Learning tracking control with forward models

Botond Bocsi, Philipp Hennig, Lehel Csato, Jan Peters
2012 2012 IEEE International Conference on Robotics and Automation  
Performing task-space tracking control on redundant robot manipulators is a difficult problem. When the physical model of the robot is too complex or not available, standard methods fail and machine learning algorithms can have advantages. We propose an adaptive learning algorithm for tracking control of underactuated or non-rigid robots where the physical model of the robot is unavailable. The control method is based on the fact that forward models are relatively straightforward to learn and
more » ... cal inversions can be obtained via local optimization. We use sparse online Gaussian process inference to obtain a flexible probabilistic forward model and second order optimization to find the inverse mapping. Physical experiments indicate that this approach can outperform stateof-the-art tracking control algorithms in this context.
doi:10.1109/icra.2012.6224831 dblp:conf/icra/BocsiHCP12 fatcat:wuzem7owwfdgja7xmtjpadiy4a