Publicação
Human-aware Autonomous Robot Navigation For Industrial Applications
| Resumo: | Autonomous robots have the skill to navigate autonomously within an environment, that can include static and dynamic obstacles, such as humans. Human–Robot Interaction (HRI) arises from robot navigation and is itself challenging due to its inherent complexity and behaviours that may be performed on both robot and human ends. Their interaction can emerge explicitly, i.e., the interaction is desired in order to execute a collaborative task, or implicitly, because humans and robots cross paths and will have to interact, in which the robot must take into consideration social constraints that can result in discomfort for humans. The goal of this dissertation is to develop and test a human-aware autonomous navi- gation system within the ROS architecture. This system will address implicit interactions so that humans feel comfortable with the robot navigation and can co-exist and work in the same workplace. The target of human-aware navigation is to add, to an already existing safety the hu- mans feel towards the robot in common autonomous navigation, a feeling of acceptance e and comfort towards the robot. For that, it is developed a navigation system that employs human-like expected behaviours such as going straight to the goal via an optimal path. This results in a more expectable navigation that does not disturb the surrounding people from their current tasks and can contribute to a more productive work environment. The navigation system developed combines collision-free navigation with human awareness, in order to contribute to the HRI paradigm standardization in a manufactur- ing indoor context. |
|---|---|
| Autores principais: | Félix, André Fialho |
| Assunto: | Autonomous Indoor Robot Navigation Human-Robot Interaction - HRI Human-awareness Robot Operating System |
| Ano: | 2022 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade Nova de Lisboa |
| Idioma: | inglês |
| Origem: | Repositório Institucional da UNL |
| Resumo: | Autonomous robots have the skill to navigate autonomously within an environment, that can include static and dynamic obstacles, such as humans. Human–Robot Interaction (HRI) arises from robot navigation and is itself challenging due to its inherent complexity and behaviours that may be performed on both robot and human ends. Their interaction can emerge explicitly, i.e., the interaction is desired in order to execute a collaborative task, or implicitly, because humans and robots cross paths and will have to interact, in which the robot must take into consideration social constraints that can result in discomfort for humans. The goal of this dissertation is to develop and test a human-aware autonomous navi- gation system within the ROS architecture. This system will address implicit interactions so that humans feel comfortable with the robot navigation and can co-exist and work in the same workplace. The target of human-aware navigation is to add, to an already existing safety the hu- mans feel towards the robot in common autonomous navigation, a feeling of acceptance e and comfort towards the robot. For that, it is developed a navigation system that employs human-like expected behaviours such as going straight to the goal via an optimal path. This results in a more expectable navigation that does not disturb the surrounding people from their current tasks and can contribute to a more productive work environment. The navigation system developed combines collision-free navigation with human awareness, in order to contribute to the HRI paradigm standardization in a manufactur- ing indoor context. |
|---|