Load estimation and control using learned dynamics models Export

@proceedings{citeulike:2860708, abstract = {Classic adaptive control methods for handling varying loads rely on an analytically derived model of the robot's dynamics. However, in many situations, it is not feasible or easy to obtain an accurate analytic model of the robot's dynamics. An alternative to analytically deriving the dynamics is learning the dynamics from movement data. This paper describes a load estimation technique that uses the learned instead of analytically derived dynamics. We study examples where the various inertial parameters of the load are estimated from the learned models, their effectiveness in control is evaluated along with their robustness in light of imperfect, intermediate dynamic models.}, author = {Petkos, G. and Vijayakumar, S.}, booktitle = {Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on}, citeulike-article-id = {2860708}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/IROS.2007.4399373}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4399373}, doi = {10.1109/IROS.2007.4399373}, journal = {Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on}, keywords = {inverse\_dynamics, lwpr}, pages = {1527--1532}, posted-at = {2008-06-04 11:21:45}, priority = {0}, title = {Load estimation and control using learned dynamics models}, url = {http://dx.doi.org/10.1109/IROS.2007.4399373}, year = {2007} }

TY - CONF ID - citeulike:2860708 L3 - citeulike-article-id:2860708 N2 - Classic adaptive control methods for handling varying loads rely on an analytically derived model of the robot's dynamics. However, in many situations, it is not feasible or easy to obtain an accurate analytic model of the robot's dynamics. An alternative to analytically deriving the dynamics is learning the dynamics from movement data. This paper describes a load estimation technique that uses the learned instead of analytically derived dynamics. We study examples where the various inertial parameters of the load are estimated from the learned models, their effectiveness in control is evaluated along with their robustness in light of imperfect, intermediate dynamic models. JF - Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on EP - 1532 TI - Load estimation and control using learned dynamics models T2 - Intelligent Robots and Systems, 2007. IROS 2007. IEEE/RSJ International Conference on SP - 1527 KW - inverse_dynamics KW - lwpr AU - Petkos, G AU - Vijayakumar, S PY - 2007/// UR - http://dx.doi.org/10.1109/IROS.2007.4399373 ER -