Percorrer por autor "Talacio, Matheus Teixeira"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Development of an intelligent personal assistant to empower operators in industry 4.0 environmentsPublication . Talacio, Matheus Teixeira; Leitão, Paulo; Vallim, MarcosIndustry 4.0 brings a high level of automation to industrial environments and changes the way companies operate, both in operational aspects and in human relations. It is important to define the role of the millions of operators affected in this new socioeconomic paradigm, integrating new technologies and empowering the workforce to take advantage of aspects such as the flexibility and versatility that human operators bring to production lines. To advance the implementation of this objective, this work proposes the development of an intelligent personal assistant, using concepts of human-in-the-loop cyber-physical systems and context awareness, to assist operators during manufacturing tasks, providing the necessary information for the fulfillment of operations and verifying the accuracy to inform them about possible errors. The implementation is divided in two parts. The first part focuses on an application that supports the real-time operations that can be present in the industry, such as pick and place in warehouses and the assembly of complex equipment on an assembly line. Through an interface, the instruction is given and, using artificial vision techniques with images coming from an IntelRealsense camera, it verifies if the operation is being correctly performed. The gathering of this information occurs in a context awareness algorithm, fulfilling the requirement of intelligent personal assistant and providing feedback to the operator so that the tasks are performed with efficiency and lower incidence of errors. The second part includes the training of these operators in an immersive environment through a virtual reality equipment such as the Oculus Go. The immersive scenario, developed in Unity3D, uses as a model the real workbench, bringing the possibility of performing these trainings in any environment and excluding the need to use real equipment, which could be damaged by the user’s inexperience. The results achieved during the validation tests performed in these two parts, commenting on the strengths, challenges and failures found in the system in general. These results are also qualitatively compared with traditional applications of the proposed case studies in order to prove the fulfillment of the objectives proposed in this work. Finally, the usability test is presented, which provides data on weak points in the user experience for possible improvements in future work.
- Machine vision to empower an intelligent personal assistant for assembly tasksPublication . Talacio, Matheus Teixeira; Funchal, Gustavo Silva; Melo, Victória; Piardi, Luis; Vallim, Marcos; Leitão, PauloIn the context of the fourth industrial revolution, the integration of human operators in emergent cyber-physical systems assumes a crucial relevance. In this context, humans and machines can not be considered in an isolated manner but instead regarded as a collaborative and symbiotic team. Methodologies based on the use of intelligent assistants that guide human operators during the execution of their operations, taking advantage of user friendly interfaces, artificial intelligence (AI) and virtual reality (VR) technologies, become an interesting approach to industrial systems. This is particularly helpful in the execution of customised and/or complex assembly and maintenance operations. This paper presents the development of an intelligent personal assistant that empowers operators to perform faster and more cost-effectively their assembly operations. The developed approach considers ICT technologies, and particularly machine vision and image processing, to guide operators during the execution of their tasks, and particularly to verify the correctness of performed operations, contributing to increase productivity and efficiency, mainly in the assembly of complex products.