A random forest application to contact-state classification for robot programming by human demonstration

e-Archivo Repository

Show simple item record

dc.contributor.author Cabras, Stefano
dc.contributor.author Castellanos, M. E.
dc.contributor.author Staffetti, E.
dc.date.accessioned 2021-07-07T10:02:04Z
dc.date.available 2021-07-07T10:02:04Z
dc.date.issued 2016-03
dc.identifier.bibliographicCitation Cabras, S., Castellanos, M. E. & Staffetti, E. (2016). A random forest application to contact-state classification for robot programming by human demonstration. Applied Stochastic Models in Business and Industry, 32(2), pp. 209–227.
dc.identifier.issn 1524-1904
dc.identifier.uri http://hdl.handle.net/10016/33014
dc.description.abstract This paper addresses the non-parametric estimation of the stochastic process related to the classification problem that arises in robot programming by demonstration of compliant motion tasks. Robot programming by demonstration is a robot programming paradigm in which a human operator demonstrates the task to be performed by the robot. In such demonstration, several observable variables, such as velocities and forces can be modeled, non-parametrically, in order to classify the current state of a contact between an object manipulated by the robot and the environment in which it operates. Essential actions in compliant motion tasks are the contacts that take place, and therefore, it is important to understand the sequence of contact states made during a demonstration, called contact classification. We propose a contact classification algorithm based on the random forest algorithm. The main advantage of this approach is that it does not depend on the geometric model of the objects involved in the demonstration. Moreover, it does not rely on the kinestatic model of the contact interactions. The comparison with state-of-the-art contact classifiers shows that random forest classifier is more accurate.
dc.description.sponsorship Stefano Cabras and María Eugenia Castellanos have been partially supported by Ministerio de Ciencia e Innovación grants MTM2013-42323, ECO2012-38442, RYC-2012-11455, by Ministero dell'Istruzione, dell'Univesità e della Ricerca of Italy and by Regione Autonoma della SardegnaCRP-59903. Ernesto Staffetti have been partially supported by the project TRA2013-47619-C2-2-R of theSpanish Ministerio de Economía y Competitividad (2014-2016).
dc.format.extent 19
dc.language.iso eng
dc.publisher Wiley
dc.rights © 2015 John Wiley & Sons, Ltd.
dc.subject.other Multi-class contact classification
dc.subject.other Sensor force analysis
dc.subject.other Supervised learning
dc.title A random forest application to contact-state classification for robot programming by human demonstration
dc.type article
dc.subject.eciencia Estadística
dc.subject.eciencia Robótica e Informática Industrial
dc.identifier.doi https://doi.org/10.1002/asmb.2145
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. ECO2012-38442
dc.relation.projectID Gobierno de España. RYC-2012-11455
dc.relation.projectID Gobierno de España. MTM2013-42323
dc.type.version acceptedVersion
dc.identifier.publicationfirstpage 209
dc.identifier.publicationissue 2
dc.identifier.publicationlastpage 227
dc.identifier.publicationtitle Applied Stochastic Models in Business and Industry
dc.identifier.publicationvolume 32
dc.identifier.uxxi AR/0000017946
dc.contributor.funder Ministerio de Economía y Competitividad (España)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)


This item appears in the following Collection(s)

Show simple item record