Retrofitting of the Robuter's platform to an AGV with visual guidance

• Autor(a) principal: Vieira, Bruno Carvalho
• Data de Publicação: 2017
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10773/22379
• topic: Engenharia de automação industrial; Automação; Controlo automático; Visão artificial

The industrial automation has made its way in responding to the growing market’s needs. Companies that wish to keep up with the competition have a common goal: improve the product’s quality while reducing manufacturing costs and time. In the last decade, the autonomous guided vehicles (AGV) have gained expression due to the fact that they are capable of responding this the last mentioned necessity. The context of the current dissertation is inserted in the development of this thematic through the recovery of an equipment with industrial scale applications. The main goal is centered in the Robuter II platform’s retrofitting. For that, it is intended to replace the old control part by a modern solution that allows the integration of different modules based on a ROS distributed architecture. A detailed analysis of the existing platform was made in order to redo all the electrical installation, as well as to setup all of the used equipment. In the end, a vehicle capable of navigating, both manual and autonomously, was achieved. The vehicle can be operated manually (via remote control) and as a proof of concept, autonomous navigation was carried out through a simple artificial vision algorithm. It was also verified the versatility of the developed solution by integrating different equipment and designed code in a simple way. This document describes generally the project where all the different steps are identified, as well as all the work developed until the present moment. Furthermore, the guidelines to follow in order to achieve the proposed goals, is presented. Finally, navigation experimental results and the integration of different works on the platform are presented.