Back
Sparse online model learning for robot control with support vector regression
The increasing complexity of modern robots makes it prohibitively hard to accurately model such systems as required by many applications. In such cases, machine learning methods offer a promising alternative for approximating such models using measured data. To date, high computational demands have largely restricted machine learning techniques to mostly offline applications. However, making the robots adaptive to changes in the dynamics and to cope with unexplored areas of the state space requires online learning. In this paper, we propose an approximation of the support vector regression (SVR) by sparsification based on the linear independency of training data. As a result, we obtain a method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques, such as nu-SVR, Gaussian process regression (GPR) and locally weighted projection regression (LWPR).
@inproceedings{6066, title = {Sparse online model learning for robot control with support vector regression}, journal = {Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)}, abstract = {The increasing complexity of modern robots makes it prohibitively hard to accurately model such systems as required by many applications. In such cases, machine learning methods offer a promising alternative for approximating such models using measured data. To date, high computational demands have largely restricted machine learning techniques to mostly offline applications. However, making the robots adaptive to changes in the dynamics and to cope with unexplored areas of the state space requires online learning. In this paper, we propose an approximation of the support vector regression (SVR) by sparsification based on the linear independency of training data. As a result, we obtain a method which is applicable in real-time online learning. It exhibits competitive learning accuracy when compared with standard regression techniques, such as nu-SVR, Gaussian process regression (GPR) and locally weighted projection regression (LWPR).}, pages = {3121-3126}, publisher = {IEEE Service Center}, organization = {Max-Planck-Gesellschaft}, institution = {Institute of Electrical and Electronics Engineers}, school = {Biologische Kybernetik}, address = {Piscataway, NJ, USA}, month = oct, year = {2009}, slug = {6066}, author = {Nguyen-Tuong, D. and Sch{\"o}lkopf, B. and Peters, J.}, month_numeric = {10} }