The primary goal of this thesis is to propose and validate a method to improve the positioning accuracy of industrial robots, particularly in applications where high precision is required. By examining the limitations of traditional repeatability-focused approaches and exploring the integration of vision systems, this research aims to enhance the robot's ability to perform complex tasks with greater accuracy. The case study involving the automation of the screwing/unscrewing process inside an aerospace casing serves as a practical demonstration of these concepts. The thesis will explore the technical modifications made to the robot and the tools used, focusing on how these changes contribute to improve accuracy and overall performance.