Mobile robot navigation based on CNN images processing: an experimental setup

Abstract

Abstract: – This paper presents results of our work in development of a path-planning algorithm for obstacle avoidance of a mobile robot in a real workspace. The gray-scale images processing of the robot’s workspace (global path-planning) is realized by using cellular neural networks (CNNs). Besides that, two IR sensors, mounted in front of the robot were used for fast obstacle avoidance (local path-planning).