Learning task-space tracking control with kernels
2011
Conference Paper
ei
Task-space tracking control is essential for robot manipulation. In practice, task-space control of redundant robot systems is known to be susceptive to modeling errors. Here, data driven learning methods may present an interesting alternative approach. However, learning models for task-space tracking control from sampled data is an ill-posed problem. In particular, the same input data point can yield many different output values which can form a non-convex solution space. Because the problem is ill-posed, models cannot be learned from such data using common regression methods. While learning of task-space control mappings is globally ill-posed, it has been shown in recent work that it is locally a well-defined problem. In this paper, we use this insight to formulate a local kernel-based learning approach for online model learning for taskspace tracking control. For evaluations, we show in simulation the ability of the method for online model learning for task-space tracking control of redundant robots.
Author(s): | Nguyen-Tuong, D. and Peters, J. |
Pages: | 704-709 |
Year: | 2011 |
Month: | September |
Day: | 0 |
Editors: | Amato, N.M. |
Publisher: | IEEE |
Department(s): | Empirical Inference |
Bibtex Type: | Conference Paper (inproceedings) |
DOI: | 10.1109/IROS.2011.6094428 |
Event Name: | IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011) |
Event Place: | San Francisco, CA, USA |
Address: | Piscataway, NJ, USA |
Digital: | 0 |
ISBN: | 978-1-61284-454-1 |
Links: |
PDF
Web |
BibTex @inproceedings{NguyenTuongP2011_3, title = {Learning task-space tracking control with kernels }, author = {Nguyen-Tuong, D. and Peters, J.}, pages = {704-709 }, editors = {Amato, N.M.}, publisher = {IEEE}, address = {Piscataway, NJ, USA}, month = sep, year = {2011}, doi = {10.1109/IROS.2011.6094428 }, month_numeric = {9} } |