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{196591,
        author = {Vedhavathi Pasala and Gedda Jyotshna and Bhanu Prakash Bolli and Chitrapu ChandraMouli},
        title = {Decentralized Cooperative Area Coverage Using Multi-UAV System Based on Multi-Agent Reinforcement Learning (PPO)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {3322-3333},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196591},
        abstract = {Cooperative area coverage using multiple Unmanned Aerial Vehicles (UAVs) is a critical task in applications such as disaster monitoring, environmental mapping, precision agriculture, and search-and-rescue missions [13][14]. Traditional centralized control approaches suffer from scalability issues, communication overhead, and single-point failures. In this work, we develop a decentralized learning framework where multiple UAVs independently acquire coverage strategies using a Multi-Agent Reinforcement Learning approach based on PPO.[10][11].
The proposed system models the environment as a grid-based exploration task where multiple UAV agents independently learn coverage strategies using shared global maps and reward shaping mechanisms. A hybrid map-fusion strategy incorporating visitation maps and frontier detection is implemented to minimize overlap and improve coverage efficiency.
Experimental evaluation demonstrates that the PPO-based decentralized approach achieves stable convergence, scalable coordination, and efficient area coverage with reduced redundancy. The work primarily serves as an educational and research-oriented implementation demonstrating the integration of MARL algorithms into cooperative UAV systems.},
        keywords = {Multi-UAV Systems, Reinforcement Learning, Multi-Agent PPO, Decentralized Control, Area Coverage, Map Fusion, Autonomous Systems.},
        month = {April},
        }