Indirect robot model learning for tracking control |
| |
Authors: | Botond Bócsi Lehel Csató Jan Peters |
| |
Affiliation: | 1. Faculty of Mathematics and Informatics, Babe?-Bolyai University, Kogalniceanu 1, 400084 Cluj-Napoca, Romania.bboti@cs.ubbcluj.ro;3. Faculty of Mathematics and Informatics, Babe?-Bolyai University, Kogalniceanu 1, 400084 Cluj-Napoca, Romania.;4. Technische Universitaet Darmstadt, Intelligent Autonomous Systems Group, Hochschulstr. 10, 64289 Darmstadt, Germany.;5. Max Planck Institute for Intelligent Systems, Spemannstr. 38, 7206 Tuebingen, Germany. |
| |
Abstract: | Learning task-space tracking control on redundant robot manipulators is an important but difficult problem. A main difficulty is the non-uniqueness of the solution: a task-space trajectory has multiple joint-space trajectories associated, therefore averaging over non-convex solution space needs to be done if treated as a regression problem. A second class of difficulties arise for those robots when the physical model is either too complex or even not available. In this situation machine learning methods may be a suitable alternative to classical approaches. We propose a learning framework for tracking control that is applicable for underactuated or non-rigid robots where an analytical physical model of the robot is unavailable. The proposed framework builds on the insight that tracking problems are well defined in the joint task- and joint-space coordinates and consequently predictions can be obtained via local optimization. Physical experiments show that state-of-the art accuracy can be achieved in both online and offline tracking control learning. Furthermore, we show that the presented method is capable of controlling underactuated robot architectures as well. |
| |
Keywords: | computational intelligence (neural fuzzy learning etc ) robot design modeling planning control |
|
|