Mestrado em Engenharia Elétrica

URI Permanente para esta coleção

http://repositorio.ufes.br/handle/10/17619

Nível: Mestrado Acadêmico
Ano de início:
Conceito atual na CAPES:
Ato normativo:
Periodicidade de seleção:
Área(s) de concentração:
Url do curso:

Navegar

Navegando Mestrado em Engenharia Elétrica por Autor "Alsina, Pablo Javier"

Agora exibindo 1 - 5 de 5
  • Nenhuma Miniatura disponível
    Item
    Design and Implementation of Electronic Architecture for Cloud Robotics and Human-Robot-Environment Interaction Strategy Applied to SmartWalker
    (Universidade Federal do Espírito Santo, 2021-12-13) Rocha Júnior, Joelson de Carvalho; Frizera Neto, Anselmo; https://orcid.org/0000000206873967; http://lattes.cnpq.br/8928890008799265; Alsina, Pablo Javier; Diaz, Camilo Arturo Rodriguez; Mello, Ricardo Carminati de
    Techniques for Human-Robot-Environment Interaction allow sharing control between assistive devices, such as smart walkers, and its users by taking into account the human motion intention and dynamic environments composed of objects and people. Smart Walkers are service robots equipped with a series of sensors and actuators to provide locomotion assistance to impaired people. The complexity in the algorithms to process all the sensors data push researchers to study and explore concepts of cloud computing, called cloud robotic paradigms, in such platforms. This dissertation presents the design and development of an electronic architecture for cloud robotics applied to Smart Walker. Through this implementation, the robotic device, from now called UFES CloudWalker, is capable of acquiring and transferring data to a robust virtual machine which process and convert them in to control signals to the robot actuators. This Master’s Thesis presents a study of smart walkers as assistive devices, as well as, control interaction strategies between the human, the robotic device and the environment. Moreover, we developed a robot environment interaction strategy which was evaluated in simulation and validated in real environment. The results showed the reliability of this strategy and boosted the development of a Human-Robot-Environment Interaction strategy in the same robotic device by adding information of the user’s legs. Finally, we validated this strategy in real environment with static and dynamic obstacles. The results show that the UFES CloudWalker adapts its behaviour accordingly changes in the environment and the user motion intentions.
  • Nenhuma Miniatura disponível
    Item
    Effects of human-robot interaction in smart walker-assisted locomotion using mixed reality scenarios
    (Universidade Federal do Espírito Santo, 2025-01-01) Loureiro, Matheus Penido; Frizera Neto, Anselmo; https://orcid.org/0000-0002-0687-3967; http://lattes.cnpq.br/8928890008799265; http://lattes.cnpq.br/5058609108829074 ; Lima, Eduardo Rocon de; https://orcid.org/0000-0001-9618-2176; http://lattes.cnpq.br/6623746131086816 ; Alsina, Pablo Javier; https://orcid.org/0000-0002-2882-5237; http://lattes.cnpq.br/3653597363789712
    The decline in neuromusculoskeletal function in older adults can significantly affect their motor control, independence, and walking ability, ultimately reducing their quality of life. With the global aging population on the rise, supporting independent mobility and enhancing rehabilitation techniques have become critical goals. The use of augmentative devices, such as smart walkers (SW) can help providing mobility assistance and enhancing residual movement capacity. SWs stand out among these devices by offering active physical support, fall prevention, as well as cognitive and navigation assistance. Despite these improvements, people may still experience frustration due to repetitive tasks and discomfort during recovery, which can lead to higher dropout rates in rehabilitation programs. In this context, integrating rehabilitation devices with mixed reality (MR) tools offers a promising approach for gait training and rehabilitation, potentially improving clinical outcomes, motivation, and adherence to therapy. However, concerns about MR-induced cybersickness and potential changes in gait patterns remain. This master's dissertation investigates the gait parameters of fourteen elderly participants under three conditions: free walking (FW), SW assisted gait (AG), and SW assisted gait combined with MR assistance (AGMR). Kinematic data from both lower limbs were captured using a 3D wearable motion capture system to evaluate the kinematic changes associated with SW use and how MR integration may influence these adaptations. Additionally, cybersickness symptoms were assessed using a questionnaire after the AGMR condition. The results reveal significant kinematic differences between FW and both AG and AGMR,with reductions in sagittal plane motion of 16%, 25%, and 38% at the hip, knee, and ankle, respectively, in both AG and AGMR compared to FW. However, no significant differences were observed between AG and AGMR gait parameters, and no MR-related adverse effects were reported. These findings suggest that MR can be effectively incorporated into walker-assisted gait rehabilitation without negatively impacting kinematic performance, while offering potential benefits for motivation and therapy adherence.
  • Nenhuma Miniatura disponível
    Item
    Handling complex smart walker interaction strategies with Behavior Trees
    (Universidade Federal do Espírito Santo, 2022-10-24) Cardoso, Paula Alcantara; Frizera Neto, Anselmo; https://orcid.org/0000000206873967; http://lattes.cnpq.br/8928890008799265; Alsina, Pablo Javier; Lima, Eduardo Rocon de
    Walking is an activity that requires mastering stability and precision in order to be learned. Between the ages of 8 and 10, gait becomes an automatic activity, which once mastered does not depend on the attention of individuals. Mechanical factors and diseases, such as Parkinson’s and spinal cord injuries, as well as physical and cognitive conditions, can contribute to the quality of gait, which starts to present different types of disorders. With the increase of life expectancy and the share of the population over 65 years old, there is a concern regarding the demands for accessibility, rehabilitation and assistance, since they suffer from the reduction of their balance and mobility capacities. In this context, mobility assistance devices are valuable options to meet the needs of their users. Walkers, in particular, are alternatives for those who have residual motor skills. Its adoption postpones the use of wheelchairs and encourages the independence of its users. The inclusion of technologies, such as sensors and actuators, in the structure of walkers makes them intelligent, as they allow the incorporation of new functionalities that provide greater and better assistance for locomotion. The devices called robotic or smart walkers have several modules and control strategies that make their operation - and understanding - complex. This Master’s Dissertation proposes the inclusion of an artificial intelligence algorithm, based on a hierarchical architecture, for decision making that is capable of integrating several control strategies human-robot-environment interactions in the UFES CloudWalker. The algorithm implemented was the Behavior Tree, a structure that allows switching between controllers in a modular and reactive way. The system was validated by volunteers who performed a series of tasks aimed at evaluating the global performance of the smart walker. As a result, the system proved to be able to handle complex interactions between user, walker and the environment during navigation.
  • Nenhuma Miniatura disponível
    Item
    Metodologia para desenvolvimento de sistemas robóticos: estudo de caso em dispositivos de reabilitação de marcha
    (Universidade Federal do Espírito Santo, 2025-06-03) Bezerra, Marcio Loureiro; Lima, Eduardo Rocon de; https://orcid.org/0000-0001-9618-2176; http://lattes.cnpq.br/6623746131086816 ; Mello, Ricardo Carminati de; https://orcid.org/0000-0003-0420-4273; http://lattes.cnpq.br/1569638571582691; Frizera Neto, Anselmo; https://orcid.org/0000-0002-0687-3967; http://lattes.cnpq.br/8928890008799265; http://lattes.cnpq.br/9701318914501137 ; Rodríguez Díaz, Camilo Arturo; https://orcid.org/0000-0001-9657-5076; http://lattes.cnpq.br/2410092083336272; Alsina, Pablo Javier; https://orcid.org/0000-0002-2882-5237; http://lattes.cnpq.br/3653597363789712
    Robotics has advanced with innovations in mechanics, computing, and electronics, expanding its applications. However, software development for robots still faces challenges due to the complexity of tasks and the diversity of hardware and environments. Although tools like ROS facilitate research, it is essential to structure software and hardware architectures systematically. This work proposes a methodology to standardize the development of robotic systems for gait rehabilitation and assistance. The methodology was validated in two case studies. In the first case study, the proposed methodology was applied to two robotic walkers (UFES vWalker and UFES WalkerXR), using ROS and ROS2, for validation and evaluation based on technical analyses and user experience. Positive results were obtained for the technical analysis, with a maximum standard deviation in ROS publishing frequency of 13.24% for the vWalker and 7.43% for the WalkerXR within the specified frequency. Additionally, the device acceptability level was satisfactory according to the System Usability Scale (SUS) , with scores of 77 for the vWalker and 86 for the WalkerXR. In the second case study, a telepresence system was developed by integrating a mobile robot, a 360° camera, and the Discover2Walk device. Mapping tests confirmed the system’s accuracy, with an average error of 0.52% in measured distances. Furthermore, it was possible to synchronize the movement of the mobile robot with the Discover2Walk treadmill, ensuring an immersive experience for the remote user. The proposed methodology demonstrated effectiveness by providing a more organized and predictable development process. The results confirm that the approach favors the creation of robust and adaptable solutions. However, the need for testing in new scenarios should still be explored. Future work suggests applying the methodology to other areas of robotics, conducting long-term studies with real users, and incorporating artificial intelligence to personalize assistive systems.
  • Nenhuma Miniatura disponível
    Item
    Virtualização de ambientes em tempo real para interação multimodal : teleoperação com uso de realidade mista e feedback háptico
    (Universidade Federal do Espírito Santo, 2025-09-06) Vieira, Igor Batista; Mello, Ricardo Carminati de; ttps://orcid.org/0000-0003-0420-4273; http://lattes.cnpq.br/1569638571582691; Frizera Neto, Anselmo; https://orcid.org/0000-0002-0687-3967; http://lattes.cnpq.br/8928890008799265; https://orcid.org/0009-0007-9547-4485; http://lattes.cnpq.br/; Rodríguez Díaz, Camilo Arturo; https://orcid.org/0000-0001-9657-5076; http://lattes.cnpq.br/2410092083336272; Alsina, Pablo Javier; https://orcid.org/0000-0002-2882-5237; http://lattes.cnpq.br/3653597363789712
    Conventionalteleoperationinterfaces, basedontwo-dimensionalmonitorsandnon immersive controllers, present significant limitations for human-robot interaction. The absence of depth perception, restricted field of view, and high cognitive load hinder the operator’s ability to build an accurate mental model of the remote envi ronment, reducing the effectiveness of robot control. In this context, the integration of immersive technologies and haptic devices emerges as an alternative to enhance the user’s sense of presence, overcome perceptual barriers, and make teleoperation more natural and efficient. To address these challenges, this dissertation proposes the development of a multi modal teleoperation system, composed of a mobile robotic platform equipped with perception sensors, a simultaneous localization and mapping (SLAM) module, and an immersive interface based on Virtual Reality integrated with a haptic device. The architecture was designed to operate in a distributed manner, with processing shared between the robot and the operator station, enabling the construction of a low-latency digital twin. Two experimental studies were conducted: the first vali dated the accuracy of the visual mapping system compared to classical approaches, while the second evaluated the haptic interface in user teleoperation tasks. The results obtained confirmed the hypothesis that the combination between Vir tual Reality and haptic feedback provides a telepresence experience superior to tra ditional solutions. The system demonstrated robustness in environment mapping, low response time in data transmission, and an increased sense of immersion re ported by the users. Specifically, the user study demonstrated that the immersive interface was able to reduce the average number of collisions from 3.00 to less than 0.3 and decrease the perceived workload (NASA-TLX) by more than 50%. These f indings highlight the potential of the proposed approach as a relevant contribution to the advancement of robotic teleoperation, with possible applications in remote inspection, hazardous environments, and human-robot collaboration systems.