Distributed learning and cooperative control for multi-agent systems

Jongeun Choi, Songhwai Oh, Roberto Horowitz

Research output: Contribution to journalArticle

129 Citations (Scopus)

Abstract

This paper presents an algorithm and analysis of distributed learning and cooperative control for a multi-agent system so that a global goal of the overall system can be achieved by locally acting agents. We consider a resource-constrained multi-agent system, in which each agent has limited capabilities in terms of sensing, computation, and communication. The proposed algorithm is executed by each agent independently to estimate an unknown field of interest from noisy measurements and to coordinate multiple agents in a distributed manner to discover peaks of the unknown field. Each mobile agent maintains its own local estimate of the field and updates the estimate using collective measurements from itself and nearby agents. Each agent then moves towards peaks of the field using the gradient of its estimated field while avoiding collision and maintaining communication connectivity. The proposed algorithm is based on a recursive spatial estimation of an unknown field. We show that the closed-loop dynamics of the proposed multi-agent system can be transformed into a form of a stochastic approximation algorithm and prove its convergence using Ljung's ordinary differential equation (ODE) approach. We also present extensive simulation results supporting our theoretical results.

Original languageEnglish
Pages (from-to)2802-2814
Number of pages13
JournalAutomatica
Volume45
Issue number12
DOIs
Publication statusPublished - 2009 Dec 1

Fingerprint

Multi agent systems
Mobile agents
Communication
Approximation algorithms
Ordinary differential equations

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Choi, Jongeun ; Oh, Songhwai ; Horowitz, Roberto. / Distributed learning and cooperative control for multi-agent systems. In: Automatica. 2009 ; Vol. 45, No. 12. pp. 2802-2814.
@article{72cdacec650a408c97c428888219993e,
title = "Distributed learning and cooperative control for multi-agent systems",
abstract = "This paper presents an algorithm and analysis of distributed learning and cooperative control for a multi-agent system so that a global goal of the overall system can be achieved by locally acting agents. We consider a resource-constrained multi-agent system, in which each agent has limited capabilities in terms of sensing, computation, and communication. The proposed algorithm is executed by each agent independently to estimate an unknown field of interest from noisy measurements and to coordinate multiple agents in a distributed manner to discover peaks of the unknown field. Each mobile agent maintains its own local estimate of the field and updates the estimate using collective measurements from itself and nearby agents. Each agent then moves towards peaks of the field using the gradient of its estimated field while avoiding collision and maintaining communication connectivity. The proposed algorithm is based on a recursive spatial estimation of an unknown field. We show that the closed-loop dynamics of the proposed multi-agent system can be transformed into a form of a stochastic approximation algorithm and prove its convergence using Ljung's ordinary differential equation (ODE) approach. We also present extensive simulation results supporting our theoretical results.",
author = "Jongeun Choi and Songhwai Oh and Roberto Horowitz",
year = "2009",
month = "12",
day = "1",
doi = "10.1016/j.automatica.2009.09.025",
language = "English",
volume = "45",
pages = "2802--2814",
journal = "Automatica",
issn = "0005-1098",
publisher = "Elsevier Limited",
number = "12",

}

Distributed learning and cooperative control for multi-agent systems. / Choi, Jongeun; Oh, Songhwai; Horowitz, Roberto.

In: Automatica, Vol. 45, No. 12, 01.12.2009, p. 2802-2814.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Distributed learning and cooperative control for multi-agent systems

AU - Choi, Jongeun

AU - Oh, Songhwai

AU - Horowitz, Roberto

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This paper presents an algorithm and analysis of distributed learning and cooperative control for a multi-agent system so that a global goal of the overall system can be achieved by locally acting agents. We consider a resource-constrained multi-agent system, in which each agent has limited capabilities in terms of sensing, computation, and communication. The proposed algorithm is executed by each agent independently to estimate an unknown field of interest from noisy measurements and to coordinate multiple agents in a distributed manner to discover peaks of the unknown field. Each mobile agent maintains its own local estimate of the field and updates the estimate using collective measurements from itself and nearby agents. Each agent then moves towards peaks of the field using the gradient of its estimated field while avoiding collision and maintaining communication connectivity. The proposed algorithm is based on a recursive spatial estimation of an unknown field. We show that the closed-loop dynamics of the proposed multi-agent system can be transformed into a form of a stochastic approximation algorithm and prove its convergence using Ljung's ordinary differential equation (ODE) approach. We also present extensive simulation results supporting our theoretical results.

AB - This paper presents an algorithm and analysis of distributed learning and cooperative control for a multi-agent system so that a global goal of the overall system can be achieved by locally acting agents. We consider a resource-constrained multi-agent system, in which each agent has limited capabilities in terms of sensing, computation, and communication. The proposed algorithm is executed by each agent independently to estimate an unknown field of interest from noisy measurements and to coordinate multiple agents in a distributed manner to discover peaks of the unknown field. Each mobile agent maintains its own local estimate of the field and updates the estimate using collective measurements from itself and nearby agents. Each agent then moves towards peaks of the field using the gradient of its estimated field while avoiding collision and maintaining communication connectivity. The proposed algorithm is based on a recursive spatial estimation of an unknown field. We show that the closed-loop dynamics of the proposed multi-agent system can be transformed into a form of a stochastic approximation algorithm and prove its convergence using Ljung's ordinary differential equation (ODE) approach. We also present extensive simulation results supporting our theoretical results.

UR - http://www.scopus.com/inward/record.url?scp=70449632298&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70449632298&partnerID=8YFLogxK

U2 - 10.1016/j.automatica.2009.09.025

DO - 10.1016/j.automatica.2009.09.025

M3 - Article

AN - SCOPUS:70449632298

VL - 45

SP - 2802

EP - 2814

JO - Automatica

JF - Automatica

SN - 0005-1098

IS - 12

ER -