Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Navegação no exterior de cadeira de rodas inteligente

Authors: Gomes, João Rafael Penacho Silva;

Navegação no exterior de cadeira de rodas inteligente

Abstract

Atualmente, a robótica avança a um ritmo impressionante desde robôs capazes de realizar tarefas domésticas como limpezas, a carro autónomos, ou robôs a praticarem desporto como o futebol. Nos últimos anos os avanços na robótica de serviços têm sido cada vez mais significativos, sendo o seu objetivo o auxílio do ser humano nas tarefas do dia a dia. Estes avanços têm o objetivo de melhorar a qualidade de vida das pessoas, usando, por exemplo, uma cadeira de rodas para o efeito. O objetivo desta dissertação, assim como o requisito do projeto, é a automatização da navegação, mapeamento e localização de uma cadeira de rodas em ambientes exteriores. Foram integrados e ajustados algoritmos de mapeamento e localização, assim como de navegação. Para isto foram estudadas tecnologias usadas em projetos semelhantes, assim como tecnologias existentes usadas para cumprir requisitos como os do projeto. Por fim é apresentado a implementação de um sistema de mapeamento, localização e navegação autónoma numa cadeira de rodas. São indicados os sensores tidos em consideração para integrar o sistema, assim como as razões da escolha de uma câmara estereoscópica e a sua integração na cadeira. A escolha, assim como a implementação, do algoritmo de SLAM baseado em visão para mapeamento e localização em ambientes exteriores da cadeira de rodas, RTAB-Map, é também aqui apresentada, assim como a escolha e implementação de algoritmos para a navegação autónoma, usando um pacote de ROS, move base, para o efeito. São apresentados os testes realizados ao sistema para validar o seu funcionamento, quer o seu mapeamento e localização, como a navegação autónoma da cadeira. Os resultados obtidos mostram que a cadeira consegue mapear o ambiente que a rodeia, podendo gerar mapas de larga escala, sendo realizado um mapeamento com uma distância percorrida de cerca de 2.3 km, assim como navegar nesses mesmos mapas, desviando-se de obstáculos já mapeados e de obstáculos não mapeados, desde que, estes se encontrem no campo de visão da câmara.

Currently, robotics advances at an impressive pace from robots capable of carrying out household tasks such as cleaning, to autonomous cars, or robots to practice sports such as football. In recent years, advances in service robotics have been increasingly significant, with the aim of helping human beings in their daily tasks. These advances are intended to improve people's quality of life, using, for example, a wheelchair for this purpose. The objective of this dissertation, as well as the project requirements, is the automation of navigation, mapping and location of a wheelchair in outdoor environments. Mapping and location algorithms, as well as navigation algorithms, were integrated and adjusted. For this, technologies used in similar projects were studied, as well as existing technologies used to fulfil requirements such as those of the project. Finally, the implementation of a mapping, location and autonomous navigation system in a wheelchair is presented. The sensors taken into account to integrate the system are indicated, as well as the reasons for choosing a stereoscopic camera and its integration in the chair. The choice, as well as the implementation, of the vision-based SLAM algorithm for mapping and locating in outdoor wheelchair environments, RTAB-Map, is also presented here, as well as the choice and implementation of algorithms for autonomous navigation using a ROS package, move base, for this purpose. The tests carried out on the system to validate its operation are presented, both its mapping and location, and the chair's autonomous navigation. The results obtained show that the chair is able to map the environment that surrounds it, being able to generate large-scale maps, being mapped a covered distance of about 2.3 km, as well as navigating these same maps, avoiding previously mapped obstacles and unmapped obstacles, provided that they are in the camera's field view.

Mestrado em Engenharia Eletrónica e Telecomunicações

Country
Portugal
Related Organizations
Keywords

Localização, SLAM, Cadeira de rodas inteligente, ROS, Robótica, Mapeamento, Navegação

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!