arXiv Analytics

Sign in

arXiv:1809.05074 [cs.LG]AbstractReferencesReviewsResources

Derivative-free online learning of inverse dynamics models

Diego Romeres, Mattia Zorzi, Raffaello Camoriano, Silvio Traversaro, Alessandro Chiuso

Published 2018-09-13Version 1

This paper discusses online algorithms for inverse dynamics modelling in robotics. Several model classes including rigid body dynamics (RBD) models, data-driven models and semiparametric models (which are a combination of the previous two classes) are placed in a common framework. While model classes used in the literature typically exploit joint velocities and accelerations, which need to be approximated resorting to numerical differentiation schemes, in this paper a new `derivative-free' framework is proposed that does not require this preprocessing step. An extensive experimental study with real data from the right arm of the iCub robot is presented, comparing different model classes and estimation procedures, showing that the proposed `derivative-free' methods outperform existing methodologies.

Related articles:
arXiv:1301.2609 [cs.LG] (Published 2013-01-11, updated 2014-02-03)
Learning to Optimize Via Posterior Sampling