Many mobility impaired users are unable to operate a powered wheelchair safely, without causing harm to themselves, others, and the environment. Smart wheelchairs that assist or replace user control have been developed to cater for these users, utilising systems and algorithms from autonomous robots. Despite a sustained period of research and development of robotic wheelchairs, there are very few available commercially. This thesis describes work towards developing a navigation system that is aimed at being retro-fitted to powered wheelchairs. The navigation system developed takes a systems engineering approach, integrating many existing open-source software projects to deliver a system that would otherwise not be possible in the time frame of a master's thesis. The navigation system introduced in this thesis is aimed at operating in an unstructured indoor environment, and requires no a priori information about the environment. The key components in the system are: obstacle avoidance, map building, localisation, path planning, and autonomously travelling towards a goal. The test electric wheelchair was instrumented with the following: a laptop, a laser scanner, wheel encoders, camera, and a variety of user input methods. The user interfaces that have been implemented and tested include a touch screen friendly graphical user interface, keyboard and joystick.

Independent mobility is critical to quality of life for people of all ages, and impaired mobility leaves one with both physical and mental disadvantages. Unfortunately, there are some individuals unable to operate an electric wheelchair due to physical, perceptual, or cognitive deficits. The prime objective of this research was to develop a prototype system which can provide mobility assistant to individuals who would otherwise find it difficult or impossible to operate a power wheelchair. To accomplish this goal, a prototype system consisting of several components including an embedded microcontroller and multiple sensors has been designed which can be added to a standard power wheelchair and make it smart. The control system algorithm designed for this prototype model is based on the fuzzy logic control theory and its main purpose is to augment the user ability to navigate the wheelchair and will provide a safe and comfortable journey to the user.

Submitted by Geandra Rodrigues (geandrar@gmail.com) on 2018-04-10T14:32:43Z No. of bitstreams: 1 guilhermemarinsmaciel.pdf: 9983956 bytes, checksum: 320096faa3f7fde371bb72a6ab3faba1 (MD5) / Approved for entry into archive by Adriana Oliveira (adriana.oliveira@ufjf.edu.br) on 2018-04-10T14:56:25Z (GMT) No. of bitstreams: 1 guilhermemarinsmaciel.pdf: 9983956 bytes, checksum: 320096faa3f7fde371bb72a6ab3faba1 (MD5) / Made available in DSpace on 2018-04-10T14:56:25Z (GMT). No. of bitstreams: 1 guilhermemarinsmaciel.pdf: 9983956 bytes, checksum: 320096faa3f7fde371bb72a6ab3faba1 (MD5) Previous issue date: 2018-01-22 / O campo da robótica assistiva lida com as tecnologias voltadas para pessoas com imparidades físicas. Alguns deficientes possuem tetraplegia e não podem movimentar os membros inferiores e superiores mas, dependendo do grau da lesão, podem acionar as musculaturas do ombro e pescoço. Visando este grupo, o presente trabalho propõe uma arquitetura de sistema semiautônomo para cadeiras de rodas inteligentes (CRIs) baseada na plataforma Robotic Operating System (ROS), embarcado em uma Raspberry Pi 3, com ênfase em baixo custo e não necessidade de localização global. É apresentada uma proposta de interface homem-máquina baseada em comandos de voz, na qual uma central de controle utiliza uma Rede de Petri para configurar e administrar o sistema. As transições são disparadas por um conjunto de frases. Depois de cada evento, o usuário recebe uma frase de retorno através de alto-falantes. Para o sistema de navegação é utilizado um controle compartilhado de velocidade, em que, utiliza-se uma Unidade de Medição Inercial (IMU) para reconhecer o padrão de movimento desejado através de medições da inclinação da cabeça do usuário. Paralelamente, um algoritmo inteligente emprega uma câmera de profundidade para reconhecer os obstáculos nos arredores e atuar em conjunto no controle, de modo a aumentar a manobrabilidade e segurança. Uma metodologia de travessia de passagens estreitas de forma autônoma é uma outra técnica proposta. Nesta técnica duas extremidades de um acesso delgado são reconhecidas por meio da câmera de profundidade e um controlador não-linear realiza a tarefa. Nos resultados, as metodologias propostas foram analisadas através de modelos de CRIs em Matlab e na plataforma de simulação Gazebo. Para testes práticos, foi utilizado um robô diferencial Pionner-P3DX. Os resultados exibidos nesta dissertação se revelaram promissores, evidenciando a aplicabilidade do sistema. / The field of assistive robotics works with technologies aimed at people with phy-sical impairments, some handicapped have quadriplegia and cannot move the lower and upper limbs, but, depending on the degree of injury, the shoulder and neck musculature can be used. Aiming at this group, the present work proposes a semiautonomous sys-tem architecture for smart wheelchairs based on the Robotic Operating System (ROS) platform, embedded in a Raspberry Pi 3, with emphasis on low cost and no need for global localization. A proposal for a human-machine-interface based on voice commands is presented, where the control center uses a Petri Net to configure and administer the system. Transitions are triggered by a set of phrases and after each event, the user re-ceives a return phrase through speakers. For the navigation system, a shared control of velocity is used. An Inertial Measurement Unit (IMU) is applied to recognize the desired movement pattern through measurements of the user's head inclination. In parallel, an intelligent algorithm employs a depth camera to recognize obstacles around and work together in control, increasing maneuverability and safety. Another technique proposed is a methodology of autonomous narrow passages crossing, the depth camera recognizes the borders of thin access and a non-linear controller performs the task. In the results, the proposed methodologies were analyzed using simulated models in the Matlab and the Gazebo platform. For practical tests, a Pioneer-P3DX differential robot was used, the results presented in this dissertation were promising, evidencing the applicability of the system.

En France, plus de 2 enfants sur 1000 naissent avec une « Paralysie Cérébrale », provoquée par des lésions au niveau cérébral. Cette pathologie non-évolutive, entraine des troubles de la motricité et du processus attentionnel. Certains de ces enfants n’ont pas accès au fauteuil roulant électrique pour des raisons de sécurité, car susceptibles de commettre des erreurs dangereuses de pilotage. Ils n’ont donc pas accès à l’autonomie et se déplacent en fauteuil manuel poussé par une tierce personne. Or, aujourd’hui les études médicales du domaine font consensus sur la nécessité de l’accession au déplacement autonome, indispensable pour le développement personnel, intellectuel et la participation sociale de toute personne, handicapée ou non. Ce travail de thèse a pour but de développer un système optronique adaptable, permettant de transformer un fauteuil roulant électrique classique, en fauteuil roulant semi-autonome. Ceci signifie que l’utilisateur garde le contrôle de la direction et de la vitesse du fauteuil, mais que des capteurs peuvent inhiber les commandes empêchant les situations de basculement (trottoirs, escaliers, etc.) ou de collision frontale. La priorité est placée sur un dispositif constitué d’une combinaison de capteurs pouvant s’adapter sur les différents modèles existants de fauteuil en respectant leur encombrement initial. Tous les capteurs utilisés ou conçus pour l’objectif recherché, doivent maintenir leurs performances dans tous les environnements (intérieur, extérieur, fort ensoleillement, goudron mouillé, etc.). La consommation énergétique totale ne doit pas excéder quelques Watts. Concernant l’anticollision frontale et le passage de portes, nous avons développé une solution associant pour chaque côté du fauteuil un double capteur infrarouge et un capteur à ultrasons. Les capteurs infrarouges, développés en interne, sont conçus pour avoir des zones de protection cylindriques, permettant de détecter efficacement les passages dégagés de la taille du fauteuil et gérer les angles grâce au double capteur. Le capteur à ultrasons est destiné à gérer les obstacles fins foncés frontaux à courte distance pouvant échapper aux capteurs infrarouges. Concernant le contrôle de la planéité du sol et donc l’antibasculement, un lidar laser miniature trifaisceaux a été développé pour protéger chaque roue avec 1 m d’anticipation. Les données des différents capteurs seront couplées à l’odométrie du fauteuil afin de prendre les décisions sur les commandes. Les capteurs sont conçus pour assurer une anticipation suffisante jusqu’à 3km/h. Il s’agit d’une vitesse faible, mais adaptée à des utilisateurs qui dans le contexte actuel ne sont pas autorisés à piloter. Des tests en situation réelle dans des situations climatiques variées sont réalisés. / In France, more than 2 children out of 1000 are born with "Cerebral Palsy", caused by lesions on the cerebral level. This non-progressive pathology causes disorders of motor skills and the attentional process. Some of these children do not have access to the electric wheelchair for safety reasons, as they may make dangerous steering mistakes. They do not have access to autonomy and move in manual wheelchair pushed by a third person. However, today the medical studies of the field point on the need for accession to autonomous displacement, essential for personal development, intellectual and social participation of any person, disabled or not. This thesis aims to develop an adaptable optronic system, transforming a classic electric wheelchair into a semi-autonomous wheelchair. This means that the user keeps control of the direction and speed of the chair, but that sensors can inhibit controls that prevent from falls (sidewalks, stairs, etc.) or frontal collisions. The priority is placed on a device consisting of a combination of sensors that can adapt to the different existing models of wheelchair respecting their initial size. All sensors used or designed for the intended purpose, must maintain their performance in all environments (indoor, outdoor, strong sunlight, wet tar, etc.). The total energy consumption must not exceed a few Watts. For frontal collision avoidance and door entry, we have developed a solution combining for each side of the chair a double infrared sensor and an ultrasonic sensor. The infrared sensors, developed in-house, are designed to have cylindrical protection zones, making it possible to effectively detect the passages cleared of the size of the chair and to manage the angles thanks to the double sensor. The ultrasonic sensor is designed to handle dark fine end-face obstacles that can escape infrared sensors. The control of the flatness of the floor and therefore of the anti-tip, a LiDAR triple laser beams has been developed to protect each wheel with 1 m of anticipation. The data of the various sensors will be coupled to the odometry of the chair to make decisions on orders. The sensors are designed to provide sufficient anticipation up to 3 km/h. This is a low speed, but suitable for users who in the current context are not allowed to drive.Real-life tests in various climatic situations are carried out. Solutions are sought for chaotic floors or when the user moves a lot on the chair.