A novel control scheme called enhanced super twisting sliding mode-based
chattering-free adaptive neural network controller is proposed in this study to deal with disturbances and uncertainties in controlling a 6-DOF manipulator (ABB IRB 140 robot). In our preliminary study, it can be observed that a high-order and complex dynamic system, like 6-DOF manipulators has shown difficulties in eliminating chattering phenomena, especially in the last joints (the fifth and the sixth joints) even within the use of modern saturation sliding mode term or second order sliding mode control laws. In general, the proposed controller is to use adaptive neural network control and modified second order super twisting sliding mode control to learn and to compensate the uncertainties and disturbances in control. By the use of the proposed enhanced super twisting sliding mode control law, the remaining phenomenon of chattering in the last two joints of the manipulator is completely eliminated as shown in our simulation.
In the approach, a radial basis function neural network is employed to deal with
unknown bounded disturbances and uncertainties. Besides, the controller also has its own output filters and constraints for the output signals for stabilizing those signals before sending to the actuators. In addition, the proposed controller also guarantees the stability of the closed loop system, successfully overcomes the chattering problem, and improves the robustness of the control system. Simulations are conducted to verify the proposed controller performance.
Moreover, the effectiveness of the proposed controlled is also evaluated by
comparing with other existing controllers. From the simulation, it is evident that the proposed controller yields elegant features of sliding mode control including fast response, robustness, and chattering-free control.

A novel control scheme called enhanced super twisting sliding mode-based
chattering-free adaptive neural network controller is proposed in this study to deal with disturbances and uncertainties in controlling a 6-DOF manipulator (ABB IRB 140 robot). In our preliminary study, it can be observed that a high-order and complex dynamic system, like 6-DOF manipulators has shown difficulties in eliminating chattering phenomena, especially in the last joints (the fifth and the sixth joints) even within the use of modern saturation sliding mode term or second order sliding mode control laws. In general, the proposed controller is to use adaptive neural network control and modified second order super twisting sliding mode control to learn and to compensate the uncertainties and disturbances in control. By the use of the proposed enhanced super twisting sliding mode control law, the remaining phenomenon of chattering in the last two joints of the manipulator is completely eliminated as shown in our simulation.
In the approach, a radial basis function neural network is employed to deal with
unknown bounded disturbances and uncertainties. Besides, the controller also has its own output filters and constraints for the output signals for stabilizing those signals before sending to the actuators. In addition, the proposed controller also guarantees the stability of the closed loop system, successfully overcomes the chattering problem, and improves the robustness of the control system. Simulations are conducted to verify the proposed controller performance.
Moreover, the effectiveness of the proposed controlled is also evaluated by
comparing with other existing controllers. From the simulation, it is evident that the proposed controller yields elegant features of sliding mode control including fast response, robustness, and chattering-free control.

[1] M. B. Suarez and R. R. Heredia. “Kinematics, Dynamics and Evaluation of Energy
Consumption for ABB IRB-140 Serial Robots in the Tracking of a Path,” The 2nd
International Congress of Engineering Mechatronics and Automation, October 2013.
[2] M. Almaged. “Forward and Inverse Kinematic Analysis and Validation of the ABB
IRB 140 Industrial Robot,” International Journal of Electronics, Mechanical and
Mechatronics Engineering, vol. 7, pp. 3-9, 2017.
[3] N.V. Truong, L. Chyi-Yeu and S. F. Su. “Adaptive Chattering Free Neural Network
Based Sliding Mode Control for Trajectory Tracking of Redundant Parallel Manipulators,”
Asian Journal of Control, vol. 21, no. 2, pp. 908-923, 2017.
[4] N. Wang, J. C. Sun, M. Han, Z. Zheng, and M. J. Er. “Adaptive approximationbased
regulation control fora class of uncertain nonlinear systems without feedback
linearizability,” IEEE Trans. Neural Netw. Learn. Syst, Vol., No. 99, pp. 1–14, 2017.
[5] Y. Li, S. Tong, L. Liu, and G. Feng. “Adaptive output-feedback control design with
prescribed performance for switched nonlinear systems,” Automatica, vol. 80, pp. 225–231,
2017.
[6] D. Kim, and W. Chung. “Analytic singularity equation and analysis of six-DOF
parallel manipulators using local structurization method,” IEEE Trans. Robot. Autom., vol.
15, no. 4, pp. 612–622, 1999.
[7] M. Boukattaya. “Robust Decoupling Control for Mobile Manipulators Based on
Disturbance Observer,” International Journal of Sciences and Technology of Automatic
control & computer engineering, IJ-STA, vol. 2, no. 2, pp. 670-683, 2008.
[8] F. Zhou, H. Peng, X. Zeng, X. Tian, and J. Wu. “Modeling and control approach to
coupled tanks liquid level system based on function-type weight RBF ARX model,” Asian
J. Control, vol. 19, no. 2, pp. 1–16, 2017.
[9] S. F. Su, C. C. Chuang, C. W. Tao, J. T. Jeng, and C. C. Hsiao. “Radial basis
function networks with linear interval regression weights for symbolic interval data,” IEEE
Trans. Syst. Man. Cybern. B, vol. 42, no. 1, pp. 69–80, 2012.
[10] F. J. Lin, S. G. Chen, and I. F. Sun. “Adaptive backstepping control of six-phase
PMSM using functional link radial basis function network uncertainty observer,” Asian J.
Control, vol. 19, no. 6, pp. 2255–2269, 2017.
[11] W.W. Shang, S. Cong, and S. L. Jiang. “Dynamic model based nonlinear tracking
control of a planar parallel manipulator,” Nonlinear Dyn., vol. 60, no. 4, pp. 597–606, 2010.
44
[12] M.C. Le, S.F. Su, V.T. Nguyen, W.C. Lee, and V.Y. Nguyen. “Adaptive neural
network controller-based chattering-free sliding mode for 6-DOF industrial manipulators,”
IEEE International Conference in Science Systems and Engineering, 2019.
[13] L. Arie. “Sliding order and sliding accuracy in sliding mode control,” International
Journal of Control, vol. 58, no. 6, pp. 1247-1263, 1993.
[14] S. Mahjoub, F. Mnif, Derbel. “Second-order sliding mode approaches for the
control of a class of underactuated systems,” International Journal of Automation and
Computing, vol. 12, no. 2, pp. 134-141, 2015.
[15] ABB website: https://new.abb.com/
[16] Mathlab website: https://www.mathworks.com/products/matlab.html
[17] Mathlab Simulink: https://www.mathworks.com/products/simulink.html