A Research on Impedance Control Based on ANN Inverse System for Robot Manipulator

Abstract:

Because of lacking the imprecise mathematical model is a difficult problem in the area of dynamic control for robot manipulator. In this paper, a novel scheme which can realize the decoupling for robot by ANN inverse system in the inner loop and control the position and force in the outer loop is presented. The method is studied in the environment of Matlab and is realized by a manipulator in Lab. Analyzed from the experiment result, this algorithm is very feasible and it provides a basis for the further research.

• Periodical: Applied Mechanics and Materials (Volumes 687-691)
• Pages: 560-563
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.687-691.560
• Online since: November 2014
• Authors: Zhen Yang*, Wei Zhang, Shang Lin Yang, Fang Wang
• Keywords: ANN, Impedance Control, Inverse System, Robot

References

[1] DAI Xianzhong, LIU Jun, FENG C, et al, Neural Network αth Inverse System Method for The Control of Nonlinear Continuous System,. IEEE Proc. Control Theory and Appl, china, 1998, 145(6), pp.519-522.

DOI: 10.1049/ip-cta:19982411

[2] DAI Xianzhong, HE Dan, ZHANG X, et al, MIMO System Invertibility and Decoupling Control Strategies Based ANN αth Inversion, IEEE Proc. Control Theory and Appl, china, 2001, 148(2), pp.125-136.

DOI: 10.1049/ip-cta:20010283

[3] Seul Jung. T. C. Hsia and R.G. Bonitz. Force Tracking Impedance Control of Robot Manipulators Under Unknown Environment. IEEE Transaction on Control Systems Technology. Vol. 12. No. 3. 2004: 474-483.

DOI: 10.1109/tcst.2004.824320

[4] S. Jung, T.C. Hsia. Neural network techniques for robust force control of robot manipulators. In Proc. IEEE Symp. Intelligent Control, Monterey, CA, Aug. 1995: 111-116.

DOI: 10.1109/isic.1995.525046

[5] T.C. Hsia. Simple robust schemes for Cartesian space control of robot manipulators. Int. J. Robot. Automat. Vol. 9, No. 4. 1994: 167-174.

[6] H Miyamoto, M Kawato, T Setoyama. Feedback error learning neural network for trajectory control of a robotic manipulator. Neural Networks, 1988, 1(3): 251-265.

DOI: 10.1016/0893-6080(88)90030-5

[7] Armstrong. B, Khatib. O., Burdick. J. The explicit dynamic model and inertial parameters of the PUMA 560 arm. Robotics and Automation IEEE International Conference, Vol3, 1986: 510-518.

DOI: 10.1109/robot.1986.1087644

[8] F. Chaumette,S. Hutchinson. Visual Servo Control Part I: Basic Approaches[J]. IEEE Transactions on Robotics & Automation Magazine, December 2006: 82-90.

DOI: 10.1109/mra.2006.250573

[9] F. Chaumette, S. Hutchinson. Visual Servo Control Part II: Advanced Approaches[J]. IEEE Transactions on Robotics & Automation Magazine, March 2007: 109-118.

DOI: 10.1109/mra.2007.339609

[10] N. Mansard, M. Lopes,J. Santo-Victor and F. Chaumette. Jacobian Learning Methods for Tasks Sequencing in Visual Servoing. Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems[C], Beijing, China, 2006: 4284-4290.

DOI: 10.1109/iros.2006.281958

[11] K. Hosoda, M. Asada. Versatile visual servoing without knowledge of true jacobian [A]. IEEE Conference On Intelligent Robots and Systems[C], 1994: 186-193.

DOI: 10.1109/iros.1994.407392

[12] KANG Q.C. Application of Pseudo-inverse Estimation of Image Jacobian Matrix to Visual Servoing[J]. Robot, 2006, 28(4): 406-409.