Improving Trajectory Tracking Performance of Robotic Manipulator Using Neural Online Torque Compensator

Mahmoud M. Al Ashi, Iyad Abu Hadrous, Hatem Elaydi


This paper introduces an intelligent adaptive control strategy called Neural Online Torque Compensator (NOTC)
based on the learning capabilities of artificial neural networks (ANNs) in order to compensate for the structured and unstructured
uncertainties in the parameters of a robotic manipulator trajectory tracking control system. A two-layered neural perceptron
was designed and trained using an Error Backpropagation Algorithm (EBA) to learn the difference between the actual
torques generated by the joints of a 2-DOF robotic arm and the torques generated by the computed torque disturbance rejection
controller that was designed previously. An objected oriented approach based on Modelica was adopted to develop a model
for the whole robotic arm trajectory tracking control system. The simulation results obtained proved the effectiveness of the
NOTC compensator in improving the performance of the computed torque disturbance rejection controller by compensating
for both structured and unstructured uncertainties.

Full Text:


Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.