Online semi-parametric learning for inverse dynamics modeling
This work addresses the challenge of improving inverse dynamics modeling for robots, specifically the iCub humanoid, but it appears incremental as it builds on existing semi-parametric and kernel methods.
The paper tackled the problem of online learning for robot inverse dynamics modeling by developing a semi-parametric algorithm that combines parametric and non-parametric approaches, and it provided an extensive comparison with other methods using real data from the iCub humanoid robot.
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.