A Payoff-Based Learning Approach to Cooperative Environmental Monitoring for PTZ Visual Sensor Networks

Takeshi Hatanaka, Yasuaki Wasa, Riku Funada, Alexandros G. Charalambides, Masayuki Fujita

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

This paper addresses cooperative environmental monitoring for Pan-Tilt-Zoom (PTZ) visual sensor networks. In particular, we investigate the optimal monitoring problem whose objective function value is intertwined with the uncertain state of the physical world. In addition, due to the large volume of vision data, it is desired for each sensor to execute processing through local computation and communication. To address these issues, we present a distributed solution to the problem based on game theoretic cooperative control and payoff-based learning. At the first stage, a utility function is designed so that the resulting game constitutes a potential game with potential function equal to the group objective function, where the designed utility is shown to be computable through local image processing and communication. Then, we present a payoff-based learning algorithm so that the sensors are led to the global objective function maximizers without using any prior information on the environmental state. Finally, we run experiments to demonstrate the effectiveness of the present approach.

Original languageEnglish
Article number7138601
Pages (from-to)709-724
Number of pages16
JournalIEEE Transactions on Automatic Control
Volume61
Issue number3
DOIs
Publication statusPublished - 2016 Mar 1
Externally publishedYes

Fingerprint

Sensor networks
Monitoring
Communication
Sensors
Learning algorithms
Image processing
Processing
Experiments

Keywords

  • Cyber-physical systems
  • Environmental monitoring
  • Game theoretic cooperative control
  • Payoff-based learning
  • Visual sensor networks

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

A Payoff-Based Learning Approach to Cooperative Environmental Monitoring for PTZ Visual Sensor Networks. / Hatanaka, Takeshi; Wasa, Yasuaki; Funada, Riku; Charalambides, Alexandros G.; Fujita, Masayuki.

In: IEEE Transactions on Automatic Control, Vol. 61, No. 3, 7138601, 01.03.2016, p. 709-724.

Research output: Contribution to journalArticle

@article{738bd79529424c9e8c55ed647129a5f2,
title = "A Payoff-Based Learning Approach to Cooperative Environmental Monitoring for PTZ Visual Sensor Networks",
abstract = "This paper addresses cooperative environmental monitoring for Pan-Tilt-Zoom (PTZ) visual sensor networks. In particular, we investigate the optimal monitoring problem whose objective function value is intertwined with the uncertain state of the physical world. In addition, due to the large volume of vision data, it is desired for each sensor to execute processing through local computation and communication. To address these issues, we present a distributed solution to the problem based on game theoretic cooperative control and payoff-based learning. At the first stage, a utility function is designed so that the resulting game constitutes a potential game with potential function equal to the group objective function, where the designed utility is shown to be computable through local image processing and communication. Then, we present a payoff-based learning algorithm so that the sensors are led to the global objective function maximizers without using any prior information on the environmental state. Finally, we run experiments to demonstrate the effectiveness of the present approach.",
keywords = "Cyber-physical systems, Environmental monitoring, Game theoretic cooperative control, Payoff-based learning, Visual sensor networks",
author = "Takeshi Hatanaka and Yasuaki Wasa and Riku Funada and Charalambides, {Alexandros G.} and Masayuki Fujita",
year = "2016",
month = "3",
day = "1",
doi = "10.1109/TAC.2015.2450611",
language = "English",
volume = "61",
pages = "709--724",
journal = "IEEE Transactions on Automatic Control",
issn = "0018-9286",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

TY - JOUR

T1 - A Payoff-Based Learning Approach to Cooperative Environmental Monitoring for PTZ Visual Sensor Networks

AU - Hatanaka, Takeshi

AU - Wasa, Yasuaki

AU - Funada, Riku

AU - Charalambides, Alexandros G.

AU - Fujita, Masayuki

PY - 2016/3/1

Y1 - 2016/3/1

N2 - This paper addresses cooperative environmental monitoring for Pan-Tilt-Zoom (PTZ) visual sensor networks. In particular, we investigate the optimal monitoring problem whose objective function value is intertwined with the uncertain state of the physical world. In addition, due to the large volume of vision data, it is desired for each sensor to execute processing through local computation and communication. To address these issues, we present a distributed solution to the problem based on game theoretic cooperative control and payoff-based learning. At the first stage, a utility function is designed so that the resulting game constitutes a potential game with potential function equal to the group objective function, where the designed utility is shown to be computable through local image processing and communication. Then, we present a payoff-based learning algorithm so that the sensors are led to the global objective function maximizers without using any prior information on the environmental state. Finally, we run experiments to demonstrate the effectiveness of the present approach.

AB - This paper addresses cooperative environmental monitoring for Pan-Tilt-Zoom (PTZ) visual sensor networks. In particular, we investigate the optimal monitoring problem whose objective function value is intertwined with the uncertain state of the physical world. In addition, due to the large volume of vision data, it is desired for each sensor to execute processing through local computation and communication. To address these issues, we present a distributed solution to the problem based on game theoretic cooperative control and payoff-based learning. At the first stage, a utility function is designed so that the resulting game constitutes a potential game with potential function equal to the group objective function, where the designed utility is shown to be computable through local image processing and communication. Then, we present a payoff-based learning algorithm so that the sensors are led to the global objective function maximizers without using any prior information on the environmental state. Finally, we run experiments to demonstrate the effectiveness of the present approach.

KW - Cyber-physical systems

KW - Environmental monitoring

KW - Game theoretic cooperative control

KW - Payoff-based learning

KW - Visual sensor networks

UR - http://www.scopus.com/inward/record.url?scp=84963741116&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84963741116&partnerID=8YFLogxK

U2 - 10.1109/TAC.2015.2450611

DO - 10.1109/TAC.2015.2450611

M3 - Article

AN - SCOPUS:84963741116

VL - 61

SP - 709

EP - 724

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

SN - 0018-9286

IS - 3

M1 - 7138601

ER -