Behavioural attentiveness patterns analysis – detecting distraction behaviours

• Autor(a) principal: Amaro, Bruno Filipe Viana
• Data de Publicação: 2018
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: https://hdl.handle.net/1822/66009
• topic: Human-robot interaction; Zeca robot; Distraction patterns; Emotional states; Machine learning; Interação humano-robô; Robô zeca; Padrões de distração; Estado emocional; Aprendizagem da máquina; Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática

The capacity of remaining focused on a task can be crucial in some circumstances. In general, this ability is intrinsic in a human social interaction and it is naturally used in any social context. Nevertheless, some individuals have difficulties in remaining concentrated in an activity, resulting in a short attention span. Children with Autism Spectrum Disorder (ASD) are a special example of such individuals. ASD is a group of complex developmental disorders of the brain. Individuals affected by this disorder are characterized by repetitive patterns of behaviour, restricted activities or interests, and impairments in social communication. The use of robots has already proved to encourage the developing of social interaction skills lacking in children with ASD. However, most of these systems are controlled remotely and cannot adapt automatically to the situation, and even those who are more autonomous still cannot perceive whether or not the user is paying attention to the instructions and actions of the robot. Following this trend, this dissertation is part of a research project that has been under development for some years. In this project, the Robot ZECA (Zeno Engaging Children with Autism) from Hanson Robotics is used to promote the interaction with children with ASD helping them to recognize emotions, and to acquire new knowledge in order to promote social interaction and communication with the others. The main purpose of this dissertation is to know whether the user is distracted during an activity. In the future, the objective is to interface this system with ZECA to consequently adapt its behaviour taking into account the individual affective state during an emotion imitation activity. In order to recognize human distraction behaviours and capture the user attention, several patterns of distraction, as well as systems to automatically detect them, have been developed. One of the most used distraction patterns detection methods is based on the measurement of the head pose and eye gaze. The present dissertation proposes a system based on a Red Green Blue (RGB) camera, capable of detecting the distraction patterns, head pose, eye gaze, blinks frequency, and the user to position towards the camera, during an activity, and then classify the user's state using a machine learning algorithm. Finally, the proposed system is evaluated in a laboratorial and controlled environment in order to verify if it is capable to detect the patterns of distraction. The results of these preliminary tests allowed to detect some system constraints, as well as to validate its adequacy to later use it in an intervention setting.