Abstract
The control of a robotic manipulators is a complicated task due to its high model uncertainties and disturbances. In this research, we study two neural network architectures to control robotic manipulators. The first method consists of using an optimized PD controller combined with a multi-layer perceptron neural network (MLPNN). The second method relies on a combination of MLPNN and a feedforward radial basis function neural network (BBFNN) compensator. Heuristic methods such as genetic optimization and pattern search optimization are used to find the optimal weights for these architectures. Extensive simulations are conducted in MATLAB environment to evaluate the feasibility of the optimized neural controllers in trajectory tracking.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ku, S., Salcudean, S.E.: Design and control of a teleoperated microgripper for microsurgery. In: 1996 Proceedings of IEEE International Conference on Robotics and Automation, Minneapolis, Minnesota, pp. 889–894 (1996)
Liu, Y., Xu, H., Geng, C., Chen, G.: A modular manipulator for industrial applications: design and implement. In: 2017 2nd International Conference on Robotics and Automation Engineering, Shanghai, China, pp. 331–335 (2017)
Tam, T.J., Yang, S.P.: Modeling and control for underwater robotic manipulators - an example. In: 1997 Proceedings of IEEE International Conference on Robotics and Automation, Albuquerque, New Mexico, pp. 2166–2171 (1997)
Wang, J., Mukherji, R., Ficocelli, M., Ogilvie, A., Liu, M., Rice, C.: Modeling and simulation of robotic system for servicing Hubble space telescope. In: 2006 Proceedings of IEEE International Conference on Intelligent Robots and Systems, Beijing, China, pp. 1026–1031
Shi, X., Duan, H.: Novel adaptive robust control for a class of uncertain nonlinear system. In: 2017 IEEE International Conference on Control and Automation, Guangzhou, China, pp. 3046–3050 (2017)
Liaw, H.C., Shirinzadeh, B., Smith, J.: Sliding-mode enhanced adaptive motion tracking control of piezoelectric actuation systems for micro/nano manipulation. IEEE Trans. Control Syst. Technol. 16, 826–833 (2018)
Song, W., Liu, Y., Sun, L.: Model reference adaptive integral-type sliding mode control design for a class of uncertain systems. In: 2006 Proceedings of 6th World Congress on Intelligent Control and Automation, pp. 2056–2060 (2006)
Van, M., Mavrovouniotis, M., Ge, S.S.: An adaptive backstepping nonsingular fast terminal sliding mode control for robust fault tolerant control of robot manipulators. IEEE Trans. Syst. Man Cybern. Syst. 49, 1448–1458 (2019)
Nguyen, V.C., Vo, A.T., Kang, H.J.: A non-singular fast terminal sliding mode control based on third-order sliding mode observer for a class of second-order uncertain nonlinear systems and its application to robot manipulators. IEEE Access 8, 78109–78120 (2020)
Melkote, H., Khorrami, F.: Nonlinear adaptive control of direct-drive brushless DC motors and applications to robotic manipulators. IEEE Trans. Mechatron. 4, 71–81 (1999)
Wang, Z., Jiao, X., Lin, Z.: Sliding model active disturbance rejection control for tip trajectory tracking of spray-painting manipulator. In: 2019 Proceedings of 38th Chinese Control Conference, Guangzhou, China, pp. 4445–4449 (2019)
Saleki, A., Fateh, M.M.: Model free control of electrically driven manipulator by optimized linear extended state observer, based on voltage control strategy. In: Proceedings of International Conference on Robotics and Mechatronics, Tehran, Iran, pp. 548–553 (2018)
Talole, S.E., Kolhe, J.P., Phadke, S.B.: Extended-state-observer-based control of flexible-joint system with experimental validation. IEEE Trans. Ind. Electron. 57, 1411–1419 (2010)
Lu, P., Sandy, T., Buchli, J.: Adaptive unscented kalman filter-based disturbance rejection with application to high precision hydraulic robotic control. In: 2019 IEEE International Conference on Intelligent Robots and Systems, Macau, China, pp. 4365–4372 (2019)
Cortesso, R., Millela, F., Nunes, U.: Joints robust position control using linear kalman filters. In: IEEE International Workshop on Advanced Motion Control, Coimbra, Portugal, pp. 417–422 (1998)
Chen, W.H., Ballance, D.J., Gawthrop, P.J., O’Reilly, J.: A nonlinear disturbance observer for robotic manipulators. IEEE Trans. Ind. Electron. 47, 932–938 (2000)
Chen, W.H.: Disturbance observer based control for nonlinear systems. IEEE Trans. Mechatron. 9, 706–710 (2004)
Chen, W.H., Ballance, D.J., Gawthrop, P.J.: A nonlinear disturbance observer for two link robotic manipulators. In: 1999, Proceedings of 38th Conference on Decision and Control, Phoenix, Arizona USA, pp. 3410–3415 (1999)
Xiao, B., Yin, S., Kaynak, O.: Tracking control of robotic manipulators with uncertain kinematics and dynamics. IEEE Trans. Ind. Electron. 63, 6439–6449 (2016)
Parlos, A.G., Menon, S.K., Atiya, A.F.: Adaptive state estimation using dynamic recurrent neural networks. In: 1999 Proceedings of Joint Conference on Neural Networks, Washington, DC, US, pp. 3361–3364 (1999)
Abdollahi, F., Talebi, H.A., Patel, R.V.: A Stable neural network-based observer with application to flexible-joint manipulators. IEEE Trans. Neural Networks 17, 118–129 (2006)
Yi, S.Y., Chung, M.J.: A robust fuzzy logic controller for robot manipulators with uncertainties. IEEE Trans. Syst. Man Cybern. 27, 706–713 (1997)
Tang, W., Chen, G.: A robust fuzzy PI controller for a flexible-joint robot arm with uncertainties. In: 1994 Proceedings of IEEE 3rd International Conference on Fuzzy Systems, Orlando, FL, pp. 1554–1559 (1994)
Ghalia, M.B., Alouani, A.T.: A robust trajectory tracking control of industrial robot manipulators using fuzzy logic. In: Proceedings of 27th Southeastern Symposium on System Theory, Starkville, MS, USA, pp. 268–271 (1995)
Wei, L.X., Yang, L., Wang, H.R.: Adaptive neural network position/force control of robot manipulators with model uncertainties. In: 2005 International Conference on Neural Networks and Brain, Beijing, pp. 1825–1830 (2005)
Chen, Z., Huang, F., Sun, W., Gu, J.: RBF-neural-network-based adaptive robust control for nonlinear bilateral teleoperation manipulators with uncertainty and time delay. IEEE Trans. Mechatron. 25, 906–918 (2020)
Er, M.J., Gao, Y.: Robust adaptive control of robot manipulators using generalized fuzzy neural networks. IEEE Trans. Ind. Electron. 50, 620–628 (2003)
Ramirez, J.A., Cervantes, I., Bautista, R.: Robust PID control for robots manipulators with elastic joints. In: 2001 Proceedings of IEEE International Conference on Control Applications, Mexico City, Mexico, pp. 542–547 (2001)
Nguyen, V.T., Lin, C.Y., Su, S.F., Tran, Q.V.: Adaptive PID tracking control based radial basic function networks for a 2-DOF parallel manipulator. In: 2017 International Conference on System Science Engineering, Ho Chi Minh City, pp. 309–312 (2017)
Dash, K.K., Choudhury, B.B., Senapati, S.K.: Inverse kinematic solution of 6-DOF industrial robot using nero-fuzzy technology. Int. J. Comput. Syst. Eng. (IJCSYSE) 5(5/6), 333–341 (2019)
Katal, N., Narayan, S.: Optimal design of QFT controller for pneumatic servo actuator system using multi-objective genetic algorithm. Int. J. Adv. Intell. Paradigms (IJAIP) 15(2), 183–206 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
In this section, we present the optimal weight values found using both GA and PS optimization techniques. These weights were used to generate plots in Figs. 3, 4, 5 and 6. First, we present the optimized weights for the MLPNN and RBFNN structure obtained through Pattern Search Optimization. Below, \({W}_{1}\), \({W}_{2}\) and \({W}_{3}\) represent the weights of the first, second and third layers of the MLPNN.
Furthermore, below are the weights, \(W\), for the RBFNN feedforward compensator
We now present the optimized weights for the MLPNN and RBFNN structure obtained through Genetic optimization.
The optimized gains and weights for the Optimized PD based MLPNN structure are presented below. We first however present the GA optimized gains of the PD controller. These were defined as:
After optimizing the weights of the MLPNN through Pattern Search, we define the weights as:
Lastly, after optimizing the weights of the MLPNN through GA, we define the weights as
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cherfouh, K., Gu, J., Farooq, U., Asad, M.U., Qureshi, K.K. (2023). Control of Robotic Manipulator Using Optimized Neural Networks. In: Balas, V.E., Jain, L.C., Balas, M.M., Baleanu, D. (eds) Soft Computing Applications. SOFA 2020. Advances in Intelligent Systems and Computing, vol 1438. Springer, Cham. https://doi.org/10.1007/978-3-031-23636-5_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-23636-5_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-23635-8
Online ISBN: 978-3-031-23636-5
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)