As world population rises, increases the need for precise agricultural monitoring. Specifically in smart farming, where they could improve crop efficiency, robotic systems have become rather valuable tools. The implementation of an automated robotic monitoring system customized for agricultural environments is reported in this work. Emphasizing thorough tomato plant monitoring with regard to ripeness assessment, disease detection, environmental monitoring, and ripeness assessment, the study addresses the constraints of time-consuming and expensive conventional techniques. The suggested robotic system presents a reasonably priced and effective substitute to raise rates of production. Constructed upon the Robot Operating System (ROS) architecture, the robot’s navigation system makes use of Dynamic Window Approach (DWA) planners and A* algorithm. Nine tomato diseases were detected and autonomous 3-level ripeness classification was accomplished using deep learning methods (YOLOV5). Through the robot, wireless soil monitoring made possible by Internet of Things (IoT) technology was integrated In actual validation, the robot attained great accuracy when assessing the ripeness degree.
Autonomous Agricultural Monitoring Robot for Efficient Smart Farming
124