Autonomous Online Learning of Velocity Kinematics on the iCub: a Comparative Study

Abstract : In the last years, several regression algorithms have been proposed to learn accurate mechanical models of robots. Comparisons are proposed at the conceptual level or through the use of recorded databases, but they deliver limited conclusions with respect to the real performance of these algorithms in their true context of use, i.e. online learning on the real robot interacting with its environment, within a feedback control loop. In this paper, we provide an empirical study of three state-of-the-art regression methods through online learning on the iCub robot holding a tool. We show that they can effectively learn a visuo-motor kinematic model for a simple visual servoing task in a very limited time (few minutes), without making any a priori hypothesis on the geometry of the robot and its tool. Furthermore, we can draw from the results some stronger conclusions about the comparison of the algorithms than previous studies based on databases.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [24 references]  Display  Hide  Download
Contributor : Alain Droniou <>
Submitted on : Monday, July 23, 2012 - 10:55:32 AM
Last modification on : Thursday, March 21, 2019 - 2:30:19 PM
Document(s) archivé(s) le : Wednesday, October 24, 2012 - 2:30:44 AM


Files produced by the author(s)


  • HAL Id : hal-00719964, version 1


Alain Droniou, Serena Ivaldi, Vincent Padois, Olivier Sigaud. Autonomous Online Learning of Velocity Kinematics on the iCub: a Comparative Study. IEEE/RSJ International Conference on Intelligent Robots and Systems, Oct 2012, Vilamoura, Portugal. To appear. ⟨hal-00719964⟩



Record views


Files downloads