Abstract
Greater production and improved safety in the mining industry can be enhanced by the use of automated vehicles. This paper presents results in applying Learning from Demonstration (LfD) to a laboratory semi-automated mine inspection robot following a path through a simulated mine. Three methods, Gaussian Mixture Model (GMM), Continuous Hidden Markov Model (CHMM), and Discrete Hidden Markov Model (DHMM) were used to implement the LfD and a comparison of the implementation results is presented. The results from the different models were then used to implement a novel, optimised path decomposition technique that may be suitable for possible robot use within an underground mine.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Adept robot. http://www.mobilerobots.com/. Accessed: 2014-10-18.
References
Ventilation standards in underground mines. (mines safety bulletin no. 95). Technical report, Department of Mines and Petroleum, WA, Australia, 2011
Draft guide for tunnelling work: Technical report. Safe Work Australia, Canderra, Australia (2012)
Argall, B.D., Chernova, S., Veloso, M., Browning, B.: A survey of robot learning from demonstration. Robot. Autonom. Syst. 57(5), 469–483 (2009)
Aulinas, J., Petillot, Y., Salvi, J., Lladó, X.: The slam problem: a survey. In: Proceedings of the 2008 Conference on Artificial Intelligence Research and Development: Proceedings of the 11th International Conference of the Catalan Association for Artificial Intelligence, pp. 363–371, Amsterdam, The Netherlands, 2008. IOS Press. ISBN 978-1-58603-925-7
Bilmes, J.: A gentle tutorial of the em algorithm and its application to parameter estimation for gaussian mixture and hidden markov models. Technical report, University of Berkeley (1997)
Siciliano, B., Khatib, O. (eds.): Springer Handbook of Robotics. Springer, Heidelberg (2008)
Burgess-Limerick, R., Steiner, L.: Injuries associated with continuous miners, shuttle cars, load-haul-dump and personnel transport in new south wales underground coal mines. Technical report, Office of Mine Safety and Health Research (2006)
Calinon, S., Billard, A.: What is the teacher’s role in robot programming by demonstration? - toward benchmarks for improved learning. Interaction Studies. Special Issue on Psychological Benchmarks in Human-Robot Interaction 8(3) (2007a)
Calinon, S, Billard, A.: Incremental learning of gestures by imitation in a humanoid robot. In: HRI, pp. 255–262 (2007b)
Calinon, S., Billard, A.: Statistical learning by imitation of competing constraints in joint space and task space. Adv. Robot. 23(15), 2059–2076 (2009)
Calinon, S., Guenter, F., Billard, A.: On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans. Syst. Man Cybern. Part B 37(2), 286–298 (2007)
Calinon, S., D’halluin, F., Sauser, E.L., Caldwell, D.G., Billard, A.: Learning and reproduction of gestures by imitation. IEEE Robot. Autom. Mag. 17(2), 44–54 (2010)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the em algorithm. J. Roy. Stat. Soc. Ser. B 39(1), 1–38 (1977)
González, J.C., Martínez, S., Jardón, A., Balaguer, C.: Robot-aided tunnel inspection and maintenance system. In: 26th International Symposium on Automation and Robotics in Construction (ISARC), Austin, TX, USA (2009)
Gosavi, A.: Reinforcement learning: a tutorial survey and recent advances. INFORMS J. Comput. 21(2), 178–192 (2009)
Gunningham, N.: Mine Safety: Law Regulation Policy. Federation Press, Annandale (2007)
Herbrich, R.: Learning Kernel Classifiers: Theory and Algorithms. Adaptive Computation and Machine Learning. The MIT Press, Cambridge (2001)
Hwamg, M., Rosenfeld, R., Theyer, E., Mosur, R., Chase, L., Weide, R., Huang, X., Alleva, F.: Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II. In: IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-94 1994 , vol. 1, pp. 549–552, April 1994
Kaelbling, L.P., Littman, M.L., Moore, A.W.: Reinforcement learning: a survey. J. Artif. Intell. Res. (JAIR) 4, 237–285 (1996)
Kober, J., Bagnell, J.A., Peters, J.: Reinforcement learning in robotics: a survey. Int. J. Robot. Res. 32(11), 1238–1274 (2013)
Kulic, D., Takano, W., Nakamura, Y.: Incremental learning, clustering and hierarchy formation of whole body motion patterns using adaptive hidden Markov chains. I. J. Robot. Res. 27(7), 761–784 (2008)
Ogata, T., Sugano, S., Tani, J.: Open-end human-robot interaction from the dynamical systems perspective: mutual adaptation and incremental learning. Adv. Robot. 19(6), 651–670 (2005)
Rabiner, L.R.: A tutorial on hidden markov models and selected applications in speech recognition. Proc. IEEE 77(2), 257–286 (1989)
Tang, S., Chen, S., Liu, Q., Wang, B., Guo, X.: A small tracked robot for cable tunnel inspection. In: Lee, G. (ed.) Advances in Automation and Robotics, Vol.1. LNEE, vol. 122. Springer, Heidelberg (2011). (ISSN 1876–1119)
Jonathan, T.: Designing to maximize operator visibility in lhd equipment. Technical report, Ontario Natural Resources Safety Association, North Bay, Ontario, Canada (2006)
Vakanski, A., Mantegh, I., Irish, A., Janabi-Sharifi, F.: Trajectory learning for robot programming by demonstration using hidden markov model and dynamic time warping. IEEE Trans. Syst. Man Cybern. Part B: Cybern. 42(4), 1039–1052 (2012)
Yang, J., Yangsheng, X., Chen, C.S.: Hidden Markov model approach to skill learning and its application to telerobotics. IEEE Trans. Robot. Autom. 10(5), 621–631 (1994)
Seung-Nam, Y., Jang, J.-H., Han, C.-S.: Auto inspection system using a mobile robot for detecting concrete cracks in a tunnel. Autom. Constr. 16(3), 255–261 (2007)
Zhuang, F., Zupan, C., Zheng, C., Zhao, Y.: A cable-tunnel inspecting robot for dangerous environment. Int. J. Adv. Robot. Syst. 5(3) (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Ge, F., Moore, W., Antolovich, M. (2015). Learning from Demonstration Using GMM, CHMM and DHMM: A Comparison. In: Pfahringer, B., Renz, J. (eds) AI 2015: Advances in Artificial Intelligence. AI 2015. Lecture Notes in Computer Science(), vol 9457. Springer, Cham. https://doi.org/10.1007/978-3-319-26350-2_18
Download citation
DOI: https://doi.org/10.1007/978-3-319-26350-2_18
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-26349-6
Online ISBN: 978-3-319-26350-2
eBook Packages: Computer ScienceComputer Science (R0)