LGMLSep 13, 2018

Derivative-free online learning of inverse dynamics models

arXiv:1809.05074v137 citations
Originality Incremental advance
AI Analysis

This addresses the challenge of noisy derivative estimation in robotics control, though it appears incremental as it builds on existing model classes within a common framework.

The paper tackles the problem of inverse dynamics modeling in robotics by proposing a derivative-free framework that eliminates the need for numerical differentiation of joint velocities and accelerations. Experimental results on the iCub robot's right arm show that the proposed methods outperform existing approaches.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes