Browsing by Author "Vallim, Marcos"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- 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.
- Remote lab of robotic manipulators through an open access ROS-based platformPublication . Stefanuto, Bruno Matheu Moreira; Piardi, Luis; Oliveira Júnior, Alexandre de; Vallim, Marcos; Leitão, PauloThe research, training, and learning in robotic systems is a difficult task for institutions that do not have an appropriate equipment infrastructure, mainly due to the high investment required to acquire these systems. Possible alternatives are the use of robotic simulation platforms and the creation of remote robotic environments available for different users. The use of the last option surpasses the former one in terms of the possibility to handle real robotic systems during the training process. However, technical challenges appear in the management of the supporting infrastructure to use the robotic systems, namely in terms of access, safety, security, communication, and programming aspects. Having this in mind, this paper presents an approach for the remote operation of real robotic manipulators under a virtual robotics laboratory. To this end, an open access and safe web-based platform was developed for the remote control of robotic manipulators, being validated through the remote control of a real UR3 manipulator. This platform contributes to the research and training in robotic systems among different research centers and educational institutions that have limited access to these technologies. Furthermore, students and researchers can use this educational tool that differs from traditional robotic simulators through a virtual experience that connects real manipulators worldwide through the Internet.
- Security experiences in IoT based applications for building and factory automationPublication . Morenas, Javier de las; Silva, Carolina Miller da; Funchal, Gustavo Silva; Melo, Victória; Vallim, Marcos; Leitão, PauloIndustry 4.0 and Industrial Internet of Things (IIoT) are promoting the connection of millions of devices, that once were seen as unconnectable, into a huge network, to be used in a large number of applications, from autonomous vehicles to industrial control systems, passing through building automation systems. These paradigm rely on the adoption of Cyber Physical Systems complemented with Internet of Things (IoT) technologies and artificial intelligence techniques. These type of systems are responsible for collecting, processing and exchanging a vast amount of data, and for that reason, it is imperative to assure data integrity and protection against malicious modifications and attacks to ensure a safe and reliable operation. Data thefts and cyber attacks in general represent a significant danger, however, cyber attacks on IoT systems can be specially critical due to their proximity with humans, enhancing the risk of physical damage. This paper highlights the importance of securing these systems, pursuing a safer operation, having in mind the amount of security vulnerabilities found in embedded devices. For this purpose, this article studies possible security threats and weakness in two case studies coming from different IoT domains, i.e. building automation and factory automation, while seeking for solutions to improve these systems’ security.
- Security for a multi-agent cyber-physical conveyor system using machine learningPublication . Funchal, Gustavo Silva; Pedrosa, Tiago; Vallim, Marcos; Leitão, PauloOne main foundation of Industry 4.0 is the connectivity of devices and systems using Internet of Things (IoT) technologies, where Cyber-physical systems (CPS) act as the backbone infrastructure based on distributed and decentralized structures. This approach provides significant benefits, namely improved performance, responsiveness and reconfigurability, but also brings some problems in terms of security, as the devices and systems become vulnerable to cyberattacks. This paper describes the implementation of several mechanisms to increase the security in a self-organized cyber-physical conveyor system, based on multi-agent systems (MAS) and build up with different individual modular and intelligent conveyor modules. For this purpose, the JADE-S add-on is used to enforce more security controls, also an Intrusion Detection System (IDS) is created supported by Machine Learning (ML) techniques that analyses the communication between agents, enabling to monitor and analyse the events that occur in the system, extracting signs of intrusions, together they contribute to mitigate cyberattacks.