Hidden Markov models as a process monitor in robotic assembly

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 mode...

Full description

Saved in:

Bibliographic Details
Published in:	Modeling, identification and control identification and control, 1999-10, Vol.20 (4), p.201-223
Main Authors:	HOVLAND, G. E, MCCARRAGHER, B. J
Format:	Article
Language:	eng
Subjects:	Applied sciences Computer science control theory systems Control theory. Systems Discrete event systems Exact sciences and technology Mathematics Probability and statistics Probability theory and stochastic processes Robotics Sciences and techniques of general use sensory perception Special processes (renewal theory, markov renewal processes, semi-markov processes, statistical mechanics type models, applications)
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	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.
ISSN:	0332-7353 1890-1328