TY - GEN
T1 - Fast modeling and identification of robot dynamics using the lasso
AU - Wang, Cong
AU - Yu, Xiaowen
AU - Tomizuka, Masayoshi
PY - 2013
Y1 - 2013
N2 - This paper presents an approach for fast modeling and identification of robot dynamics. By using a data-driven machine learning approach, the process is simplified considerably from the conventional analytical method. Regressor selection using the Lasso (l1-norm penalized least squares regression) is used. The method is explained with a simple example of a two-link direct-drive robot. Further demonstration is given by applying the method to a three-link belt-driven robot. Promising result has been demonstrated.
AB - This paper presents an approach for fast modeling and identification of robot dynamics. By using a data-driven machine learning approach, the process is simplified considerably from the conventional analytical method. Regressor selection using the Lasso (l1-norm penalized least squares regression) is used. The method is explained with a simple example of a two-link direct-drive robot. Further demonstration is given by applying the method to a three-link belt-driven robot. Promising result has been demonstrated.
UR - http://www.scopus.com/inward/record.url?scp=84902375453&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84902375453&partnerID=8YFLogxK
U2 - 10.1115/DSCC2013-3767
DO - 10.1115/DSCC2013-3767
M3 - Conference contribution
AN - SCOPUS:84902375453
SN - 9780791856147
T3 - ASME 2013 Dynamic Systems and Control Conference, DSCC 2013
BT - Nonlinear Estimation and Control; Optimization and Optimal Control; Piezoelectric Actuation and Nanoscale Control; Robotics and Manipulators; Sensing;
PB - American Society of Mechanical Engineers (ASME)
T2 - ASME 2013 Dynamic Systems and Control Conference, DSCC 2013
Y2 - 21 October 2013 through 23 October 2013
ER -