DYNAMIC MODELLING OF MANIPULATOR USING ADAPTIVE NEURO
FUZZY INFERENCE SYSTEM

UDC 004.896, 004.942
DOI:10.26102/2310-6018/2019.27.4.001

Thu Rain, Yan Naing Soe


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.

Keywords: dynamic modelling, Newton-Euler method, adaptive neuro fuzzy inference system, manipulator dynamics.

Full text:
ThuRainSoavtors_4_19_1.pdf