MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043736 A) filed by Sr University, Warangal, Telangana, on April 6, for 'system and method for federated machine learning-based decision making in autonomous uav swarms.'
Inventor(s) include Dr. Sachin Bandewar; and Dr. Durgesh Nandan.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "This invention presents a system and method that enables coordinated decision-making in autonomous unmanned aerial vehicle (UAV) swarms using federated machine learning. Instead of relying on centralized data aggregation, each UAV independently trains local models using its onboard data, preserving privacy and reducing communication overhead. The locally learned parameters are periodically shared and aggregated to form a global model that enhances collective intelligence across the swarm. The proposed framework supports real-time adaptability in dynamic environments, allowing UAVs to respond efficiently to changing conditions such as obstacles, mission objectives, and environmental uncertainties. It incorporates secure communication protocols, distributed optimization techniques, and lightweight model updates to ensure scalability and robustness. The system is particularly suitable for applications including surveillance, disaster response, environmental monitoring, and search-and-rescue operations. By combining decentralized learning with collaborative intelligence, the invention improves decision accuracy, minimizes latency, and enhances operational autonomy, making UAV swarms more efficient, resilient, and capable in complex and data-sensitive scenarios."
Disclaimer: Curated by HT Syndication.
