Addressing the pressing challenges in autism rehabilitation – such as teacher shortages, homogenized intervention approaches, and high costs of overseas equipment – this study proposes and implements an intelligent intervention robot system that integrates multi-source sensory data. First, the study constructed China’s first facial emotion dataset for children with autism spectrum disorder facial expression dataset (ASDface). Based on this dataset, it designed an ASDface-AlexNet recognition model incorporating a dual-attention mechanism. This model achieved an average recognition accuracy of 89.31% even for subtle facial expressions. Building upon this, the study further integrated four types of signals – facial, ocular, head movement, and task-response – to develop a cognitive-load assessment model. This enables the robot to dynamically and adaptively adjust intervention strategies in real time. The system comprises integrated robotic hardware and a collaborative mobile app for home-institution coordination, forming a closed-loop intervention framework. An eight-week controlled trial demonstrated that this system significantly reduced the proportion of cognitive overload during children’s training sessions (11.30% in the experimental group vs. 42.70% in the control group). It also effectively enhanced children’s core competencies and greatly improved the sustainability of home-based interventions. This research provides a localized technological solution to enhance the accessibility and inclusivity of autism intervention services in China.
References
[1] Ali, S., Mehmood, F., Dancey, D., Ayaz, Y., Khan, M. J., Naseer, N., Nawaz, R. (2019) An adaptive multi-robot therapy for improving joint attention and imitation of ASD children. IEEE Access, 7, 81808-81825.
[2] Vagnetti, R., Di Nuovo, A., Mazza, M., Valenti, M. (2026) Social robots: a promising tool to support people with autism. A systematic review of recent research and critical analysis from the clinical perspective. Review Journal of Autism and Developmental Disorders, 13(1), 202-226.
[3] Heinsfeld, A. S., Franco, A. R., Craddock, R. C., Buchwitz, A., Meneguzzi, F. (2018) Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroImage: Clinical, 17, 16-23.
[4] Kouroupa, A., Laws, KR., Irvine, K., Mengoni, SE., Baird, A., Sharma, S. (2022) The use of social robots with children and young people on the autism spectrum: a systematic review and meta-analysis. PLoS One, 17(6), e0269800.
[5] Salimi, Z., Jenabi, E., Bashirian, S. (2021) Are social robots ready yet to be used in care and therapy of autism spectrum disorder: a systematic review of randomized controlled trials. Neuroscience & Biobehavioral Reviews, 129, 1-16.
[6] Costley, J., Gorbunova, A., Courtney, M., Chen, O., Lange, C. (2024) Problem-solving support and instructional sequence: impact on cognitive load and student performance: J. Costley. European Journal of Psychology of Education, 39(3), 1817-1840.
[7] Leong, H. M., Carter, M., Stephenson, J. R. (2015) Meta-analysis of research on sensory integration therapy for individuals with developmental and learning disabilities. Journal of Developmental and Physical Disabilities, 27(2), 183-206.
[8] Schreibman, L., Dawson, G., Stahmer, A. C., Landa, R., Rogers, S. J., McGee, G. G., Halladay, A. (2015) Naturalistic developmental behavioral interventions: Empirically validated treatments for autism spectrum disorder. Journal of Autism and Developmental Disorders, 45(8), 2411-2428.
[9] Waddington, H., Reynolds, J. E., Macaskill, E., Curtis, S., Taylor, L. J., Whitehouse, A. J. (2021) The effects of JASPER intervention for children with autism spectrum disorder: a systematic review. Autism, 25(8), 2370-2385.
[10] Zhao, Z., Tang, H., Zhang, X., Qu, X., Hu, X., Lu, J. (2021) Classification of children with autism and typical development using eye-tracking data from face-to-face conversations: machine learning model development and performance evaluation. Journal of Medical Internet Research, 23(8), e29328.
[11] Van der Donck, S., Vettori, S., Dzhelyova, M., Mahdi, S. S., Claes, P., Steyaert, J., Boets, B. (2021) Investigating automatic emotion processing in boys with autism via eye tracking and facial mimicry recordings. Autism Research, 14(7), 1404-1420.
[12] Hoffmann, T. C., Glasziou, P. P., Boutron, I., Milne, R., Perera, R., Moher, D., Michie, S. (2016) Better reporting of interventions: template for intervention description and replication (TIDieR) checklist and guide. Gesundheitswesen (Bundesverband der Arzte des Offentlichen Gesundheitsdienstes (Germany)), 78(3), 175-188.
[13] Liu, X., Rivera, S. C., Moher, D., Calvert, M. J., Denniston, A. K., Ashrafian, H., Yau, C. (2020) Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: the CONSORT-AI extension. The Lancet Digital Health, 2(10), e537-e548.
Share and Cite
Qiu, Y., Pan, X., Jiang, C., Liu, M. (2026) Research on a Multi-source Perception-fused Intelligent Intervention Robot System for Children with Autism Spectrum Disorder. Scientific Research Bulletin, 3(3), 51-64. https://doi.org/10.71052/srb2024/XYNU6143