FPGA IMPLEMENTATION OF RECONFIGURABLE INTELLIGENT CONTROLLER FOR MOBILE ROBOT
Author(s):
Abbas H. Issa, Abdulrahim Thiab Humod, Sabah A. Gitaffa
Affiliation(s):
University of Technology, Electrical Engineering Department, Baghdad, Iraq
Corresponding Author Email: [email protected]
This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
In this research, a reconfigurable intelligent controller for mobile robot is proposed. As stated by the proposed system name, the control system architecture was modified by software called reconfigurable control system, and the controller was designed and executed utilizing Field Programmable Gate Array (FPGA) technology. The robot performs the function of obstacles’ detection and avoidance while moving to a specific distance by a set point in unknown environments. The intelligent neural network (NN) controller was trained by the Levenberg-Marquardt algorithm using Adaptive Direct Inverse Neural Network (ADINN) control technique, then it was implemented on the FPGA board. The response appears completely the same as simulation response before implementation, so the software designed controller results can be relied on. The controller designed by both m-file and Simulink in MATLAB R2012a version 7.14. The hardware implementation of the mobile robot system used: FPGA board as the hardware platform of the proposed controller, Ultrasonic sensors, Analog to Digital Converters (ADCs), incremental encoders, motor driver and Direct Current (DC) motors.