Development and Implementation of a Machine Learning Algorithm for Path Optimization in Autonomous Floor Cleaning Robots
Laila Abdulaziz
Bilal Fares
Abstract
The efficiency of autonomous floor cleaning robots significantly depends on their ability to navigate and clean spaces optimally. This paper introduces a novel machine learning algorithm designed to enhance path optimization in autonomous floor cleaning robots, aiming to improve cleaning efficiency and reduce operational time. We detail the development process of the algorithm, including data collection, model training, and implementation challenges. A comparative analysis of the algorithm's performance against conventional pathfinding algorithms used in cleaning robots, such as A* and Dijkstra’s algorithm, is presented. The results demonstrate a marked improvement in path efficiency, coverage uniformity, and obstacle avoidance, leading to a reduction in energy consumption and operational time. This research contributes to the field of robotics by providing a scalable and adaptive solution for path optimization in autonomous cleaning robots, with potential applications in various environments, including homes, offices, and healthcare facilities.
