“Hidden Markov Models as a Process Monitor in Robotic Assembly”

Authors: Geir Hovland and Brenan J. McCarragher,
Affiliation: ABB and Australian National University
Reference: 1999, Vol 20, No 4, pp. 201-223.

Keywords: Discrete event systems, sensory perception, robotic assembly

Abstract: A process monitor for robotic assembly based on hidden Markov models (HMMs) is presented. The HMM process monitor is based on the dynamic force/torque signals arising from interaction between the workpiece and the environment. The HMMs represent a stochastic, knowledge-based system in which the models are trained off-line with the Baum-Welch reestimation algorithm. The assembly task is modeled as a discrete event dynamic system in which a discrete event is defined as a change in contact state between the workpiece and the environment. Our method (1) allows for dynamic motions of the workpiece, (2) accounts for sensor noise and friction, and (3) exploits the fact that the amount of force information is large when there is a sudden change of discrete state in robotic assembly. After the HMMs have been trained, the authors use them on-line in a 2D experimental setup to recognize discrete events as they occur. Successful event recognition with an accuracy as high as 97with a training set size of only 20 examples for each discrete event.

PDF PDF (3465 Kb)        DOI: 10.4173/mic.1999.4.2

DOI forward links to this article:
[1] C. Kwan, X. Zhang, R. Xu and L. Haynes (2003), doi:10.1109/ROBOT.2003.1241660
[2] K.A. Tahboub (2001), doi:10.1109/ROBOT.2001.933023
[3] Knut B. Kaldestad, Geir Hovland and David A. Anisi (2012), doi:10.3182/20120905-3-HR-2030.00059
[4] Shuangqi Luo, Hongmin Wu, Shuangda Duan, Yijiong Lin and Juan Rojas (2021), doi:10.1007/s10846-021-01312-6
References:
[1] ASTUTI, P. (1995). The convergence and control of a class of hybrid dynamic systems, PhD thesis, The Australian National University, Department of Engineering.
[2] BADANO, F. et al (1991). Robotic assembly by slight random movements, Robotica, 9, pp. 23-29 doi:10.1017/S0263574700015538
[3] BICCHI, A., SALISBURY, J.K. BROCK D.L. (1993). Contact sensing from force measurements, Int. J Robotics Research, 1.3, pp. 249-262 doi:10.1177/027836499301200304
[4] CHIACCHIO, P., et al. (1991). Closed loop inverse kinematics schemes for constrained redundant manipulators with task space augmentation and task priority strategy, Int. Robotics Research, 1.4, pp. 410-425 doi:10.1177/027836499101000409
[5] DONALD, B.R. (1990). Planning multi-step error detection and recovery strategies, Int. J. Robotics Research, .1, pp. 3-60 doi:10.1177/027836499000900101
[6] DUTRÉ S., BRUYNINCKX, H. DE SCHUTTER, J. (1996). Contact identification and monitoring based on energy, Proc. 1996 International Conference on Robotics and Automation, pp. 1333-1338..Minneapolis, MN, April 22-28.
[7] EBERMAN, B. SALISBURY, J.K. (1994). Application of change detection to dynamic contact sensing, Int. J. Robotics Research, 1.5, pp. 369-394 doi:10.1177/027836499401300501
[8] HANNAFORD, B. LEE, P. (1991). Hidden Markov model analysis of force/torque information in telemanipulation, Int. J Robotics Research, 1.5, pp. 528-539 doi:10.1177/027836499101000508
[9] HIRAI, S. (1989). Analysis and planning of manipulation using the theory of polyhedral convex cones, PhD thesis, Kyoto University, Department of Applied Mathematics and Physics.
[10] HOVLAND, G.E. MCCARRACHER, B. J. (1996). Sensory perception and dynamic programming, Proc. First Australian Data Fusion Symposium..Adelaide, November 21-22.
[11] HUANG, X.D., ARIKI, Y. JACK, M.A. (1990). Hidden Markov Models for Speech Recognition, Edinburgh: Edinburgh University Press.
[12] HUO, Q. CHAN, C. (1993). The gradient projection method for the training of hidden Markov models, Speech Comm., 13, pp. 307-313 doi:10.1016/0167-6393(93)90029-K
[13] JOHANSSON, R.S. (1978). Tactile sensibility in the human hand: receptive field characteristics of mechanoreceptive units in the glabrous skin area, J. Physiology, 281, pp. 101-123.
[14] MCCARRACHER, B. J. (1996). Task primitives for the discrete event modeling and control of 6-DOF assembly tasks, IEEE Trans. Robotics and Automation, 1.2, pp. 280-289 doi:10.1109/70.488947
[15] MCCARRAGHER, B.J. ASADA, H. (1995). The discrete event control of robotic assembly tasks, ASME J Dyn. Sys. Meas. Control, 11.3, pp. 384-393 doi:10.1115/1.2799129
[16] MCCARRAGHER, B.J. ASADA, H. (1995). The discrete event modelling and trajectory planning of robotic assembly tasks, ASME J. Dyn. Sys. Meas. Control, 11.3, pp. 394-400 doi:10.1115/1.2799130
[17] MCCARRAGHER, B.J. ASADA, H. (1993). Qualitative template matching using dynamic process models for state transition recognition of robotic assembly, ASME J Dyn. Sys. Meas. Control, 11.2A, pp. 261-269 doi:10.1115/1.2899030
[18] PICONE, J. (1990). Continuous speech recognition using hidden Markov models, IEEE ASSP Magazine, .3, pp. 26-41 doi:10.1109/53.54527
[19] RABINER, L.R. JUANG, B.H. (1986). An introduction to hidden Markov models, IEEE ASSP Magazine, .1, pp. 4-16 doi:10.1109/MASSP.1986.1165342
[20] RABINER, L.R. et al. (1985). Recognition of isolated digits using hidden Markov models with continuous mixture densities, ATand&T Technical J., 6.6, pp. 1211-1234.
[21] RABINER, L.R. et al (1985). Some properties of continuous hidden Markov model representations, ATand&T Technical J. 6.6, pp. 1251-1269.
[22] TRINKLE, J.C. ZENG, D.C. (1995). Prediction of the quasistatic planar motion of a contacted rigid body, IEEE Trans. Robotics and Automation, 1.2, pp. 229-246 doi:10.1109/70.370504
[23] VLONTZOS, L.A. KUNG, S.Y. (1992). Hidden Markov models for character recognition, IEEE Trans. Image Processing, .4, pp. 539-543 doi:10.1109/83.199925
[24] YANG, J., XU, Y. CHEN, C.S. (1994). Hidden Markov model approach to skill learning and its application to telerobotics, IEEE Trans. Robotics and Automation, 1.5, pp. 621-631 doi:10.1109/70.326567
[25] XU, Y. YANG, J. (1995). Towards Human-Robot Coordination: Skill Modeling and Transferring via Hidden Markov Model, Proceedings of the IEEE International Conference on Robotics and Automation, Nagoya, Japan, pp. 1906-1911..Nagoya, Japan, May 19-26.
[26] ZHU, Q. (1996). Hidden Markov model for dynamic obstacle avoidance of mobile robot navigation, IEEE Trans. Robotics and Automation, .3, pp. 390-397 doi:10.1109/70.88149


BibTeX:
@article{MIC-1999-4-2,
  title={{Hidden Markov Models as a Process Monitor in Robotic Assembly}},
  author={Hovland, Geir and McCarragher, Brenan J.},
  journal={Modeling, Identification and Control},
  volume={20},
  number={4},
  pages={201--223},
  year={1999},
  doi={10.4173/mic.1999.4.2},
  publisher={Norwegian Society of Automatic Control}
};