MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202641098326 A) filed by Mr. Utpal Madhu; Dr. Arpan Dutta; Dr. Manasi Mukhopadhyay; Dr. Paramita Biswas; Dr. Sujoy Kumar Goswami; Dr. Sudipta Nath; Mr. Rajendra Patra; Mr. Debangsu Halder; Ms. Archita Mondal; and Mr. Shan Mondal on August 13, 2026, for A Multi-Reservoir Edge-Ai Controlled Precision Spraying System With Dynamic Agrochemical Optimization And Electrostatic Variable- Charge Targeting.
Inventors include Mr. Utpal Madhu; Dr. Arpan Dutta; Dr. Manasi Mukhopadhyay; Dr. Paramita Biswas; Dr. Sujoy Kumar Goswami; Dr. Sudipta Nath; Mr. Rajendra Patra; Mr. Debangsu Halder; Ms. Archita Mondal; and Mr. Shan Mondal.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: The present invention relates to an Edge Artificial Intelligence (Edge-AI)-controlled precision agricultural spraying system capable of autonomously identifying crop health conditions, optimizing agrochemical selection, and executing targeted electrostatic spraying without dependence on cloud computing. The system comprises a multi-reservoir agrochemical storage module, a multi-modal sensing unit including one or more RGB, multispectral, thermal, or depth cameras and environmental sensors, an embedded Edge-AI computing platform implemented using a Jetson Orin Nano Super, an adaptive decision and optimization framework, an electronically controlled spray delivery system, and a variable-charge electrostatic spraying module. The embedded Edge-AI platform performs real-time crop, weed, pest, and disease detection, severity estimation, crop growth-stage identification, and environmental condition analysis to autonomously determine the optimal agrochemical reservoir, spray dosage, droplet size, nozzle configuration, spray pressure, travel speed, and electrostatic charging voltage. The invention further incorporates a closed- loop spray verification mechanism that evaluates spray coverage and deposition quality immediately after application and automatically performs corrective spraying when predetermined coverage criteria are not satisfied. A local self-learning database continuously updates decision parameters based on previous spraying operations, field conditions, agrochemical performance, and application history, enabling adaptive optimization while operating entirely offline. By integrating dynamic agrochemical optimization, adaptive electrostatic variable-charge targeting, real-time Edge-AI decision making, and closed-loop spray verification into a unified autonomous framework, the invention significantly improves spraying precision, enhances agrochemical deposition efficiency, reduces chemical consumption and off- target drift, minimizes environmental impact, and supports scalable precision agriculture across diverse cropping systems. This integrated Edge-AI optimization framework provides a technically advanced and robust solution for next-generation intelligent precision spraying applications.
Disclaimer: Curated by HT Syndication.
