Publicação
Natural language-based human-robot control
| Resumo: | With the increase in the number of robots arriving at our homes, it is important to find an easy and efficient way to communicate with them. Natural language is the most natural form of communication between humans, so its use by users to communicate with robots, with no knowledge of how they work, is an added value to control them. We present a solution that allows us to interact with a robot in a natural way, so it is easier for human-robot cooperation to happen. This solution includes a method of transforming the information in natural language into controls that a robot can perform. We implement this solution in the specific case of indoor navigation. Finally, we evaluate the performance and interactivity of our approach, by having users, without previous knowledge of robotic control, controlling a robot in a simulated environment. |
|---|---|
| Autores principais: | Bernardo, João Miguel Nunes |
| Assunto: | Natural language Human-robot interaction Robot navigation Lingua natural Interação homem-máquina Navegação robótica |
| Ano: | 2019 |
| País: | Portugal |
| Tipo de documento: | dissertação de mestrado |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | ISCTE |
| Idioma: | inglês |
| Origem: | Repositório ISCTE |
| Resumo: | With the increase in the number of robots arriving at our homes, it is important to find an easy and efficient way to communicate with them. Natural language is the most natural form of communication between humans, so its use by users to communicate with robots, with no knowledge of how they work, is an added value to control them. We present a solution that allows us to interact with a robot in a natural way, so it is easier for human-robot cooperation to happen. This solution includes a method of transforming the information in natural language into controls that a robot can perform. We implement this solution in the specific case of indoor navigation. Finally, we evaluate the performance and interactivity of our approach, by having users, without previous knowledge of robotic control, controlling a robot in a simulated environment. |
|---|