Robot-Mediated Imitation Skill Training for Children With Autism

Abstract

Autism spectrum disorder (ASD) impacts 1 in 68 children in the US, with tremendous individual and societal costs. Technology-aided intervention, more specifically robotic intervention, has gained momentum in recent years due to the inherent affinity of many children with ASD towards technology. In this paper we present a novel robot-mediated intervention system for imitation skill learning, which is considered a core deficit area for children with ASD. The Robot-mediated Imitation Skill Training Architecture (RISTA) is designed in such a manner that it can operate either completely autonomously or in coordination with a human therapist depending on the intervention need. Experimental results are presented from small user studies validating system functionality, assessing user tolerance, and documenting subject performance. Preliminary results show that this novel robotic system draws more attention from the children with ASD and teaches gestures more effectively as compared to a human therapist. While no broad generalized conclusions can be made about the effectiveness of RISTA based on our small user studies, initial results are encouraging and justify further exploration in the future.

Social skills training for children with autism spectrum disorder using a robotic behavioral intervention system

“…The participants in this study showed clear interest in the robots and responded positively and correctly to them throughout the treatment sessions. These results were generally in line with those of previous studies using robots as cotherapists in the treatment of ASD [Zheng et al, ]. As in previous studies with humanoid robots, the participants in this study showed behaviors that children normally exhibit toward other humans during play, such as singing with them, asking questions, proposing play activities, or talking to them [Chaminade et al, ; Pierno, Mari, Lusher, & Castiello, ].…”

“…These findings were similar to those of previous robot studies, in which performances in various areas, such as eye contact, motor imitation, and speech expression, were generally better with robot‐mediated treatment than with human therapist‐mediated treatment[Bird, Leighton, Press, & Heyes, ; Kim et al, ]. The better performances, especially in the initial sessions, in the robot‐treatment groups might be attributable to higher attentional preferences for the robotic prompts than those of humans [Zheng et al, ]. The improvements in the frequency of eye contact attenuated after the fourth session in the TG but continued to gradually increase in the CG.…”

“…We suggest that the dramatic increases in the first sessions in the TG and the attenuation more reflected the children's initial interest in the robot and subsequent decline than the actual learning process. That is, the initial steep increase might have been simply a response to novel stimuli, as suggested by Zheng et al (). However, this characteristic, the dramatic initial increase, can still be utilized in short‐term treatment protocols, especially with subjects who have difficulty engaging in treatment.…”

Involving Autistics in User Experience Studies

“…Prior to our study, we did not consider including virtual characters and robots as actors in the analysis, but in some cases, they took the human therapist's role as they gave instructions or prompts to the autistic user with therapeutic purposes [6,59]. Besides, human-robot interaction studies in autism have been proving that robots' presence and guidance can be more efficient than humans' in educational and therapeutic settings [59]. Thus, their involvement in future studies may not only be based on how the users interact with them, but also how robots take roles in UX studies as actors.…”

“…the immersive room in [16]) or objects (e.g. the watch in [58] or the chair in [59]) used. These behaviors may result in irreversible situations leading to session cancellations.…”