Title :
Kernel machines for uncalibrated visual servoing of robots
Author :
Kale, Anup ; Meena, M.L. ; Gopal, M.
Author_Institution :
Dept. of Electr. Eng., IIT Delhi, New Delhi, India
Abstract :
A new modelling method of image Jacobian estimation is presented for uncalibrated visual servoing of robots, in which a kernel recursive least squares (KRLS) technique is used for non-linear mapping between target image features and robot joint angles, and an image Jacobian expression is derived from the KRLS algorithm with gaussian kernel. The simulations of robot visual servoing with eye-in-hand camera configuration are conducted using the KRLS Jacobian estimator and the same are compared with SVR and LS-SVM Jacobian estimators. The simulation results have shown that the robot visual servoing converges at the desired goal and KRLS is proved to be a better choice.
Keywords :
Gaussian processes; Jacobian matrices; feature extraction; least squares approximations; regression analysis; robot vision; support vector machines; visual servoing; Gaussian kernel; KRLS technique; LS-SVM Jacobian estimators; SVR estimators; eye-in-hand camera configuration; image Jacobian estimation; kernel machines; kernel recursive least squares technique; least squares support vector machines; nonlinear mapping; robot joint angles; robot visual servoing; support vector regression; target image features; uncalibrated visual servoing; Accuracy; Jacobian matrices; Jacobian estimation; Kernel Recursive Least Squares; Least Square; Support Vector Machine; Uncalibrated visual servoing;
Conference_Titel :
Intelligent Control (ISIC), 2013 IEEE International Symposium on
Conference_Location :
Hyderabad
DOI :
10.1109/ISIC.2013.6658623
