Abstract. This article discusses the process of developing an automated spot irrigation system for plants, including the use of computer vision and robotic systems. One of the most advanced systems today is the FPV agro-robots operating with the Raspberry Pi 4 mini-computer and a web camera. This system allows real-time monitoring and analysis of visual data for accurate irrigation of plant roots. The optimal choice for software and hardware development is the RaspController web application, which enables remote control via local and global Internet networks. This application provides access to GPIO pins and images from the web camera. Control of the robot’s movement is carried out by encoding the control pins of the L298N chip. A key feature of controlling the FPV agro-robot is the intelligent recognition of the white lines of the movement trajectory to the irrigation point and horizontal white strips that determine the watering dose for each plant, using computer vision. The prototype of the agro-robot has passed testing and has enabled the creation of a working semi-industrial model, and the use of the spot irrigation method contributes to saving over 50% of water.

Keywords: Spot irrigation, agro-robots, computer vision, neural networks, agriculture, Raspberry Pi, IOT.