Alsina, Pablo JavierRibeiro, William da Cunha2025-06-092025-06-092025-02-07RIBEIRO, William da Cunha. Robô autônomo para rondas de monitoramento em ambientes industriais. Orientador: Dr. Pablo Javier Alsina. 2025. 77f. Dissertação (Mestrado em Engenharia Mecatrônica) - Centro de Tecnologia, Universidade Federal do Rio Grande do Norte, Natal, 2025.https://repositorio.ufrn.br/handle/123456789/63880This study aims to develop a robotic system specialized in performing autonomous inspection rounds in industrial environments, using computer vision techniques for odometry correction. The adoption of this approach is justified by the complexity and high cost associated with replacing analog pressure gauges with models connected to the automation network. Such replacement would require production downtime, leading to loss of revenue during the retrofit process. Additionally, the proposed solution offers advantages over traditional rounds performed by human operators, which are time-consuming and divert personnel from more strategic intellectual activities, such as production data analysis, performance monitoring, and preventive actions within the factory. The robot’s localization is based on the fusion of odometry data and visual markers using the ArUco tag standard. This approach provides a visual reference for the robot’s autonomous navigation, enabling the correction of odometry and, consequently, the robot’s positioning within the workspace. The embedded hardware and software architecture is essential for the system’s efficient operation. Odometry and motor control are managed by a dedicated microcontroller (Arduino), while communication and high-level task management, including computer vision and navigation, are handled by an ESP32. This task distribution enables efficient and optimized operation, ensuring that the robot’s different modules work in a coordinated manner. As part of the validation testing, the robot captures images of pressure gauges along its route. This process aims to visually document the devices without performing automatic extraction and interpretation of the indicated values. This approach ensures that visual data is available for later analysis without compromising the robot’s performance during operation. This work presents an innovative solution for monitoring analog pressure gauges in industrial environments, emphasizing the effectiveness of computer vision and robotic autonomy. The proposed approach not only optimizes financial resources by avoiding costly gauge replacements but also enhances operational efficiency by freeing operators to focus on more strategic tasks.pt-BRAcesso AbertoRobô autônomoIdentificação de manômetrosOdometria e marcos visuaisNavegação em ambientes industriaisProcessamento de imagensmasterThesisENGENHARIAS