Hybrid autonomous control for multi mobile robots

Kazuyuki Ito, Akio Gofuku

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Reinforcement learning can be an adaptive and flexible control method for autonomous system. It does not need a priori knowledge; behaviors to accomplish given tasks are obtained automatically by repeating trial and error. However, with increasing complexity of the system, the learning costs are increased exponentially. Thus, application to complex systems, like a many redundant d.o.f. robot and multi-agent system, is very difficult. In the previous works in this field, applications were restricted to simple robots and small multi-agent systems, and because of restricted functions of the simple systems that have less redundancy, effectiveness of reinforcement learning is restricted. In our previous works, we had taken these problems into consideration and had proposed new reinforcement learning algorithm, 'Q-learning with dynamic structuring of exploration space based on GA (QDSEGA)'. Effectiveness of QDSEGA for redundant robots has been demonstrated using a 12-legged robot and a 50-link manipulator. However, previous works on QDSEGA were restricted to redundant robots and it was impossible to apply it to multi mobile robots. In this paper, we extend our previous work on QDSEGA by combining a rule-based distributed control and propose a hybrid autonomous control method for multi mobile robots. To demonstrate the effectiveness of the proposed method, simulations of a transportation task by 10 mobile robots are carried out. As a result, effective behaviors have been obtained.

Original languageEnglish
Pages (from-to)83-99
Number of pages17
JournalAdvanced Robotics
Volume18
Issue number1
DOIs
Publication statusPublished - 2004

Fingerprint

Mobile robots
Robots
Reinforcement learning
Multi agent systems
Learning algorithms
Manipulators
Redundancy
Large scale systems
Costs

Keywords

  • Autonomous control
  • Multi mobile robots
  • QDSEGA
  • Redundant system
  • Reinforcement learning

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Hybrid autonomous control for multi mobile robots. / Ito, Kazuyuki; Gofuku, Akio.

In: Advanced Robotics, Vol. 18, No. 1, 2004, p. 83-99.

Research output: Contribution to journalArticle

Ito, Kazuyuki ; Gofuku, Akio. / Hybrid autonomous control for multi mobile robots. In: Advanced Robotics. 2004 ; Vol. 18, No. 1. pp. 83-99.
@article{69c18c745976490ea8a75a2eda67df89,
title = "Hybrid autonomous control for multi mobile robots",
abstract = "Reinforcement learning can be an adaptive and flexible control method for autonomous system. It does not need a priori knowledge; behaviors to accomplish given tasks are obtained automatically by repeating trial and error. However, with increasing complexity of the system, the learning costs are increased exponentially. Thus, application to complex systems, like a many redundant d.o.f. robot and multi-agent system, is very difficult. In the previous works in this field, applications were restricted to simple robots and small multi-agent systems, and because of restricted functions of the simple systems that have less redundancy, effectiveness of reinforcement learning is restricted. In our previous works, we had taken these problems into consideration and had proposed new reinforcement learning algorithm, 'Q-learning with dynamic structuring of exploration space based on GA (QDSEGA)'. Effectiveness of QDSEGA for redundant robots has been demonstrated using a 12-legged robot and a 50-link manipulator. However, previous works on QDSEGA were restricted to redundant robots and it was impossible to apply it to multi mobile robots. In this paper, we extend our previous work on QDSEGA by combining a rule-based distributed control and propose a hybrid autonomous control method for multi mobile robots. To demonstrate the effectiveness of the proposed method, simulations of a transportation task by 10 mobile robots are carried out. As a result, effective behaviors have been obtained.",
keywords = "Autonomous control, Multi mobile robots, QDSEGA, Redundant system, Reinforcement learning",
author = "Kazuyuki Ito and Akio Gofuku",
year = "2004",
doi = "10.1163/156855304322753317",
language = "English",
volume = "18",
pages = "83--99",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",
number = "1",

}

TY - JOUR

T1 - Hybrid autonomous control for multi mobile robots

AU - Ito, Kazuyuki

AU - Gofuku, Akio

PY - 2004

Y1 - 2004

N2 - Reinforcement learning can be an adaptive and flexible control method for autonomous system. It does not need a priori knowledge; behaviors to accomplish given tasks are obtained automatically by repeating trial and error. However, with increasing complexity of the system, the learning costs are increased exponentially. Thus, application to complex systems, like a many redundant d.o.f. robot and multi-agent system, is very difficult. In the previous works in this field, applications were restricted to simple robots and small multi-agent systems, and because of restricted functions of the simple systems that have less redundancy, effectiveness of reinforcement learning is restricted. In our previous works, we had taken these problems into consideration and had proposed new reinforcement learning algorithm, 'Q-learning with dynamic structuring of exploration space based on GA (QDSEGA)'. Effectiveness of QDSEGA for redundant robots has been demonstrated using a 12-legged robot and a 50-link manipulator. However, previous works on QDSEGA were restricted to redundant robots and it was impossible to apply it to multi mobile robots. In this paper, we extend our previous work on QDSEGA by combining a rule-based distributed control and propose a hybrid autonomous control method for multi mobile robots. To demonstrate the effectiveness of the proposed method, simulations of a transportation task by 10 mobile robots are carried out. As a result, effective behaviors have been obtained.

AB - Reinforcement learning can be an adaptive and flexible control method for autonomous system. It does not need a priori knowledge; behaviors to accomplish given tasks are obtained automatically by repeating trial and error. However, with increasing complexity of the system, the learning costs are increased exponentially. Thus, application to complex systems, like a many redundant d.o.f. robot and multi-agent system, is very difficult. In the previous works in this field, applications were restricted to simple robots and small multi-agent systems, and because of restricted functions of the simple systems that have less redundancy, effectiveness of reinforcement learning is restricted. In our previous works, we had taken these problems into consideration and had proposed new reinforcement learning algorithm, 'Q-learning with dynamic structuring of exploration space based on GA (QDSEGA)'. Effectiveness of QDSEGA for redundant robots has been demonstrated using a 12-legged robot and a 50-link manipulator. However, previous works on QDSEGA were restricted to redundant robots and it was impossible to apply it to multi mobile robots. In this paper, we extend our previous work on QDSEGA by combining a rule-based distributed control and propose a hybrid autonomous control method for multi mobile robots. To demonstrate the effectiveness of the proposed method, simulations of a transportation task by 10 mobile robots are carried out. As a result, effective behaviors have been obtained.

KW - Autonomous control

KW - Multi mobile robots

KW - QDSEGA

KW - Redundant system

KW - Reinforcement learning

UR - http://www.scopus.com/inward/record.url?scp=1642341910&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=1642341910&partnerID=8YFLogxK

U2 - 10.1163/156855304322753317

DO - 10.1163/156855304322753317

M3 - Article

AN - SCOPUS:1642341910

VL - 18

SP - 83

EP - 99

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

IS - 1

ER -