Design and Implementation of Electronic Architecture for Cloud Robotics and Human-Robot-Environment Interaction Strategy Applied to SmartWalker

• Ano de defesa: 2021
• Autor(a) principal: Rocha Júnior, Joelson de Carvalho
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado em Engenharia Elétrica; Centro Tecnológico; UFES; Programa de Pós-Graduação em Engenharia Elétrica
• Palavras-chave em Português: Interação Humano-robô-Ambiente; dispositivos assistivos; UFES CloudWalker; andadores inteligentes; robótica em nuvem; subject.br-rjbn; Engenharia Elétrica
• Link de acesso: http://repositorio.ufes.br/handle/10/15626

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.