This paper presents the design and implementation of a Convolution Neural Network (CNN) for path following of a mobile robot. The goal of the paper is to develop an effective system that allows the robot to navigate autonomously along a predefined trajectory. The CNN architecture is designed to extract meaningful features from sensor inputs, such as images or signals, and make accurate predictions of the robot’s next action. The proposed CNN-based path following system offers several advantages, including robustness to environmental changes, adaptability to different path structures, and potential for real-time deployment. Furthermore, the system showcases the potential of CNNs in enhancing the autonomy and navigation capabilities of mobile robots. This research contributes to the field of robotics by presenting a comprehensive approach to designing and implementing a custom CNN for path following of a mobile robot which supports the approach for future developments in autonomous robot navigation, offering new opportunities for applications in various domains, such as warehouse automation, agricultural robotics, and unmanned vehicles.