Wavelet networks for estimation of coupled friction in robotic manipulators

A wavelet network (WN) friction model has been developed for robots where the friction is coupled, such that it is a function of the velocity of multiple joints. Wavelets have the ability to estimate random friction maps without any prior modeling while preserving linearity in the model parameters. The WN friction model was compared against the Coulomb+viscous (CV) model through experiments with the PHANTOM Omni haptic device (SensAble Technologies, MA, USA); however, the theory is valid for any serial-chain robotic manipulator. Ability to estimate applied motor torques was used as the performance metric, quantified using relative RMS values. During training of the WN model it outperformed the CV model in all cases, with an improvement in relative RMS ranging from 0.4 to 7.5 percentage points, illustrating the potential of the WN friction model. However, during testing of the WN model on an independent data set results were mixed, highlighting the challenge of achieving sufficient training.

[1]  S. Cicero Pinheiro Gomes,et al.  Neuro-fuzzy friction compensation to robotic actuators , 2005 .

[2]  Vincent Hayward,et al.  Single state elastoplastic friction models , 2002, IEEE Trans. Autom. Control..

[3]  Kok Kiong Tan,et al.  Adaptive friction compensation using neural network approximations , 2000, IEEE Trans. Syst. Man Cybern. Part C.

[4]  Jan Tommy Gravdahl,et al.  Modeling and simulation for automatic control , 2002 .

[5]  Antonio Visioli,et al.  Hybrid force/velocity robot contour tracking: an experimental analysis of friction compensation strategies , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[6]  M. Bergamasco,et al.  Dynamic modelling of a class of tendon driven manipulators , 1997, 1997 8th International Conference on Advanced Robotics. Proceedings. ICAR'97.

[7]  R. M. Sanner,et al.  Structurally dynamic wavelet networks for the adaptive control of uncertain robotic systems , 1995, Proceedings of 1995 34th IEEE Conference on Decision and Control.

[8]  Hiroaki Kobayashi,et al.  Adaptive neural network control of tendon-driven mechanisms with elastic tendons , 2003, Autom..

[9]  Rafael Kelly,et al.  A novel global asymptotic stable set-point fuzzy controller with bounded torques for robot manipulators , 2005, IEEE Transactions on Fuzzy Systems.

[10]  S. Nair,et al.  Identification of friction at low velocities using wavelet basis function network , 1998, Proceedings of the 1998 American Control Conference. ACC (IEEE Cat. No.98CH36207).

[11]  K. Hashtrudi-Zaad,et al.  Dynamic parameter identification and analysis of a PHANToM haptic device , 2005, Proceedings of 2005 IEEE Conference on Control Applications, 2005. CCA 2005..

[12]  Steven A. Orszag,et al.  CBMS-NSF REGIONAL CONFERENCE SERIES IN APPLIED MATHEMATICS , 1978 .

[13]  P. Dahl A Solid Friction Model , 1968 .

[14]  Weiping Li,et al.  Applied Nonlinear Control , 1991 .

[15]  Carlos Canudas de Wit,et al.  Adaptive Friction Compensation in Robot Manipulators: Low Velocities , 1991, Int. J. Robotics Res..

[16]  Ingrid Daubechies,et al.  Ten Lectures on Wavelets , 1992 .

[17]  Jan Swevers,et al.  An integrated friction model structure with improved presliding behavior for accurate friction compensation , 1998, IEEE Trans. Autom. Control..

[18]  Carlos Canudas de Wit,et al.  A new model for control of systems with friction , 1995, IEEE Trans. Autom. Control..