Dynamic velocity feed-forward compensation control with RBF-NN system identification for industrial robots

A dynamic velocity feed-forward compensation control (DVFCC) approach with RBF neural network (RBF-NN) dynamic model identification was presented for the adaptive trajectory tracking of industrial robots. The proposed control approach combined the advantages of traditional feedback closed-loop position control and computed torque control based on inverse dynamic model. The feed-forward compensator used a nominal robot dynamics as accurate dynamic model and on-line identification with RBF-NN as uncertain part to improve dynamic modeling accuracy. The proposed compensation was applied as velocity feed-forward by an inverse velocity controller that can convert torque signal into velocity in the standard industrial controller. Then, the need for a torque control interface was avoided in the real-time dynamic control of industrial robot. The simulations and experiments were carried out on a gas cutting manipulator. The results show that the proposed control approach can reduce steady-state error, suppress overshoot and enhance tracking accuracy and efficiency in joint space and Cartesian space, especially under highspeed condition.

[1]  D. Broomhead,et al.  Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks , 1988 .

[2]  Gang Wang.  Approach to improvement of robot trajectory accuracy by dynamic compensation , 2004 .

[3]  Takao Kakizaki,et al.  Dynamic Parameter Identification Of An Industrial Robot And Its Application To Trajectory Controls , 1992, Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  Jan Swevers,et al.  Improving the dynamic accuracy of industrial robots by trajectory pre-compensation , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[5]  Romeo Ortega,et al.  Adaptive motion control of rigid robots: a tutorial , 1988, Proceedings of the 27th IEEE Conference on Decision and Control.

[6]  Philippe Martinet,et al.  A Review on the Dynamic Control of Parallel Kinematic Machines: Theory and Experiments , 2009, Int. J. Robotics Res..

[7]  Bodo Heimann,et al.  Model-based Feedforward Control in Industrial Robotics , 2002, Int. J. Robotics Res..

[8]  Gang Feng.  A compensating scheme for robot tracking based on neural networks , 1995, Robotics Auton. Syst..

[9]  Hanlei Wang,et al.  Adaptive inverse dynamics control of robots with uncertain kinematics and dynamics , 2009, Autom..

[10]  Kang Woong Lee,et al.  Robust control of robot manipulators using dynamic compensator , 2009, 2009 IEEE International Conference on Control and Automation.

[11]  Antonio Visioli,et al.  On the trajectory tracking control of industrial SCARA robot manipulators , 2002, IEEE Trans. Ind. Electron..

[12]  M. Togai,et al.  Learning control and its optimality: Analysis and its application to controlling industrial robots , 1986, Proceedings. 1986 IEEE International Conference on Robotics and Automation.

[13]  J. Y. S. Luh,et al.  On-Line Computational Scheme for Mechanical Manipulators , 1980 .

[14]  Satoru Goto,et al.  Forcefree control with independent compensation for industrial articulated robot arms , 2005 .

[15]  Torgny Brogårdh,et al.  Present and future robot control development - An industrial perspective , 2007, Annu. Rev. Control..

[16]  Zhao-Hui Jiang,et al.  Trajectory tracking control of industrial robot manipulators using a neural network controller , 2007, 2007 IEEE International Conference on Systems, Man and Cybernetics.