Design and validation of two embodied mirroring setups for interactive games with autistic children using the NAO humanoid robot

A bibliometric analysis of research trends of artificial intelligence in the treatment of autistic spectrum disorders

OBJECTIVE

Autism Spectrum Disorder (ASD) is a serious neurodevelopmental disorder that has become the leading cause of disability in children. Artificial intelligence (AI) is a potential solution to this issue. This study objectively analyzes the global research situation of AI in the treatment of ASD from 1995 to 2022, aiming to explore the global research status and frontier trends in this field.

METHODS

Web of Science (WoS) and PubMed databese were searched for Literature related to AI on ASD from 1995 to April 2022. CiteSpace, VOSviewer, Pajek and Scimago Graphica were used to analyze the collaboration between countries/institutions/authors, clusters and bursts of keywords, as well as analyses on references.

RESULTS

A total of 448 literature were included, the total number of literature has shown an increasing trend. The most productive country and institution were the USA, and Vanderbilt University. The authors with the greatest contributions were Warren, Zachary, Sakar, Nilanjan and Swanson, Amy. the most prolific and cited journal is Journal of Autism and Developmental Disorders, the highest cited and co-cited articles were Dautenhahn (Socially intelligent robots: dimensions of human-robot interaction 2007) and Scassellati B (Robots for Use in Autism Research 2012). "Artificial Intelligence", "Brain Computer Interface" and "Humanoid Robot" were the hotspots and frontier trends of AI on ASD.

CONCLUSION

The application of AI in the treatment of ASD has attracted the attention of researchers all over the world. The education, social function and joint attention of children with ASD are the most concerned issues for global researchers. Robots shows gratifying advantages in these issues and have become the most commonly used technology. Wearable devices and brain-computer interface (BCI) were emerging AI technologies in recent years, which is the direction of further exploration. Restoring social function in individuals with ASD is the ultimate aim and driving force of research in the future.

Design of a Robotic Coach for Motor, Social and Cognitive Skills Training Toward Applications With ASD Children

Socially assistive robots may help the treatment of autism spectrum disorder(ASD), through games using dyadic interactions to train social skills. Existing systems are mainly based on simplified protocols which qualitatively evaluate subject performance. We propose a robotic coaching platform for training social, motor and cognitive capabilities, with two main contributions: (i) using triadic interactions(adult, robot and child), with robotic mirroring, and (ii) providing quantitative performance indicators. The key system features were accurately designed, including type of protocols, feedback systems and evaluation metrics, contemplating the requirements for applications with ASD children. We implemented two protocols, Robot-Master and Adult-Master, where children performed different gestures guided by the robot or the adult respectively, eventually receiving feedback about movement execution. In both, the robot mirrors the subject during the movement. To assess system functionalities, with a homogeneous group of subjects, tests were carried out with 28 healthy subjects; one preliminary acquisition was done with an ASD child. Data analysis was customized to design protocol-specific parameters for movement characterization. Our tests show that robotic mirroring execution depends on the complexity and standardization of movements, as well as on the robot technical features. The feedback system evaluated movement phases and successfully estimated the completion of the exercises. Future work includes improving platform flexibility and adaptability, and clinical trials with ASD children to test the impact of the robotic coach on reducing symptoms. We trust that the proposed quantitative performance indicators extend the current state-of-the-art towards clinical usage of robotic-based coaching systems.