Home > Published Issues > 2020 > Volume 9, No. 3, March 2020 >

Development of an Artificial Intelligent Approach in Adapting the Characteristic of Polynomial Trajectory Planning for Robot Manipulator

Ze Han. Ang, Chun Kit. Ang, Wei Hong. Lim, Lih Jiun. Yu, and Mahmud Iwan Solihin
Mechanical Engineering Department, UCSI University, Kuala Lumpur, Malaysia

Abstract—The trajectory planning of robot manipulator can be calculated by using the mathematical approach when the type of trajectories is known. However, the conventional mathematical method becomes prohibitive because of the complicated mathematical equation and derivation. This research introduces the use of artificial neural networks (ANN) to overcome these limitations by solving nonlinear functions and adapting the characteristics of trajectory planning. A virtual three-degree-of-freedom (DOF) robot manipulator is exploited in this research. The analysis and selection of hyper-parameter for ANN will go through in order to get the optimum performance for ANN. Finally, sample data will be used to evaluate the robustness of the developed ANN topology by comparing the actual results (mathematical approach) with ANN results. 

Index Terms—artificial neural networks, forward kinematics, trajectory planning, robotic manipulator

Cite: Ze Han. Ang, Chun Kit. Ang, Wei Hong. Lim, Lih Jiun. Yu, and Mahmud Iwan Solihin, "Development of an Artificial Intelligent Approach in Adapting the Characteristic of Polynomial Trajectory Planning for Robot Manipulator" International Journal of Mechanical Engineering and Robotics Research, Vol. 9, No. 3, pp. 408-414, March 2020. DOI: 10.18178/ijmerr.9.3.408-414

Copyright © 2020 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.