Robot learning by a mining tunnel inspection robot

Author

Fenglu Ge ; Moore, William ; Antolovich, Michael ; Junbin Gao

Author_Institution

Sch. of Comput. & Math., Charles Sturt Univ., Bathurst, NSW, Australia

fYear

2012

fDate

26-28 Nov. 2012

Firstpage

200

Lastpage

204

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 Markov Model (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 speed based 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 problems on implementation are discussed.

Keywords

Gaussian processes; control engineering computing; hidden Markov models; inspection; learning by example; mining; service robots; tunnels; DHMM; GMM; Gaussian mixture model; LfD; discrete hidden Markov model; learning from demonstration; learning speed; mining inspection task; mining tunnel inspection robot; robot learning; teaching; training method; Hidden Markov models; Inspection; Kernel; Robot kinematics; Training; Turning; Discrete Hidden Markov Model; Gaussian Mixture Model; Inspection Robot; Learning from Demonstration;

fLanguage

English

Publisher

ieee

Conference_Titel

Ubiquitous Robots and Ambient Intelligence (URAI), 2012 9th International Conference on

Conference_Location

Daejeon

Print_ISBN

978-1-4673-3111-1

Electronic_ISBN

978-1-4673-3110-4

Type

conf

DOI

10.1109/URAI.2012.6462974

Filename

6462974