Robot learning by a mining tunnel inspection robot

Feng Lu Ge; Wayne Moore; Michael Antolovich; Junbin Gao

doi:10.1109/URAI.2012.6462974

Robot learning by a mining tunnel inspection robot

Feng Lu Ge, Wayne Moore, Michael Antolovich, Junbin Gao

Research output: Book chapter/Published conference paper › Conference paper › peer-review

2 Citations (Scopus)

Abstract

Learning from Demonstration (LfD) is a method of teaching an agent a task by a number of suitable demonstrations. The agent will then perform the task without any further supervision. In this paper, Discrete Hidden MarkovModel (DHMM) is applied to train a robot for a mining inspection task. An initial training method based on the Gaussian Mixture Model (GMM) was developed and is compared to DHMM. Results show that the learning speedbased on DHMM is faster than the one for GMM and DHMM may prove to be more suitable for the mining inspection task under consideration. The proposed method has already been implemented, and some important problemson implementation are discussed.

Original language	English
Title of host publication	IEEE International Conference on Ubiquitous Robots and Ambient Intelligence
Place of Publication	United States
Publisher	Institute of Electrical and Electronics Engineers
Pages	200-204
Number of pages	5
ISBN (Electronic)	9781467331104
DOIs	https://doi.org/10.1109/URAI.2012.6462974
Publication status	Published - 2012
Event	URAI 2012: 9th International Conference - Daejeon, Korea (South), Korea, Republic of Duration: 26 Nov 2012 → 28 Nov 2012

Conference

Conference	URAI 2012: 9th International Conference
Country/Territory	Korea, Republic of
Period	26/11/12 → 28/11/12

Access to Document

10.1109/URAI.2012.6462974

Cite this

@inproceedings{09e08d329cf64c8dbc1302f1f3696455,

title = "Robot learning by a mining tunnel inspection robot",

abstract = "Learning from Demonstration (LfD) is a method of teaching an agent a task by a number of suitable demonstrations. The agent will then perform the task without any further supervision. In this paper, Discrete Hidden MarkovModel (DHMM) is applied to train a robot for a mining inspection task. An initial training method based on the Gaussian Mixture Model (GMM) was developed and is compared to DHMM. Results show that the learning speedbased on DHMM is faster than the one for GMM and DHMM may prove to be more suitable for the mining inspection task under consideration. The proposed method has already been implemented, and some important problemson implementation are discussed.",

keywords = "Discrete Hidden Markov Model, Gaussian Mixture Model, Inspection Robot, Learning from Demonstration",

author = "Ge, {Feng Lu} and Wayne Moore and Michael Antolovich and Junbin Gao",

note = "Imported on 03 May 2017 - DigiTool details were: publisher = United States: Institute of Electrical and Electronics Engineers, 2012. Event dates (773o) = 26-28 November, 2012; Parent title (773t) = IEEE International Conference on Ubiquitous Robots and Ambient Intelligence.; URAI 2012: 9th International Conference ; Conference date: 26-11-2012 Through 28-11-2012",

year = "2012",

doi = "10.1109/URAI.2012.6462974",

language = "English",

pages = "200--204",

booktitle = "IEEE International Conference on Ubiquitous Robots and Ambient Intelligence",

publisher = "Institute of Electrical and Electronics Engineers",

}

Ge, FL, Moore, W, Antolovich, M & Gao, J 2012, Robot learning by a mining tunnel inspection robot. in IEEE International Conference on Ubiquitous Robots and Ambient Intelligence. Institute of Electrical and Electronics Engineers, United States, pp. 200-204, URAI 2012: 9th International Conference, Korea, Republic of, 26/11/12. https://doi.org/10.1109/URAI.2012.6462974

TY - GEN

T1 - Robot learning by a mining tunnel inspection robot

AU - Ge, Feng Lu

AU - Moore, Wayne

AU - Antolovich, Michael

AU - Gao, Junbin

N1 - Imported on 03 May 2017 - DigiTool details were: publisher = United States: Institute of Electrical and Electronics Engineers, 2012. Event dates (773o) = 26-28 November, 2012; Parent title (773t) = IEEE International Conference on Ubiquitous Robots and Ambient Intelligence.

PY - 2012

Y1 - 2012

N2 - Learning from Demonstration (LfD) is a method of teaching an agent a task by a number of suitable demonstrations. The agent will then perform the task without any further supervision. In this paper, Discrete Hidden MarkovModel (DHMM) is applied to train a robot for a mining inspection task. An initial training method based on the Gaussian Mixture Model (GMM) was developed and is compared to DHMM. Results show that the learning speedbased on DHMM is faster than the one for GMM and DHMM may prove to be more suitable for the mining inspection task under consideration. The proposed method has already been implemented, and some important problemson implementation are discussed.

AB - Learning from Demonstration (LfD) is a method of teaching an agent a task by a number of suitable demonstrations. The agent will then perform the task without any further supervision. In this paper, Discrete Hidden MarkovModel (DHMM) is applied to train a robot for a mining inspection task. An initial training method based on the Gaussian Mixture Model (GMM) was developed and is compared to DHMM. Results show that the learning speedbased on DHMM is faster than the one for GMM and DHMM may prove to be more suitable for the mining inspection task under consideration. The proposed method has already been implemented, and some important problemson implementation are discussed.

KW - Discrete Hidden Markov Model

KW - Gaussian Mixture Model

KW - Inspection Robot

KW - Learning from Demonstration

U2 - 10.1109/URAI.2012.6462974

DO - 10.1109/URAI.2012.6462974

M3 - Conference paper

SP - 200

EP - 204

BT - IEEE International Conference on Ubiquitous Robots and Ambient Intelligence

PB - Institute of Electrical and Electronics Engineers

CY - United States

T2 - URAI 2012: 9th International Conference

Y2 - 26 November 2012 through 28 November 2012

ER -

Robot learning by a mining tunnel inspection robot

Abstract

Conference

Access to Document

Fingerprint

Cite this