Learning Tracking Control with Forward Models
2012
Conference Paper
ei
pn
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 local 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 state-of-the-art tracking control algorithms in this context.
Author(s): | Bócsi, B. and Hennig, P. and Csató, L. and Peters, J. |
Pages: | 259 -264 |
Year: | 2012 |
Month: | May |
Day: | 0 |
Department(s): | Empirical Inference, Probabilistic Numerics |
Bibtex Type: | Conference Paper (inproceedings) |
DOI: | 10.1109/ICRA.2012.6224831 |
Event Name: | IEEE International Conference on Robotics and Automation (ICRA 2012) |
Event Place: | St. Paul, MN, USA |
Digital: | 0 |
Links: |
PDF
Web |
BibTex @inproceedings{BocsiHCP2012, title = {Learning Tracking Control with Forward Models}, author = {Bócsi, B. and Hennig, P. and Csató, L. and Peters, J.}, pages = {259 -264}, month = may, year = {2012}, doi = {10.1109/ICRA.2012.6224831}, month_numeric = {5} } |