A reinforcement-learning approach to robot navigation

Mu Chun Su; De Yuan Huang; Chien Hsing Chou; Chen Chiung Hsieh

A reinforcement-learning approach to robot navigation

Mu Chun Su, De Yuan Huang, Chien Hsing Chou, Chen Chiung Hsieh

Department of Computer Science and Information Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

16 Scopus citations

Abstract

This paper presents a reinforcement-learning approach to a navigation system which allows a goal-directed mobile robot to incrementally adapt to an unknown environment. Fuzzy rules which map current sensory inputs to appropriate actions are built through the reinforcement learning. Simulation results illustrate the performance of the proposed navigation system.

Original language	English
Title of host publication	Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control
Pages	665-669
Number of pages	5
State	Published - 2004
Event	Conference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control - Taipei, Taiwan Duration: 21 Mar 2004 → 23 Mar 2004

Publication series

Name	Conference Proceeding - IEEE International Conference on Networking, Sensing and Control
Volume	1

Conference

Conference	Conference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control
Country/Territory	Taiwan
City	Taipei
Period	21/03/04 → 23/03/04

Keywords

Navigation
Neural network
Neuro-fuzzy system
Reinforcement learning
Robot

Cite this

@inproceedings{035f01dd2594434c83877b272998a30d,

title = "A reinforcement-learning approach to robot navigation",

abstract = "This paper presents a reinforcement-learning approach to a navigation system which allows a goal-directed mobile robot to incrementally adapt to an unknown environment. Fuzzy rules which map current sensory inputs to appropriate actions are built through the reinforcement learning. Simulation results illustrate the performance of the proposed navigation system.",

keywords = "Navigation, Neural network, Neuro-fuzzy system, Reinforcement learning, Robot",

author = "Su, {Mu Chun} and Huang, {De Yuan} and Chou, {Chien Hsing} and Hsieh, {Chen Chiung}",

year = "2004",

language = "???core.languages.en_GB???",

isbn = "0780381939",

series = "Conference Proceeding - IEEE International Conference on Networking, Sensing and Control",

pages = "665--669",

booktitle = "Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control",

note = "Conference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control ; Conference date: 21-03-2004 Through 23-03-2004",

}

Su, MC, Huang, DY, Chou, CH & Hsieh, CC 2004, A reinforcement-learning approach to robot navigation. in Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control. Conference Proceeding - IEEE International Conference on Networking, Sensing and Control, vol. 1, pp. 665-669, Conference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control, Taipei, Taiwan, 21/03/04.

A reinforcement-learning approach to robot navigation. / Su, Mu Chun; Huang, De Yuan; Chou, Chien Hsing et al.
Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control. 2004. p. 665-669 (Conference Proceeding - IEEE International Conference on Networking, Sensing and Control; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A reinforcement-learning approach to robot navigation

AU - Su, Mu Chun

AU - Huang, De Yuan

AU - Chou, Chien Hsing

AU - Hsieh, Chen Chiung

PY - 2004

Y1 - 2004

N2 - This paper presents a reinforcement-learning approach to a navigation system which allows a goal-directed mobile robot to incrementally adapt to an unknown environment. Fuzzy rules which map current sensory inputs to appropriate actions are built through the reinforcement learning. Simulation results illustrate the performance of the proposed navigation system.

AB - This paper presents a reinforcement-learning approach to a navigation system which allows a goal-directed mobile robot to incrementally adapt to an unknown environment. Fuzzy rules which map current sensory inputs to appropriate actions are built through the reinforcement learning. Simulation results illustrate the performance of the proposed navigation system.

KW - Navigation

KW - Neural network

KW - Neuro-fuzzy system

KW - Reinforcement learning

KW - Robot

UR - http://www.scopus.com/inward/record.url?scp=2942642050&partnerID=8YFLogxK

M3 - 會議論文篇章

AN - SCOPUS:2942642050

SN - 0780381939

T3 - Conference Proceeding - IEEE International Conference on Networking, Sensing and Control

SP - 665

EP - 669

BT - Conference Proceedings - 2004 IEEE International Conference on Networking, Sensing and Control

T2 - Conference Proceeding - 2004 IEEE International Conference on Networking, Sensing and Control

Y2 - 21 March 2004 through 23 March 2004

ER -

A reinforcement-learning approach to robot navigation

Abstract

Publication series

Conference

Keywords

Fingerprint

Cite this