DYNAMIC MODELLING OF MANIPULATOR USING ADAPTIVE NEURO FUZZY INFERENCE SYSTEM

The dynamic modelling of manipulator is essential for the design, simulation and control system of manipulator. Researchers have proposed different techniques for dynamic modelling of manipulators. The commonly used methods to formulate the dynamic equations of motion for manipulators are Newton-Euler and Lagrange-Euler methods. Because of these methods are numerical recursive methods, they are computationally expensive and not suitable to use directly in real time applications. In this paper, we proposed the adaptive neuro fuzzy inference system-based method to construct the input-output mapping for the dynamic equations of motion of a 5 degree-of-freedom manipulator. The dynamic model of the manipulator is computed using Newton-Euler dynamic formulation to create the training data sets for the adaptive neuro fuzzy inference system. The proposed method is tested in generating the required torques for a point-to point trajectory. Results show that the proposed method can perform within shorter operational time and its performance is comparable to Newton-Euler method. The proposed method can be used for the rigid-body manipulators whose dynamical characteristics are known

1. Craig J.J. Introduction to Robotics, Mechanics and Control. 3rd ed. Upper Saddle River, NJ: Pearson; 2005:165–200.

2. Raibert M.H. Analytical Equations vs. Table Look-up for Manipulation: A Unifying Concept. IEEE Conference on Decision and Control; 1977 Dec; New Orleans. New Orleans; 1977:576–579.

3. Albus J.S. A New Approach to Manipulator Control: The Cerebellar Model Articulation Controller (CMAC). Dynamic Systems, Measurement, Control. 1975;97:270–277.

4. Cheng C.A., Huang H.P., Hsu H.K. et al. Learning the Inverse Dynamics of Robotic Manipulators in Structured Reproducing Kernel Hilbert Space. IEEE Transactions on Cybernetics. 2016;46(7):1691–1703.

5. Vijayakumar S., Schaal S. Locally Weighted Projection Regression: An O(n) Algorithm for Incremental Real Time Learning in High Dimensional Space. Proceedings of the Seventeenth International Conference on Machine Learning; 2000 July; Stanford. Stanford; 2000:1079–1086.

6. Nguyen-Tuong D., Seeger M., Peters J. Model learning with local gaussian process regression. Advanced Robotics. 2009;23(15):2015–2034.

7. Gijsberts A., Metta G. Real-time Model Learning Using Incremental Sparse Spectrum Gaussian Process Regression. Neural Networks. 2013;41:59–69.

8. Nguyen-Tuong D., Peters J., Seeger M. Learning Inverse Dynamics: A Comparison. Advances in Computational Intelligence and Learning: Proceedings of the European Symposium on Artificial Neural Networks; 2008 Apr; Bruges. Bruges; 2008:13–18.

9. Polydoros A.S., Boukas E., Nalpantidis L. Online Multi-Target Learning of Inverse Dynamics Models for Computed-Torque Control of Compliant Manipulators. 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems; 2017 Sep; Vancouver. Vancouver; 2017:4716–4722.

10. Nguyen-Tuong D., Peters J. Using Model Knowledge for Learning Inverse Dynamics. 2010 IEEE International Conference on Robotics and Automation; 2010 May; Alaska. Alaska; 2010: 2677–2682.

11. Cruz J.S., Kulic D., Owen W. Online Incremental Learning of Inverse Dynamics Incorporating Prior Knowledge. Autonomous and Intelligent Systems. Lecture Notes in Computer Science. 2011;6752:167–176.

12. Jang J. R. ANFIS: Adaptive-network-based Fuzzy Inference System. IEEE Transactions on Systems, Man, and Cybernetics. 1993;23(3):665–685.