Predicting Task Intent From Surface Electromyography Using Layered Hidden Markov Models

TitlePredicting Task Intent From Surface Electromyography Using Layered Hidden Markov Models
Publication TypeJournal Article
Year of Publication2017
AuthorsRazin, Y., K. Pluckter, J. Ueda, and K. M. Feigh
JournalIEEE Robotics and Automation Letters
Start Page1180
Date Published02/2017
Type of ArticleLetter
Accession Number16712505
KeywordsElectromyography, Feature extraction, Hidden Markov models, Muscles, Service robots, Support vector machines

Human–robot interaction faces the challenge of

designing and modelling tightly coupled and effectively controlled

human–machine systems. The objective of this research is to

learn human operator’s performance characteristics from sur-

face electromyography measurements to predict their intentions

during task operations. For the first time, a Layered Hidden

Markov Model (LHMM) is successfully used with physiological

data from co-contracting arm muscles to achieve accurate intent

prediction. Furthermore, optimal model parameters and high-

performing feature sets are identified and prediction accuracy

at various time horizons calculated. The LHMM outperformed

various other classification methods, including Naive Bayes and

Support Vector Machine, ultimately achieving 82% accuracy in

predicting the next 50 ms window of intent and maintaining 60%

accuracy even after one second. These results hold the promise

of improving robots’ internal model of their human partners,

which could increase the safety and productivity of human-robot

teams in the factories of the future.

Refereed DesignationRefereed
Map of Cognitive Engineering Center

Cognitive Engineering Center (CEC)
Georgia Institute of Technology
270 Ferst Drive
Atlanta GA 30332-0150