Hybrid neuro-analytical approaches for motion control of multi-link mechanisms

This paper addresses the problem of synthesizing a unified control system for the motion of stationary multi-link serial-chain manipulators. The developed real-time control system provides solutions to the forward and inverse kinematics problems for a multi-link manipulator in real-time. The core contribution is a hybrid method for solving the inverse kinematics problem, based on the synergistic integration of fuzzy neural networks and classical iterative numerical methods. This approach guarantees the achievement of the required positioning accuracy within strict time constraints. The fundamental feasibility of adapting the algorithmic software and the overall control system architecture for use with manipulators of different kinematic configurations is demonstrated. A modification of the iterative solution refinement algorithm, operating in the vicinity of approximate values generated by the of fuzzy neural network, significantly enhances computational performance while maintaining accuracy control. The control system architecture is hierarchically decomposed: the subsystem for low-level control of actuators (servo drives, encoders, etc.) is isolated into an independent loop, which improves the manipulator’s operational reliability and safety.
EDN: OHHUVX, https://elibrary/ohhuvx

References

[1] Artobolevskiy I.I. Teoriya mekhanizmov i mashin [Theory of mechanisms and machines]. Moscow, Alyans Publ., 2011. 639 p. (In Russ.).

[2] Zenkevich S.L., Yushchenko A.S. Osnovy upravleniya manipulyatsionnymi robotami [Basics of control on manipulation robots]. Moscow, Bauman MSTU Publ., 2004. 480 p. (In Russ.).

[3] Kolovskiy M.Z., Evgrafov A.N., Semenov Yu.A. et al. Teoriya mekhanizmov i mashin [Theory of mechanisms and machines]. Moscow, Academia, 2006. 557 p. (In Russ.).

[4] Chernousko F.L., Bolotnik N.N., Gradetskiy V.G. Manipulyatsionnye roboty [Manipulation robots]. Moscow, Nauka Publ., 1989. 363 p. (In Russ.).

[5] Yurevich E.I. Osnovy robototekhniki [Fundamentals of robotics]. Sankt-Peterburg, BKhV-Peterburg Publ., 2010. 359 p. (In Russ.).

[6] Denavit J., Hartenberg R.S. Kinematic synthesis of linkages. McGraw-Hill, 1964. 435 p.

[7] Uicker J.J., Denavit J., Hartenberg R.S. An iterative method for the displacement analysis of spatial mechanisms. J. Appl. Mech., 1964, vol. 31, no. 2, pp. 309–314, doi: https://doi.org/10.1115/1.3629602

[8] Park F.C., Kim J.W. Manipulability and singularity analysis of multiple robot systems: a geometric approach. IEEE Int. Conf. on Robotics and Automation, 1998, vol. 2, pp. 1032–1037, doi: https://doi.org/10.1109/ROBOT.1998.677224

[9] Park F.C. A coordinate-free description of robot dynamics. IEEE Int. Conf. on Robotics and Automation, 1997, vol. 3, pp. 2282–2287, doi: https://doi.org/10.1109/ROBOT.1997.619302

[10] Park F.C. Optimal robot design and differential geometry. J. Mech. Des., 1995, vol. 117, no. B, pp. 87–92, doi: https://doi.org/10.1115/1.2836475

[11] Park F.C. Computational aspects of the product-of-exponentials formula for robot kinematics. IEEE Trans. Automat. Contr., 1994, vol. 39, no. 3, pp. 643–647, doi: https://doi.org/10.1109/9.280779

[12] Lee H.-Y., Roth B. A closed-form solution of the forward displacement analysis of a class of in-parallel mechanisms. IEEE Int. Conf. on Robotics and Automation, 1993, vol. 1, pp. 720–724, doi: https://doi.org/10.1109/ROBOT.1993.292063

[13] Lee H.-Y., Lin W., Duffy J. A method for forward displacement analysis of in-parallel platform mechanisms. Mechatronics, 1993, vol. 3, no. 5, pp. 659–669, doi: https://doi.org/10.1016/0957-4158(93)90030-6

[14] Lee H.-Y., Reinholtz C.F. Inverse kinematics of serial-chain manipulators. J. Mech. Des., 1996, vol. 118, no. 3, pp. 396–404, doi: https://doi.org/10.1115/1.2826899

[15] Tsai L.-W., Morgan A.P. Solving the kinematics of the most general six- and five-degree-of-freedom manipulators by continuation methods. J. Mech., Trans., and Automation, 1985, vol. 107, no. 2, pp. 189–200, doi: https://doi.org/10.1115/1.3258708

[16] Pieper D.L. The kinematics of manipulators under computer control. Stanford University, 1968. 157 p.

[17] Makarov I.M., Lokhin V.M., eds. Intellektualnye sistemy avtomaticheskogo upravleniya [Intelligent automatic control systems]. Moscow, Fizmatlit Publ., 2001. 576 p. (In Russ.).

[18] Makarov I.M., ed. Iskusstvennyy intellekt i intellektualnye sistemy upravleniya [Artificial intelligence and intelligent control systems]. Moscow, Nauka Publ., 2006. 332 p. (In Russ.).

[19] Guez A., Eilbert J.L., Kam M. Neural network architecture for control. IEEE Control Syst. Mag., 1988, vol. 8, no. 2, pp. 22–25, doi: https://doi.org/10.1109/37.1869

[20] Guez A., Ahmad Z. Accelerated convergence in the inverse kinematics via multilayer feedforward networks. Int. Joint Conf. on Neural Networks, 1989, vol. 2, pp. 341–344, doi: https://doi.org/10.1109/IJCNN.1989.118720

[21] Hashimoto H., Kubota T., Kudou M. et al. Self-organizing visual servo system based on neural networks. IEEE Control Syst., 1992, vol. 12, no. 2, pp. 31–36, doi: https://doi.org/10.1109/37.126850

[22] Morris A.S., Mansor A. Finding the inverse kinematics of manipulator arm using artificial neural network with lookup table. Robotica, 1997, vol. 15, no. 6, pp. 617–625, doi: https://doi.org/10.1017/S026357479700074X

[23] Manjaree S., Agarwal V., Nakra B.C. Kinematic analysis using neuro-fuzzy intelligent technique for robotic manipulator. IJERT, 2013, vol. 6, no. 4, pp. 557–562.

[24] Kosko B. Fuzzy systems as universal approximators. IEEE Trans. Comput., 1994, vol. 43, no. 11, pp. 1329–1333, doi: https://doi.org/10.1109/12.324566

[25] Jha P. Inverse kinematic analysis of robot manipulators. PhD thesis. National Institute of Technology Rourkela, 2015. 336 p.

[26] Jha P. Inverse kinematic solution of 5R manipulator using ANN and ANFIS. IJRA, 2016, vol. 4, no. 2, pp. 109–123, doi: http://doi.org/10.11591/ijra.v4i2.pp109-123

[27] Park J.-K. Inverse kinematics based on fuzzy logic and neural networks for the WAM-titan II teleoperation system. Master’s Thesis. University of Tennessee, 2007. 122 p.