Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot

Ri Wei Deng, Yin Hao Wang, Chih Jui Lin, Tzuu-Hseng S. Li

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

3 Citations (Scopus)

Abstract

This paper mainly implements human following function for home service robot, May, developed in our laboratory. In order to follow the operator accurately, visual tracking is composed by Tracing-Learning-Detection (TLD) and Kinect skeleton, where TLD plays the role as re-detecting the situation that operator is occluded or disappeared, and Kinect skeleton is adopted to track all other situations while TLD is learning how to enlarge operator image patterns in order to enhance recognition rates. For the sake of improving tracking capability, fuzzy head motion control is added in the visual tracking system to compensate the constraints that the mobile platform of May cannot react rapidly. Every instant movement of the operator can be captured by fuzzy head motion control in real time. Q-learning is applied to discover the pose switching of the mobile platform such that May possesses more robust following ability. By Q-learning, states setting are based on three dimensional position, actions are created by the pose of four wheel independent steering and four wheel independent driven (4WIS4WID) platform, and rewards are established on state transitions. Finally, both the experimental results in the laboratory and competition consequents of Follow Me Mission in robot@home league at RoboCup Japan Open 2013 Tokyo demonstrate that our robot May can fluently switch its poses to follow operator by utilizing the proposed schemes.

Original languageEnglish
Title of host publicationiFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications
PublisherIEEE Computer Society
Pages55-60
Number of pages6
ISBN (Print)9781479903863
DOIs
Publication statusPublished - 2013 Jan 1
EventiFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications - Taipei, Taiwan
Duration: 2013 Dec 62013 Dec 8

Publication series

NameiFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications

Other

OtheriFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications
CountryTaiwan
CityTaipei
Period13-12-0613-12-08

Fingerprint

Service Robot
Q-learning
Motion Control
Motion control
Wheel
Wheels
Robots
Tracing
Operator
Visual Tracking
Skeleton
Robot
Switches
Visual System
Tracking System
State Transition
Reward
Japan
Instant
Switch

All Science Journal Classification (ASJC) codes

  • Applied Mathematics

Cite this

Deng, R. W., Wang, Y. H., Lin, C. J., & Li, T-H. S. (2013). Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot. In iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications (pp. 55-60). [6825409] (iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications). IEEE Computer Society. https://doi.org/10.1109/iFuzzy.2013.6825409
Deng, Ri Wei ; Wang, Yin Hao ; Lin, Chih Jui ; Li, Tzuu-Hseng S. / Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot. iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications. IEEE Computer Society, 2013. pp. 55-60 (iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications).
@inproceedings{fc8f34e077024301987b412a2d6cb3b8,
title = "Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot",
abstract = "This paper mainly implements human following function for home service robot, May, developed in our laboratory. In order to follow the operator accurately, visual tracking is composed by Tracing-Learning-Detection (TLD) and Kinect skeleton, where TLD plays the role as re-detecting the situation that operator is occluded or disappeared, and Kinect skeleton is adopted to track all other situations while TLD is learning how to enlarge operator image patterns in order to enhance recognition rates. For the sake of improving tracking capability, fuzzy head motion control is added in the visual tracking system to compensate the constraints that the mobile platform of May cannot react rapidly. Every instant movement of the operator can be captured by fuzzy head motion control in real time. Q-learning is applied to discover the pose switching of the mobile platform such that May possesses more robust following ability. By Q-learning, states setting are based on three dimensional position, actions are created by the pose of four wheel independent steering and four wheel independent driven (4WIS4WID) platform, and rewards are established on state transitions. Finally, both the experimental results in the laboratory and competition consequents of Follow Me Mission in robot@home league at RoboCup Japan Open 2013 Tokyo demonstrate that our robot May can fluently switch its poses to follow operator by utilizing the proposed schemes.",
author = "Deng, {Ri Wei} and Wang, {Yin Hao} and Lin, {Chih Jui} and Li, {Tzuu-Hseng S.}",
year = "2013",
month = "1",
day = "1",
doi = "10.1109/iFuzzy.2013.6825409",
language = "English",
isbn = "9781479903863",
series = "iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications",
publisher = "IEEE Computer Society",
pages = "55--60",
booktitle = "iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications",
address = "United States",

}

Deng, RW, Wang, YH, Lin, CJ & Li, T-HS 2013, Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot. in iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications., 6825409, iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications, IEEE Computer Society, pp. 55-60, iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications, Taipei, Taiwan, 13-12-06. https://doi.org/10.1109/iFuzzy.2013.6825409

Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot. / Deng, Ri Wei; Wang, Yin Hao; Lin, Chih Jui; Li, Tzuu-Hseng S.

iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications. IEEE Computer Society, 2013. p. 55-60 6825409 (iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications).

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

TY - GEN

T1 - Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot

AU - Deng, Ri Wei

AU - Wang, Yin Hao

AU - Lin, Chih Jui

AU - Li, Tzuu-Hseng S.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - This paper mainly implements human following function for home service robot, May, developed in our laboratory. In order to follow the operator accurately, visual tracking is composed by Tracing-Learning-Detection (TLD) and Kinect skeleton, where TLD plays the role as re-detecting the situation that operator is occluded or disappeared, and Kinect skeleton is adopted to track all other situations while TLD is learning how to enlarge operator image patterns in order to enhance recognition rates. For the sake of improving tracking capability, fuzzy head motion control is added in the visual tracking system to compensate the constraints that the mobile platform of May cannot react rapidly. Every instant movement of the operator can be captured by fuzzy head motion control in real time. Q-learning is applied to discover the pose switching of the mobile platform such that May possesses more robust following ability. By Q-learning, states setting are based on three dimensional position, actions are created by the pose of four wheel independent steering and four wheel independent driven (4WIS4WID) platform, and rewards are established on state transitions. Finally, both the experimental results in the laboratory and competition consequents of Follow Me Mission in robot@home league at RoboCup Japan Open 2013 Tokyo demonstrate that our robot May can fluently switch its poses to follow operator by utilizing the proposed schemes.

AB - This paper mainly implements human following function for home service robot, May, developed in our laboratory. In order to follow the operator accurately, visual tracking is composed by Tracing-Learning-Detection (TLD) and Kinect skeleton, where TLD plays the role as re-detecting the situation that operator is occluded or disappeared, and Kinect skeleton is adopted to track all other situations while TLD is learning how to enlarge operator image patterns in order to enhance recognition rates. For the sake of improving tracking capability, fuzzy head motion control is added in the visual tracking system to compensate the constraints that the mobile platform of May cannot react rapidly. Every instant movement of the operator can be captured by fuzzy head motion control in real time. Q-learning is applied to discover the pose switching of the mobile platform such that May possesses more robust following ability. By Q-learning, states setting are based on three dimensional position, actions are created by the pose of four wheel independent steering and four wheel independent driven (4WIS4WID) platform, and rewards are established on state transitions. Finally, both the experimental results in the laboratory and competition consequents of Follow Me Mission in robot@home league at RoboCup Japan Open 2013 Tokyo demonstrate that our robot May can fluently switch its poses to follow operator by utilizing the proposed schemes.

UR - http://www.scopus.com/inward/record.url?scp=84903590839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84903590839&partnerID=8YFLogxK

U2 - 10.1109/iFuzzy.2013.6825409

DO - 10.1109/iFuzzy.2013.6825409

M3 - Conference contribution

SN - 9781479903863

T3 - iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications

SP - 55

EP - 60

BT - iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications

PB - IEEE Computer Society

ER -

Deng RW, Wang YH, Lin CJ, Li T-HS. Implementation of human following mission by using fuzzy head motion control and Q-learning wheel motion control for home service robot. In iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications. IEEE Computer Society. 2013. p. 55-60. 6825409. (iFUZZY 2013 - 2013 International Conference on Fuzzy Theory and Its Applications). https://doi.org/10.1109/iFuzzy.2013.6825409