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{188930,
        author = {Uma Maheswara Rao Mogili and Dr. Mohit Gangwar},
        title = {A Real-Time Closed-Loop UAV Spraying Framework Integrating 3D Perception, IoT Control, and Adaptive Pesticide Application},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {4222-4234},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188930},
        abstract = {Background / Context:  Growing precision agriculture, together with the automation of UAVs over highly variable field conditions, has created the need for real-time efficient crop spraying systems. Traditional methods of constant-rate UAV sprayers often could not account for canopy height variability, resulting in chemical waste and increased deposition. These limitations hence set the need for intelligent, perception-driven, feedback-enabled spraying systems. Problem/Gap: Most of the early works in UAV spraying fall either into fixed rate or open-loop spraying without any real-time canopy awareness. In fact, none of them have truly integrated 3D sensing with adaptive flow control. Only a few of those works have been able to integrate LiDAR perception, IoT telemetry, and automated variable-rate spraying into a single unified closed-loop framework. Aim/Objective: It sought to develop and evaluate a closed-loop, IoT-based 3D canopy perception and adaptive pesticide application UAV-spraying framework. Methodology/approach: This system integrated LiDAR-derived canopy height and density maps to enable dynamic spray flow adjustments through a real-time adaptive algorithm. The IoT communication used in this work was designed to minimize latency in sensor data transmission for responsive control actuation. Performance evaluation was done using LiDAR-based canopy datasets and simulated spray behavior in adaptive and constant-rate spraying modes. The performance metrics also included predicted deposition uniformity, variation in spray demand, and pesticide-use efficiency. Results/Findings: This adaptive control model resulted in the development of higher spray flow in the dense zone of the canopy and reduction of that flow by as much as 40% in sparse areas. The estimated savings in use of the pesticide was 22-28%. Simulated performance showed improved uniformity of deposition and more stable patterns of application compared with constant-rate spraying. Statistical comparison indicated significantly higher predicted performance of the adaptive mode. Implications / Significance: These test results unveiled the possibility of integrating 3D perception with IoT telemetry and adaptive spraying to allow more accurate, efficient, and environmentally sensitive pesticide application. The results showed that a closed-loop architecture like this will improve accuracy in crop protection while reducing chemical usages and lowering environmental risks associated with drift.},
        keywords = {UAV Spraying; LiDAR; 3D Canopy Perception; IoT; Adaptive Variable-Rate Spraying; Precision Agriculture; Closed-Loop Control.},
        month = {December},
        }