Name: RICARDO CARMINATI DE MELLO
Publication date: 01/03/2018
Advisor:
Name |
Role |
|---|---|
| ANSELMO FRIZERA NETO | Advisor * |
| MOISÉS RENATO NUNES RIBEIRO | Co-advisor * |
Examining board:
| Name |
Role |
|---|---|
| ANDRE FERREIRA | External Examiner * |
| ANSELMO FRIZERA NETO | Advisor * |
| CARLOS ANDRES CIFUENTES GARCIA | External Examiner * |
| MOISÉS RENATO NUNES RIBEIRO | Co advisor * |
Summary: 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 offer to users, patients, medical staff, and family members. 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. 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. UFES CloudWalker's overall system and architecture are described and proposed. Nevertheless, as network and cloud parameters (e.g.,end-to-end latency, information loss, and availability) can largely affect 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 first 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.
