Online semi-parametric learning for inverse dynamics modeling

TL;DR

This paper introduces an online semi-parametric learning algorithm for robot inverse dynamics that combines physical equations with kernel-based methods, validated on real iCub robot data.

Contribution

It proposes a novel semi-parametric approach for online inverse dynamics modeling, integrating parametric physics-based models with non-parametric kernel methods.

Findings

The method outperforms existing approaches on real robot data.

Hyperparameter estimation via marginal likelihood improves model accuracy.

The approach effectively combines physics and data-driven modeling.

Abstract

This paper presents a semi-parametric algorithm for online learning of a robot inverse dynamics model. It combines the strength of the parametric and non-parametric modeling. The former exploits the rigid body dynamics equa- tion, while the latter exploits a suitable kernel function. We provide an extensive comparison with other methods from the literature using real data from the iCub humanoid robot. In doing so we also compare two different techniques, namely cross validation and marginal likelihood optimization, for estimating the hyperparameters of the kernel function.