Experimental Robot Inverse Dynamics Identification Using Classical and Machine Learning Techniques

Inhalt:
This paper shows the experimental identification of the inverse dynamics model of a KUKA iiwa lightweight robot. We use experimental data from optimal identification experiments to evaluate and compare two different identification approaches: a classical method using a parametrized robot dynamical model and a machine learning method. Both methods accurately estimate the dynamics model and this paper will discuss the pros and cons of each method.