Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{183499,
        author = {Amtul Mateen and Dr. Mohammed Abdul Waheed},
        title = {performance evaluation of machine learning in wireless connected robotics swarms},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {3},
        pages = {1818-1824},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=183499},
        abstract = {Wireless-connected robotic swarms are increasingly utilized in applications requiring scalable, adaptive, and decentralized systems like search-and-rescue, and military surveillance. Efficient communication, coordination, and task allocation among swarm members are critical to their overall performance. This study presents a comprehensive performance evaluation of various machine learning models—including K-Means Clustering, Artificial Neural Networks (ANN), and Q-Learning—for enhancing swarm behavior in wireless-connected robotic systems. A simulation framework has been developed using Python and Pygame to visualize swarm interactions, message exchange, and learning outcomes. Robots are modeled as intelligent agents capable of dynamic movement, message passing, and sensor-based communication. Q-Learning is implemented to optimize robot decisions in sending messages based on proximity and past rewards, allowing adaptive behavior in high-density networks. K-Means is applied to group robots based on location patterns, while ANN models predict action outcomes for future decision-making. Key performance metrics such as communication efficiency, message success rate, and model accuracy are evaluated and visualized through GUI dashboards. Warning messages trigger sound alerts and red trail visualization, while task messages are logged with green paths. The system also supports real-time logging and graphical representation of learned behaviors. Experimental results demonstrate that Q-Learning significantly improves adaptive communication strategies, especially in dynamic environments. The integration of machine learning into swarm robotics highlights promising directions for intelligent, self-organizing multi-agent systems.},
        keywords = {K-Means Clustering, Artificial Neural Networks (ANN),  Q-Learning, GUI dashboard, robotic swarm, pygame},
        month = {August},
        }