Publicação
Semantic navigation applied to narrow passages for intelligent wheelchairs
| Resumo: | With the development of robotics technology, new opportunities for improving the quality of life of people with mobility impairments arise. The IntellWheels project was born with the goal of developing a hardware and software kit that can turn a motorized wheelchair into an autonomous Intelligent Wheelchair. This dissertation fits into this project on the topic of indoor navigation with the goal of adding a semantic layer to the navigation framework. Semantic in robotics is the ability of a robot to understand its environment. In the case of an Intelligent Wheelchair, this is especially important considering it is a robot that carries a passenger. A solution was developed where concepts of semantic navigation are used to tackle the problem of crossing narrow passages, building an additional mapping layer where these passages are automatically detected and marked on the map and an extra planning layer that takes in this semantic information and makes decisions for controlling the lower-level planners. In order to validate this solution tests, in both simulated and real-world environments, were performed to verify if the individual components worked as intended. This thesis resulted in an improvement of the indoor navigation capabilities of the framework and is a base for further development in the area of semantic navigation of Intelligent Wheelchairs. |
|---|---|
| Autores principais: | Correia, Daniel Pinto |
| Assunto: | Semantic navigation Planning Mapping Narrow passages ROS Intelligent wheelchair Navigation in indoor environment |
| Ano: | 2022 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade de Aveiro |
| Idioma: | inglês |
| Origem: | RIA - Repositório Institucional da Universidade de Aveiro |
| Resumo: | With the development of robotics technology, new opportunities for improving the quality of life of people with mobility impairments arise. The IntellWheels project was born with the goal of developing a hardware and software kit that can turn a motorized wheelchair into an autonomous Intelligent Wheelchair. This dissertation fits into this project on the topic of indoor navigation with the goal of adding a semantic layer to the navigation framework. Semantic in robotics is the ability of a robot to understand its environment. In the case of an Intelligent Wheelchair, this is especially important considering it is a robot that carries a passenger. A solution was developed where concepts of semantic navigation are used to tackle the problem of crossing narrow passages, building an additional mapping layer where these passages are automatically detected and marked on the map and an extra planning layer that takes in this semantic information and makes decisions for controlling the lower-level planners. In order to validate this solution tests, in both simulated and real-world environments, were performed to verify if the individual components worked as intended. This thesis resulted in an improvement of the indoor navigation capabilities of the framework and is a base for further development in the area of semantic navigation of Intelligent Wheelchairs. |
|---|