Open Access

ARTICLE

A Deep Learning Approach for the Mobile-Robot Motion Control System

Rihem Farkh^1,4,*, Khaled Al jaloud¹, Saad Alhuwaimel², Mohammad Tabrez Quasim³, Moufida Ksouri⁴

1 King Saud University, Riyadh, 11451, Saudi Arabia
2 King Abdulaziz City for Science and Technology, Riyadh, Saudi Arabia
3 College of Computing and Information Technology, University of Bisha, Bisha, 67714, Saudi Arabia
4 Laboratory for Analysis, Conception and Control of Systems, LR-11-ES20, Department of Electrical Engineering, National Engineering School of Tunis, Tunis El Manar University, Tunis, 1002, Tunisia

* Corresponding Author: Rihem Farkh. Email:

(This article belongs to this Special Issue: Machine Learning and Deep Learning for Transportation)

Intelligent Automation & Soft Computing 2021, 29(2), 423-435. https://doi.org/10.32604/iasc.2021.016219

Received 22 December 2020; Accepted 24 January 2021; Issue published 16 June 2021

Abstract

A line follower robot is an autonomous intelligent system that can detect and follow a line drawn on floor. Line follower robots need to adapt accurately, quickly, efficiently, and inexpensively to changing operating conditions. This study proposes a deep learning controller for line follower mobile robots using complex decision-making strategies. An Arduino embedded platform is used to implement the controller. A multilayered feedforward network with a backpropagation training algorithm is employed. The network is trained offline using Keras and implemented on a ATmega32 microcontroller. The experimental results show that it has a good control effect and can extend its application.

---

Keywords

---