Hierarchical Adaptive Control System of a Manipulator Based on the Synthesis of a Neural Network of Fuzzy Inference and an Iterative Refinement Algorithm

Авторы: Ganin P.E., Kobrin A.I. Опубликовано: 13.08.2019
Опубликовано в выпуске: #4(127)/2019  
DOI: 10.18698/0236-3933-2019-4-18-31

Раздел: Информатика, вычислительная техника и управление | Рубрика: Системный анализ, управление и обработка информации  
Ключевые слова: robot manipulator, adaptive control, neural network, fuzzy inference system, iterative refinement, programmable logic controller, electric stepper drive

The main aim of this work is to develop an adaptive control system for a kinematically redundant multilink industrial manipulator. Proposed solution allows to construct a unified real-time control system with the ability to control the accuracy of calculations. In order to achieve the required accuracy of the calculations and the performance of the control system, we propose an algorithm that is based on the so-called hybrid method for finding the solution of the inverse kinematics (IK) problem, including the adaptive neural network and fuzzy inference system with subsequent iterative refinement of numerical solution by the Newton --- Raphson method. The influence of the training sample size on the quality of the obtained initial approximation for the neural network part of the algorithm is described in the paper. The results of experimental studies of the developed hybrid algorithm are presented in comparison with the iterative and neural network methods for three-, five- and eight-link manipulator structures. Paper presents the main steps of the control system synthesis for kinematically redundant industrial manipulator, including the description for developed algorithms for finding an IK solution of multilink structures. The structure of a multi-level hierarchical manipulator control system, based on a programmable logic controller and electric stepping motors with the possibility of integration into the production system at various levels, is presented


[1] Lim K.Y., Eslami M. Robust adaptive controller designs for robot manipulator systems. IEEE J. Robot. Automat., 1987, vol. 3, no. 1, pp. 54--66.DOI: 10.1109/JRA.1987.1087070

[2] Craig J.J., Hsu P., Satry S.S. Adaptive control of mechanical manipulators. IEEE Int. Conf. Robotics and Automation, 1986, pp. 418--432.DOI: 10.1109/ROBOT.1986.1087661

[3] Zenkevich S.L., Yushchenko A.S. Osnovy upravleniya manipulyatsionnymi robotami [Basics of robot control]. Moscow, Bauman MSTU Publ., 2004.

[4] Matyukhin V.I. Upravlenie mekhanicheskimi sistemami [Mechanical systems control]. Moscow, Fizmatlit Publ., 2009.

[5] Chernous’ko F.L., Anan’yevskiy I.M., Reshmin S.A. Metody upravleniya nelineynymi mekhanicheskimi sistemami [Methods for control on nonlinear mechanical systems]. Moscow, Fizmatlit Publ., 2006.

[6] Lopota A.V., Yurevich E.I. [Stages and prospects of development modular design concept in robotics]. Sb. dok. Vseross. nauch.-tekh. konf. "Ekstremal’naya robototekhnika" [Proc. Russ. sci.-tech. conf. "Extreme robotics"]. St. Petersburg, Politekhnika-servis Publ., 2012, pp. 15--18 (in Russ.).

[7] Utkin A.V. Method of state space expansion in the design of autonomous control. Autom. Remote Control, 2007, vol. 68, no. 6, pp. 1006--1022. DOI: S0005117907060082

[8] Solovyev M., Vorotnikov A., Klimov D., et al. Control system of the articulated arm braking mechatronic machine (AABMM). Proc. 28th Int. DAAAM Symp., 2017, pp. 1002--1009. DOI: 10.2507/28th.daaam.proceedings.139

[9] Goldenberg A., Benhabib B., Fenton R. A complete generalized solution to the inverse kinematics of robots. IEEE J. Robot. Autom., 1985, vol. 1, no.1, pp. 14--20. DOI: 10.1109/JRA.1985.1086995

[10] Fletcher R. Practical methods of optimization. Wiley, 1987.

[11] Wang L.-C.T., Chen C.C. A combined optimization method for solving the inverse kinematics problem of mechanical manipulators. IEEE Trans. Robot. Autom., 1991, vol. 7, no. 4, pp. 489--499. DOI: 10.1109/70.86079

[12] Isabe T., Nagasaka K., Yamamoto S. A new approach to kinematic control of simple manipulators. IEEE Trans. Syst., Man, Cybern., 1992, vol. 22, no. 5, pp. 1116--1124. DOI: 10.1109/21.179848

[13] Deo A.S., Walker I.D. Adaptive non-linear least squares for inverse kinematics. Proc. IEEE Int. Conf. Robotics and Automation, 1993, pp. 186--193. DOI: 10.1109/ROBOT.1993.291981

[14] Morris A.S., Mansor A. Finding the inverse kinematics of manipulator arm using artificial neural network with look-up table. Robotica, 1997, vol. 15, no. 6, pp. 617--625. DOI: 10.1017/S026357479700074X

[15] Driscoll J.A. Comparison of neural network architectures for the modeling of robot inverse kinematics. Proc. IEEE, 2000, vol. 3, pp. 44--51.

[16] Oyama E., Agah A., MacDorman K.F., et al. A modular neural architecture for inverse kinematics model learning. Neurocomputing, 2001, vol. 38-40, pp. 797--805. DOI: 10.1016/S0925-2312(01)00416-7

[17] Karlra P., Prakash N.R. A neuro-genetic algorithm approach for solving inverse kinematics of robotic manipulators. IEEE Int. Conf. on Systems, Man and Cybernetics, 2003, vol. 2, pp. 1979--1984. DOI: 10.1109/ICSMC.2003.1244702

[18] Ankarali A., Cilli M. ANFIS Inverse kinematics and hybrid control of a human leg gait model. APJES I-II, 2013, pp. 34--49.