021 through 8 October 2021

ER -

Building a Synthetic Task Environment to Support Artificial Social Intelligence Research

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this