UFES CloudWalker: a cloud-enabled cyber-physical system for mobility assistance

• Ano de defesa: 2018
• Autor(a) principal: Mello, Ricardo Carminati de
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: eng
• 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: Andador robótico; Engenharia elétrica; Engenharia biomédica; Robótica - Reabilitação; Robótica na medicina; Equipamentos de autoajuda para deficientes; Computação em nuvem; Engenharia Elétrica; 621.3
• Link de acesso: http://repositorio.ufes.br/handle/10/9573

Smart walkers are robotic devices which rely on a series of sensors, actuators, and interfaces to provide mobility assistance functionalities to mobility impaired individuals. The increased computational complexity demanded by recent algorithms and techniques applied to mobile, healthcare, and social robotics, often limited by the robot's embedded hardware, together with advancements on networking and cloud computing enabled the so-called cloud robotics paradigm. This dissertation proposes, implements, and validates a cloud-enabled cyber-physical system for mobility assistance. The system, named UFES CloudWalker, envisions the integration of smart walkers and remote cloud computing platforms, aiming at expanding smart walkers' capabilities and the features those devices can o er to users, patients, medical sta , and family members. UFES CloudWalker explores cloud robotics concepts to unleash smart walker's capabilities despite possible hardware limitations. This work presents a study on mobility assistive devices, focused on smart walkers, and a study on cyber-physical systems and cloud robotics, focused on its applications in healthcare, and discuss the challenges and potentialities of combining cyber-physical systems and cloud robotics concepts concepts in smart walkers. Nevertheless, as network and cloud parameters (e.g.,end-to-end latency, packet loss, and availability) can largely a ect control on such class of systems, two experiments sets are performed to preliminarily validate UFES CloudWalker's feasibility and to understand the impacts of the network and cloud quality of service over the end user's quality of experience. The system is implemented for the rst time by integrating an in-house developed smart walker, the UFES Smart Walker, and a cloud platform located in an edge data center. To complete the validation of the UFES CloudWalker, the implemented system is used in an experiment set built over a mobility assistance service scenario. The results obtained argue for the feasibility of such system even under unfavorable network quality scenarios, opening a door for the development of a new generation of smart walkers, in which the devices are enabled by the cloud and able to cope with future connected healthcare systems.