From Robot-Assisted Intervention to New Generation of Autism Screening: an Engineering Implementation Beyond the Technical Approach

Autism spectrum disorder (ASD) is a neurodevelopmental disorder that affects people from birth, whose symptoms are found in the early developmental period. The ASD diagnosis is usually performed through several sessions of behavioral observation, exhaustive screening, and manual coding behavior. The early detection of ASD signs in naturalistic behavioral observation may be improved through Social Assistive Robotics (SAR) and technological-based tools for an automated behavior assessment. Robot-assisted tools using Child-Robot Interaction (CRI) theories have been of interest in intervention for children with Autism Spectrum Disorder (CwASD), elucidating faster and more significant gains from the diagnosis and therapeutic intervention when compared with classical methods. Additionally, using computer vision to analyze the childs behaviors and automated video coding to summarize the responses would help clinicians to reduce the delay of ASD diagnosis. Despite the increment of researches related to SAR, achieving a plausible Robot-Assisted Diagnosis (RAD) for CwASD remains a considerable challenge to the clinical and robotics community. The work of specialists regarding ASD diagnosis is hard and labor-intensive, as the conditions manifestations are inherently heterogeneous and make the process more difficult. In addition, the aforementioned complexity may be the main reason for the slow progress in the development of SAR with diagnostic purpose. Also, there still is a lack of guidelines on how to select the appropriate robotic features, such as appearance, morphology, autonomy level, and how to design and implement the robots role in the CRI. Thus, this Ph.D. Thesis provides a comprehensive Robot-Assisted intervention for CwASD to assess autism risk factors for an autism diagnostic purpose. More specifically, two studies were conducted to analyze and validate the system performance. Through statistical data analysis, different behavior pattern of the CwASD group were identified, which suggest that these patterns can be used to detect autism risk factors through robot-based interventions. To increase the scope of this research, a theoretical conceptualization of the pervasive version of the multimodal environment was described as well as a participatory design methodology was designed and implemented on the Colombian autism community, providing, a set of guidelines regarding the design of a social robot-device suitable to be applied for robot-assisted intervention for CwASD