Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems

Ayumi Sugiyama, Lingying Wu, Toshiharu Sugawara

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a learning method that decides the appropriate activity cycle length (ACL) according to environmental characteristics and other agents' behavior in the (multi-agent) continuous cooperative patrol problem. With recent advances in computer and sensor technologies, agents, which are intelligent control programs running on computers and robots, obtain high autonomy so that they can operate in various fields without pre-defined knowledge. However, cooperation/coordination between agents is sophisticated and complicated to implement. We focus on the ACL which is time length from starting patrol to returning to charging base for cooperative patrol when agents like robots have batteries with limited capacity. Long ACL enable agent to visit distant location, but it requires long rest. The basic idea of our method is that if agents have long-life batteries, they can appropriately shorten the ACL by frequently recharging. Appropriate ACL depends on many elements such as environmental size, the number of agents, and workload in an environment. Therefore, we propose a method in which agents autonomously learn the appropriate ACL on the basis of the number of events detected per cycle. We experimentally indicate that our agents are able to learn appropriate ACL depending on established spatial divisional cooperation.

Original languageEnglish
Title of host publicationICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence
EditorsAna Rocha, Luc Steels, Jaap van den Herik
PublisherSciTePress
Pages62-71
Number of pages10
ISBN (Electronic)9789897583506
Publication statusPublished - 2019 Jan 1
Event11th International Conference on Agents and Artificial Intelligence, ICAART 2019 - Prague, Czech Republic
Duration: 2019 Feb 192019 Feb 21

Publication series

NameICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence
Volume1

Conference

Conference11th International Conference on Agents and Artificial Intelligence, ICAART 2019
CountryCzech Republic
CityPrague
Period19/2/1919/2/21

Fingerprint

Robots
Intelligent control
Sensors

Keywords

  • Battery Limitation
  • Continuous Cooperative Patrol Problem
  • Cycle Learning
  • Division of Labor
  • Multi-agent

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Sugiyama, A., Wu, L., & Sugawara, T. (2019). Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems. In A. Rocha, L. Steels, & J. van den Herik (Eds.), ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence (pp. 62-71). (ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence; Vol. 1). SciTePress.

Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems. / Sugiyama, Ayumi; Wu, Lingying; Sugawara, Toshiharu.

ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. ed. / Ana Rocha; Luc Steels; Jaap van den Herik. SciTePress, 2019. p. 62-71 (ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence; Vol. 1).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sugiyama, A, Wu, L & Sugawara, T 2019, Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems. in A Rocha, L Steels & J van den Herik (eds), ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence, vol. 1, SciTePress, pp. 62-71, 11th International Conference on Agents and Artificial Intelligence, ICAART 2019, Prague, Czech Republic, 19/2/19.
Sugiyama A, Wu L, Sugawara T. Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems. In Rocha A, Steels L, van den Herik J, editors, ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. SciTePress. 2019. p. 62-71. (ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence).
Sugiyama, Ayumi ; Wu, Lingying ; Sugawara, Toshiharu. / Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems. ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence. editor / Ana Rocha ; Luc Steels ; Jaap van den Herik. SciTePress, 2019. pp. 62-71 (ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence).
@inproceedings{70f2b25bcdee47c1beef0f3b1b433a78,
title = "Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems",
abstract = "We propose a learning method that decides the appropriate activity cycle length (ACL) according to environmental characteristics and other agents' behavior in the (multi-agent) continuous cooperative patrol problem. With recent advances in computer and sensor technologies, agents, which are intelligent control programs running on computers and robots, obtain high autonomy so that they can operate in various fields without pre-defined knowledge. However, cooperation/coordination between agents is sophisticated and complicated to implement. We focus on the ACL which is time length from starting patrol to returning to charging base for cooperative patrol when agents like robots have batteries with limited capacity. Long ACL enable agent to visit distant location, but it requires long rest. The basic idea of our method is that if agents have long-life batteries, they can appropriately shorten the ACL by frequently recharging. Appropriate ACL depends on many elements such as environmental size, the number of agents, and workload in an environment. Therefore, we propose a method in which agents autonomously learn the appropriate ACL on the basis of the number of events detected per cycle. We experimentally indicate that our agents are able to learn appropriate ACL depending on established spatial divisional cooperation.",
keywords = "Battery Limitation, Continuous Cooperative Patrol Problem, Cycle Learning, Division of Labor, Multi-agent",
author = "Ayumi Sugiyama and Lingying Wu and Toshiharu Sugawara",
year = "2019",
month = "1",
day = "1",
language = "English",
series = "ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence",
publisher = "SciTePress",
pages = "62--71",
editor = "Ana Rocha and Luc Steels and {van den Herik}, Jaap",
booktitle = "ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence",

}

TY - GEN

T1 - Learning of activity cycle length based on battery limitation in multi-agent continuous cooperative patrol problems

AU - Sugiyama, Ayumi

AU - Wu, Lingying

AU - Sugawara, Toshiharu

PY - 2019/1/1

Y1 - 2019/1/1

N2 - We propose a learning method that decides the appropriate activity cycle length (ACL) according to environmental characteristics and other agents' behavior in the (multi-agent) continuous cooperative patrol problem. With recent advances in computer and sensor technologies, agents, which are intelligent control programs running on computers and robots, obtain high autonomy so that they can operate in various fields without pre-defined knowledge. However, cooperation/coordination between agents is sophisticated and complicated to implement. We focus on the ACL which is time length from starting patrol to returning to charging base for cooperative patrol when agents like robots have batteries with limited capacity. Long ACL enable agent to visit distant location, but it requires long rest. The basic idea of our method is that if agents have long-life batteries, they can appropriately shorten the ACL by frequently recharging. Appropriate ACL depends on many elements such as environmental size, the number of agents, and workload in an environment. Therefore, we propose a method in which agents autonomously learn the appropriate ACL on the basis of the number of events detected per cycle. We experimentally indicate that our agents are able to learn appropriate ACL depending on established spatial divisional cooperation.

AB - We propose a learning method that decides the appropriate activity cycle length (ACL) according to environmental characteristics and other agents' behavior in the (multi-agent) continuous cooperative patrol problem. With recent advances in computer and sensor technologies, agents, which are intelligent control programs running on computers and robots, obtain high autonomy so that they can operate in various fields without pre-defined knowledge. However, cooperation/coordination between agents is sophisticated and complicated to implement. We focus on the ACL which is time length from starting patrol to returning to charging base for cooperative patrol when agents like robots have batteries with limited capacity. Long ACL enable agent to visit distant location, but it requires long rest. The basic idea of our method is that if agents have long-life batteries, they can appropriately shorten the ACL by frequently recharging. Appropriate ACL depends on many elements such as environmental size, the number of agents, and workload in an environment. Therefore, we propose a method in which agents autonomously learn the appropriate ACL on the basis of the number of events detected per cycle. We experimentally indicate that our agents are able to learn appropriate ACL depending on established spatial divisional cooperation.

KW - Battery Limitation

KW - Continuous Cooperative Patrol Problem

KW - Cycle Learning

KW - Division of Labor

KW - Multi-agent

UR - http://www.scopus.com/inward/record.url?scp=85064628024&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064628024&partnerID=8YFLogxK

M3 - Conference contribution

T3 - ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence

SP - 62

EP - 71

BT - ICAART 2019 - Proceedings of the 11th International Conference on Agents and Artificial Intelligence

A2 - Rocha, Ana

A2 - Steels, Luc

A2 - van den Herik, Jaap

PB - SciTePress

ER -