Analysis, Design and Implementation of a Robotic Arm with Writing Ability Using Neural Networks

Abstract

In this paper, multi-segments parametric cartesian space trajectory planning equations based on Neural Network approach is proposed. This work includes using a real two-link robotic arm to be able to write the english words or letters. The proposed algorithm is used to find the positions of the end-effector robotic arm. Neural Network is trained by Back Propagation Algorithm. The two-link robotic has two Degrees Of Freedom. It has two joint angles with three servo motors. A pen is connected to the third servomotor in order to raise and lower the pen. The outputs of this algorithm are: two Pulse Width Modulation motor commands, one Pulse Width Modulation motor command voltage for the first joint angle and the second Pulse Width Modulation motor command voltage for the second joint angle. The results of position errors are acceptable due to servomotors of practical robotic arm. The best training performance error of Mean Square Error for Back Propagation Algorithm equals to (5.3465*10^(-25)). In this work, the maximum positions errors for the end-effector of the robot are computed between theoretical and experimental work. The maximum position error in X axis equals to (-0.0102 m) and the maximum position error in Y axis equals to (-0.0098 m). The writing results of two-link real robotic arm was smooth line segments according to small position errors in X and Y axes.