Proposta de uma metodologia para a obtenção de vocabulários de gestos intuitivos para a interação homem-robô

• Autor(a) principal: Santos, Clebeson Canuto dos
• Data de Publicação: 2016
• Tipo de documento: Dissertação
• Idioma: por
• Título da fonte: Repositório Institucional da UFS
• Texto Completo: https://ri.ufs.br/handle/riufs/3358
• topic: Computação; Interação homem-máquina; Linguística; Gestos; Interação homem-robô; Vocabuláario de gestos; Gestos intuitivos; Processamento de dados; Human-robot interaction; Gesture vocabulary; Intuitive gestures; CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO

Development in robotics has been accelerated in the last decades. Mainly due to the advancement in technology, especially computers. However, even having enough technology to create robots that can participate in the daily lives of people, robotics has not become popular, once that the most robots purchased by people still fall into the category of toys, monitoring systems, among others. The search for such robots is due to the fact that their repertoire of tasks is so much limited and predetermined, which ultimately facilitate the interaction between users and robots. Meanwhile, more sophisticated robots, in most cases, can only be used by specialized people, because they have a larger task repertoire, which needs more complex interaction mechanisms. In others areas, such as computing, the communication interface was of fundamental importance for its popularization. This way, the construction of friendly communication interfaces between people and robots can be the key to robotics can be widespread in the actual society. However, not every interface can provide an easy and e cient communication. An e ective interface should be as intuitive as possible, what, according the psycholinguistics studies, can be achieved through the use of spontaneous gestures. Therefore, knowing the di cult to nd a procedure to obtain intuitive gesture vocabularies, this master thesis proposes a methodology that, based on psycholinguistics and HCI (Human-Computer Interaction) studies, is suitable to obtain intuitive gesture vocabularies to be used in HRI (Human-Robot Interaction). Therefore, after the application of this methodology, it was possible to notice that it was able to lead to results as good as those obtained by another methodology which is already used and accepted in HCI. Moreover, the proposed methodology has some distinct characteristics, such as the possibility to obtain more complex vocabularies, that can lead to more intuitive gesture vocabularies and which, in form, are more likely to be robust. In addition, by submitting the obtained gestures to a recognizer, an average hit rate of 77,5% was obtained, which, even though it is not so high, can be considered good enough, since some of the gestures are performed with both arms, increasing the complexity of the recognition task. Thus, at the end of this master thesis, some complementary works are proposed, which must be carried out in order to move further towards the development of intuitive interfaces for human-robot interaction.