JSwarm: A Jingulu-Inspired Human-AI-Teaming Language for Context-Aware Swarm Guidance

Hussein A. Abbass; Eleni Petraki; Robert Hunjet

doi:10.3389/fphy.2022.944064

JSwarm: A Jingulu-Inspired Human-AI-Teaming Language for Context-Aware Swarm Guidance

Hussein A. Abbass, Eleni Petraki, Robert Hunjet

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

87 Downloads (Pure)

Abstract

Bi-directional communication between humans and swarm systems begs for efficient languages to communicate information between the humans and the Artificial Intelligence (AI)-enabled agents in a manner that is most appropriate for the context. We discuss the criteria for effective teaming and functional bi-directional communication between humans and AI, and the design choices required to create effective languages. We then present a human-AI-teaming communication language inspired by the Australian Aboriginal language of Jingulu, which we call JSwarm. We present the motivation and structure of the language. An example is used to demonstrate how the language operates for a shepherding swarm guidance task.

Original language	English
Article number	944064
Pages (from-to)	1-14
Number of pages	14
Journal	Frontiers in Physics
Volume	10
DOIs	https://doi.org/10.3389/fphy.2022.944064
Publication status	Published - 14 Jul 2022

Access to Document

10.3389/fphy.2022.944064Licence: CC BY

ArticleFinal published version, 1.17 MBLicence: CC BY

Cite this

@article{7a22fc9b2bbc4d97b18f7f95258a3539,

title = "JSwarm: A Jingulu-Inspired Human-AI-Teaming Language for Context-Aware Swarm Guidance",

abstract = "Bi-directional communication between humans and swarm systems begs for efficient languages to communicate information between the humans and the Artificial Intelligence (AI)-enabled agents in a manner that is most appropriate for the context. We discuss the criteria for effective teaming and functional bi-directional communication between humans and AI, and the design choices required to create effective languages. We then present a human-AI-teaming communication language inspired by the Australian Aboriginal language of Jingulu, which we call JSwarm. We present the motivation and structure of the language. An example is used to demonstrate how the language operates for a shepherding swarm guidance task.",

keywords = "human-AI teaming, human-swarm languages, human-swarm teaming, jingulu, teaming languages",

author = "Abbass, {Hussein A.} and Eleni Petraki and Robert Hunjet",

note = "Funding Information: This work is funded by Grant No N62909-18-1-2140 from Office of Naval Research Global (ONRG). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the ONRG. Publisher Copyright: Copyright {\textcopyright} 2022 Abbass, Petraki and Hunjet.",

year = "2022",

month = jul,

day = "14",

doi = "10.3389/fphy.2022.944064",

language = "English",

volume = "10",

pages = "1--14",

journal = "Frontiers in Physics",

issn = "2296-424X",

}

TY - JOUR

T1 - JSwarm

T2 - A Jingulu-Inspired Human-AI-Teaming Language for Context-Aware Swarm Guidance

AU - Abbass, Hussein A.

AU - Petraki, Eleni

AU - Hunjet, Robert

N1 - Funding Information: This work is funded by Grant No N62909-18-1-2140 from Office of Naval Research Global (ONRG). Its contents are solely the responsibility of the authors and do not necessarily represent the official views of the ONRG. Publisher Copyright: Copyright © 2022 Abbass, Petraki and Hunjet.

PY - 2022/7/14

Y1 - 2022/7/14

N2 - Bi-directional communication between humans and swarm systems begs for efficient languages to communicate information between the humans and the Artificial Intelligence (AI)-enabled agents in a manner that is most appropriate for the context. We discuss the criteria for effective teaming and functional bi-directional communication between humans and AI, and the design choices required to create effective languages. We then present a human-AI-teaming communication language inspired by the Australian Aboriginal language of Jingulu, which we call JSwarm. We present the motivation and structure of the language. An example is used to demonstrate how the language operates for a shepherding swarm guidance task.

AB - Bi-directional communication between humans and swarm systems begs for efficient languages to communicate information between the humans and the Artificial Intelligence (AI)-enabled agents in a manner that is most appropriate for the context. We discuss the criteria for effective teaming and functional bi-directional communication between humans and AI, and the design choices required to create effective languages. We then present a human-AI-teaming communication language inspired by the Australian Aboriginal language of Jingulu, which we call JSwarm. We present the motivation and structure of the language. An example is used to demonstrate how the language operates for a shepherding swarm guidance task.

KW - human-AI teaming

KW - human-swarm languages

KW - human-swarm teaming

KW - jingulu

KW - teaming languages

UR - http://www.scopus.com/inward/record.url?scp=85135101453&partnerID=8YFLogxK

U2 - 10.3389/fphy.2022.944064

DO - 10.3389/fphy.2022.944064

M3 - Article

AN - SCOPUS:85135101453

SN - 2296-424X

VL - 10

SP - 1

EP - 14

JO - Frontiers in Physics

JF - Frontiers in Physics

M1 - 944064

ER -

JSwarm: A Jingulu-Inspired Human-AI-Teaming Language for Context-Aware Swarm Guidance

Abstract

Access to Document

Other files and links

Fingerprint

Cite this