Human-inspired strategies to solve complex joint tasks in multi agent systems

Fabrizia Auletta; Mario di Bernardo; Michael J. Richardson

doi:10.1016/j.ifacol.2021.11.033

Human-inspired strategies to solve complex joint tasks in multi agent systems

Fabrizia Auletta^*, Mario di Bernardo, Michael J. Richardson

^*Corresponding author for this work

Faculty of Medicine, Health and Human Sciences

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

5 Citations (Scopus)

56 Downloads (Pure)

Abstract

In this paper we propose a methodology to integrate human expertise with effective control laws to drive artificial agents in a complex joint task. We use Supervised Machine Learning to derive human-inspired strategies that succeed in task performance independently from the operating conditions of the samples provided in the training phase. Numerical simulations validate the efficiency of the proposed human-inspired strategies against simpler yet computationally expensive rule-based strategies.

Original language	English
Pages (from-to)	105-110
Number of pages	6
Journal	IFAC-PapersOnLine
Volume	54
Issue number	17
DOIs	https://doi.org/10.1016/j.ifacol.2021.11.033
Publication status	Published - Sept 2021
Event	IFAC Conference on Analysis and Control of Chaotic Systems (6th : 2021): CHAOS 2021 - Catania, Italy Duration: 27 Sept 2021 → 29 Sept 2021

Bibliographical note

Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Keywords

nonlinear time series and identification
multi-agent systems
multi-agent coordination
herding problem

Access to Document

10.1016/j.ifacol.2021.11.033Licence: CC BY-NC-ND

Publisher version (open access)Final published version, 812 KBLicence: CC BY-NC-ND

Cite this

@article{d95cde90528e4e658b7683d89e534eaf,

title = "Human-inspired strategies to solve complex joint tasks in multi agent systems",

abstract = "In this paper we propose a methodology to integrate human expertise with effective control laws to drive artificial agents in a complex joint task. We use Supervised Machine Learning to derive human-inspired strategies that succeed in task performance independently from the operating conditions of the samples provided in the training phase. Numerical simulations validate the efficiency of the proposed human-inspired strategies against simpler yet computationally expensive rule-based strategies.",

keywords = "nonlinear time series and identification, multi-agent systems, multi-agent coordination, herding problem",

author = "Fabrizia Auletta and {di Bernardo}, Mario and Richardson, {Michael J.}",

note = "Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.; IFAC Conference on Analysis and Control of Chaotic Systems (6th : 2021) : CHAOS 2021 ; Conference date: 27-09-2021 Through 29-09-2021",

year = "2021",

month = sep,

doi = "10.1016/j.ifacol.2021.11.033",

language = "English",

volume = "54",

pages = "105--110",

journal = "IFAC-PapersOnLine",

issn = "2405-8963",

publisher = "IFAC Secretariat",

number = "17",

}

TY - JOUR

T1 - Human-inspired strategies to solve complex joint tasks in multi agent systems

AU - Auletta, Fabrizia

AU - di Bernardo, Mario

AU - Richardson, Michael J.

N1 - Copyright the Author(s) 2021. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2021/9

Y1 - 2021/9

N2 - In this paper we propose a methodology to integrate human expertise with effective control laws to drive artificial agents in a complex joint task. We use Supervised Machine Learning to derive human-inspired strategies that succeed in task performance independently from the operating conditions of the samples provided in the training phase. Numerical simulations validate the efficiency of the proposed human-inspired strategies against simpler yet computationally expensive rule-based strategies.

AB - In this paper we propose a methodology to integrate human expertise with effective control laws to drive artificial agents in a complex joint task. We use Supervised Machine Learning to derive human-inspired strategies that succeed in task performance independently from the operating conditions of the samples provided in the training phase. Numerical simulations validate the efficiency of the proposed human-inspired strategies against simpler yet computationally expensive rule-based strategies.

KW - nonlinear time series and identification

KW - multi-agent systems

KW - multi-agent coordination

KW - herding problem

UR - http://www.scopus.com/inward/record.url?scp=85120918184&partnerID=8YFLogxK

UR - http://purl.org/au-research/grants/arc/FT180100447

U2 - 10.1016/j.ifacol.2021.11.033

DO - 10.1016/j.ifacol.2021.11.033

M3 - Conference paper

AN - SCOPUS:85120918184

SN - 2405-8963

VL - 54

SP - 105

EP - 110

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

IS - 17

T2 - IFAC Conference on Analysis and Control of Chaotic Systems (6th : 2021)

Y2 - 27 September 2021 through 29 September 2021

ER -

Human-inspired strategies to solve complex joint tasks in multi agent systems

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

ARC - Future Fellowships: Modelling Human Perceptual-Motor Interaction for Human-Machine Applications

Cite this

Human-inspired strategies to solve complex joint tasks in multi agent systems

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Projects

ARC - Future Fellowships: Modelling Human Perceptual-Motor Interaction for Human-Machine Applications

Cite this