The purpose of this study is to develop a scientifically grounded approach to the design of ergonomic control systems for information models of agricultural unmanned aerial vehicles based on hand gesture recognition algorithms using modern computer vision and deep learning technologies. The proposed approach aims to improve the efficiency, accuracy, and usability of human–machine interaction in real-world agrodrone operation.The study applies system analysis methods to formalize the “user–device” interaction, as well as comparative analysis of modern software libraries and frameworks (MediaPipe, OpenCV, TensorFlow, PyTorch). Methods of deep learning, including convolutional neural networks, are used to solve hand gesture recognition tasks. Simulation modeling using Python is employed to test and validate the developed prototype.A methodology for designing an ergonomic gesture-based control system for agro-drones has been developed. It includes the formalization of the interaction model, justification of a gesture set based on ergonomic criteria, selection of software tools, and determination of neural network architecture parameters. An experimental prototype based on MediaPipe and Python has been implemented, providing real-time gesture recognition. Simulation testing using cursor control modeling was conducted to evaluate recognition accuracy and stability. The obtained results confirm the operability of the proposed approach and demonstrate its practical applicability for developing intuitive control interfaces for agro-drones.The proposed approach improves human–machine interaction efficiency through the use of natural gesture interfaces and adaptive recognition algorithms. The developed methodology can be applied not only to agro-drones but also to other smart devices. Experimental results confirm the feasibility of applying computer vision and neural networks for contactless control systems, opening prospects for further research in improving accuracy, robustness, and integration into real cyber-physical systems.Recieved2025-11-20Recieved2026-02-01Accepted2026-02-11
Shvorov et al. (Fri,) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: