By exploiting an a priori estimate of the dynamic model of a manipulator, it is possible to command joint torques which ideally realize a Feedback Linearization (FL) controller. The exact cancellation may nevertheless not be achieved due to model uncertainties and possible errors in the estimation of the dynamic coefficients. In this work, an online learning scheme for control based on FL is presented. By reading joint positions and joint velocities information only (without the use of any torque measurement), we are able to learn those model uncertain- ties and thus achieve perfect FL control. Simulations results on the popular KUKA LWR iiwa robot are reported to show the quality of the proposed approach.

An online learning procedure for feedback linearization control without torque measurements / Capotondi, Marco; Turrisi, Giulio; Gaz, Claudio Roberto; Modugno, Valerio; Oriolo, Giuseppe; De Luca, Alessandro. - 100(2019), pp. 1359-1368. ((Intervento presentato al convegno 2019 Conference on Robot Learning tenutosi a Osaka; Japan.

An online learning procedure for feedback linearization control without torque measurements

Marco Capotondi;Giulio Turrisi;Claudio Gaz;Valerio Modugno;Giuseppe Oriolo
;
Alessandro De Luca
2019

Abstract

By exploiting an a priori estimate of the dynamic model of a manipulator, it is possible to command joint torques which ideally realize a Feedback Linearization (FL) controller. The exact cancellation may nevertheless not be achieved due to model uncertainties and possible errors in the estimation of the dynamic coefficients. In this work, an online learning scheme for control based on FL is presented. By reading joint positions and joint velocities information only (without the use of any torque measurement), we are able to learn those model uncertain- ties and thus achieve perfect FL control. Simulations results on the popular KUKA LWR iiwa robot are reported to show the quality of the proposed approach.
File allegati a questo prodotto
File Dimensione Formato  
Capotondi_An-Online-Learning_2019.pdf

accesso aperto

Note: http://proceedings.mlr.press/v100/capotondi20a.html
Tipologia: Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza: Tutti i diritti riservati (All rights reserved)
Dimensione 1.17 MB
Formato Adobe PDF
1.17 MB Adobe PDF Visualizza/Apri PDF

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11573/1396028
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact