Adaptive Neural Compensator for Robotic Systems Control

In the area of robotics systems, there are numerous applications where robots are expected to move rapidly from one place to another, or follow desired trajectories while maintaining good dynamic behavior. However, certain non-linearities, uncertainties in dynamics and external perturbations make the design of ideal controllers a complicated task in many situations. In this paper, we propose a control scheme that combines a nominal feedback controller with a classical PD and a robust adaptive compensator based on artificial neural networks. Using this control scheme, it is possible to obtain a fully tuned compensation parameters and a strong robustness with respect to uncertain dynamics and different non-linearities, as well as to keep the output tracking error bounded to values close to zero. In order to show the performance of the proposed technique, a SCARA (Selective Compliant Articulated Robot Arm) type robot with two degrees of freedom is considered in this case; but this control proposal can be applied to different systems with dynamic variations. The efficiency and performance of the control law is demonstrated through simulation results and the stability analysis is carried out using Lyapunov's theory.

[1]  Lee jong-shin A Compensation Control Method Using Neural Network for Mechanical Deflection Error in SCARA Robot with Random Payload , 2011 .

[2]  Carlos Miguel Soria,et al.  Self-tuning of a Neuro-Adaptive PID Controller for a SCARA Robot Based on Neural Network , 2018, IEEE Latin America Transactions.

[3]  Frank L. Lewis,et al.  Robot Manipulator Control: Theory and Practice , 2003 .

[4]  Javier Moreno-Valenzuela,et al.  Tracking of periodic oscillations in an underactuated system via adaptive neural networks , 2018 .

[5]  Shuai Li,et al.  Kinematic Control of Redundant Robot Arms Using Neural Networks , 2019 .

[6]  Miroslaw Galicki An Adaptive Regulator of Robotic Manipulators in the Task Space , 2008, IEEE Transactions on Automatic Control.

[7]  F. G. Rossomando,et al.  Adaptive Neural Sliding Mode Control in Discrete Time for a SCARA robot arm , 2016, IEEE Latin America Transactions.

[8]  Vu Thi Yen,et al.  Robust Adaptive Sliding Mode Neural Networks Control for Industrial Robot Manipulators , 2019, International Journal of Control, Automation and Systems.

[9]  Surendra Kumar,et al.  Dynamic Control of Three-Link SCARA Manipulator using Adaptive Neuro Fuzzy Inference System , 2008, 2008 IEEE International Conference on Networking, Sensing and Control.

[11]  Francisco G. Rossomando,et al.  Discrete-time sliding mode neuro-adaptive controller for SCARA robot arm , 2017, Neural Computing and Applications.

[12]  Rajneesh Sharma,et al.  A Markov Game-Adaptive Fuzzy Controller for Robot Manipulators , 2008, IEEE Transactions on Fuzzy Systems.

[13]  G. G. Stokes "J." , 1890, The New Yale Book of Quotations.

[14]  Javier Moreno-Valenzuela,et al.  Two adaptive control strategies for trajectory tracking of the inertia wheel pendulum: neural networks vis à vis model regressor , 2017, Intell. Autom. Soft Comput..

[15]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[16]  Ricardo O. Carelli,et al.  Sliding mode Neuro-adaptive controller designed in discrete Time for Mobile robots , 2018, Mechatron. Syst. Control..

[17]  Jing Na,et al.  Adaptive neural network control for robotic manipulators with guaranteed finite-time convergence , 2019, Neurocomputing.

[18]  Javier Moreno-Valenzuela,et al.  Adaptive Neural Network Control for the Trajectory Tracking of the Furuta Pendulum , 2016, IEEE Transactions on Cybernetics.