A Deep Learning Approach for the Mobile-Robot Motion Control System Rihem Farkh 1,4,* , Khaled Al jaloud 1 , Saad Alhuwaimel 2 , Mohammad Tabrez Quasim 3 and Moufida Ksouri 4 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: rfarkh@ksu.edu.sa Received: 22 December 2020; Accepted: 24 January 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 accu- rately, 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: Neural control system; real-time implementation; navigation environment; and mobile robots 1 Introduction With the advancement of technology and science and improvement of productivity, robots are increasingly being used in various fields ranging from industry, military, healthcare and related fields [1], search and rescue, management, and agriculture, allowing humans to accomplish complicated tasks [2,3]. Currently, robots are developing in the direction of high precision, high speed, and stable safety [4]. To design and manufacture useful products, intelligent mobile robots combine control, electronic, computer, software, and mechanical engineering [5]. Mobile robots can move between locations to perform desired and complex tasks [6]. A mobile robot is controlled by software and integrated sensors, such as infrared, ultrasonic, and magnetic sensors, and webcams and GPSs. Wheels and DC motors are used to drive the robot [7]. Line follower robots can be utilized in many industrial applications, such as transporting heavy materials and materials that pose a danger to human safely, e.g., nuclear products. These robots are also capable of monitoring patients in hospitals and notifying medical personnel of dangerous conditions [8]. A significant number of researchers have focused on control techniques and smart vehicle navigation, since This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Intelligent Automation & Soft Computing DOI:10.32604/iasc.2021.016219 Article ech T Press Science