Abstract
Recent years have witnessed the proliferation of social robots in various domains including special education. However, specialized tools to assess their effect on human behavior, as well as to holistically design social robot applications, are often missing. In response, this work presents novel tools for analysis of human behavior data regarding robot-assisted special education. The objectives include, first, an understanding of human behavior in response to an array of robot actions and, second, an improved intervention design based on suitable mathematical instruments. To achieve these objectives, Lattice Computing (LC) models in conjunction with machine learning techniques have been employed to construct a representation of a child’s behavioral state. Using data collected during real-world robot-assisted interventions with children diagnosed with Autism Spectrum Disorder (ASD) and the aforementioned behavioral state representation, time series of behavioral states were constructed. The paper then investigates the causal relationship between specific robot actions and the observed child behavioral states in order to determine how the different interaction modalities of the social robot affected the child’s behavior.
Highlights
One of the areas where social robots have been applied in recent years is education, as well as special education for children
Numerous studies have demonstrated the use of social robots toward improving social skills such as joint attention [4,5,6]
Children participants were recruited based on a diagnosis of Level I Autism Spectrum Disorder (ASD) [41] at the outpatient Pediatric Neurology clinic of the 4th Department of Pediatrics of the Papageorgiou General Hospital (PGH) in Thessaloniki, Greece
Summary
One of the areas where social robots have been applied in recent years is education, as well as special education for children. The two main contributions of the present paper are summarized as follows: (1) the development of novel computational instruments for the representation of behavioral states without the need for manual behavior annotation, and (2) a novel data analysis methodology for providing a better insight into induced child behavior in response to robot actions. It is worth noting that in this work, assessments of the causal relationship between stimuli and child behavior were conducted by examining an existing robot-assisted therapeutic protocol in a real-world therapeutic setting, as opposed to child–robot interaction activities designed for data collection purposes. Note that human–robot interaction may involve more complex data than merely real number measurements; for instance, it may involve structural data representing human body posture and sets of features, among others In the latter context, a novel mathematical background for rigorous analysis is required that may accommodate disparate types of data as explained next.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
