Precision agriculture is a key technology for addressing challenges such as increasing food demand, labour shortages, and the environmental impact of intensive agrochemical use. In this context, selective weed management remains a critical issue due to its direct effect on crop productivity and sustainability. This article presents a simulation-based framework for the design and evaluation of an agricultural robotic module for the detection, classification, and selective intervention of weeds. The proposed system integrates convolutional neural networks and the kinematic model of a 2DOF robot manipulator with 5 links for weed classification and treatment. The system is evaluated in a virtual environment, where camera calibration, perception accuracy, and the performance of the kinematic model are analysed. Quantitative results include detection accuracy, localization error, and intervention success rate under simulated field conditions. The results demonstrate selective weed management and the feasibility of simulation for developing weed control systems, while also identifying the main challenges for real-world deployment.

Precision agriculture has revolutionised the way farmers manage their crops, maximising efficiency and minimising environmental impact. This thesis addresses the design and implementation of a device that identifies the corn plant and with the help of artificial intelligence implement a robotic arm that delivers herbicides and in some cases precision lasers. We will explore the design and control of a precision farming device, from basic principles to the most advanced technologies currently in use. We will analyse the sensorisation tools, control systems and optimisation techniques employed to ensure a more sustainable and profitable agriculture through: precision identification of maize plants and the use of a robotic mechanical arm equipped with two nozzles, one to deliver herbicide and the other to deliver lasers to the weeds surrounding the maize plants. The proposal aims for the expected results to reduce herbicide consumption by 30-50%, validating the feasibility of this scalable and sustainable solution to improve efficiency in agricultural infrastructures.