Abstract
Autism spectrum disorder (ASD) is a serious hazard to the physical and mental health of children, which limits the social activities of patients throughout their lives and places a heavy burden on families and society. The developments of communication techniques and artificial intelligence (AI) have provided new potential methods for the treatment of autism. The existing treatment systems based on AI for children with ASD focus on detecting health status and developing social skills. However, the contradiction between the terminal interaction capability and availability cannot meet the needs for real application scenarios. At the same time, the lack of diverse data cannot provide individualized care for autistic children. To explore this robot-based approach, a novel AI-based first-view-robot architecture is proposed in this article. By providing care from the first-person perspective, the proposed wearable robot overcomes the difficulty of the absence of cognitive ability in the third-view of traditional robotics and improves the social interaction ability of children with ASD. The first-view-robot architecture meets the requirements of dynamic, individualized, and highly immersed interaction services for autistic children. First, the multi-modal and multi-scene data collection processes of standard, static, and dynamic datasets are introduced in detail. Then, to comprehensively evaluate the learning ability of children with ASD through mental states and external performances, a learning assessment model with emotion correction is proposed. Besides, a wearable robot-assisted environment perception and expression enhancement mechanism for children with ASD is realized by reinforcement learning, which can be adapted to interactive environments with optimal action policies. An interactive testbed for children with ASD treatments is demonstrated and experimental cases for test subjects are presented. Last, three open issues are discussed from data processing, robot designing, and service responding perspectives.
- L. Fusar-Poli, N. Brondino, P. Politi, and E. Aguglia. 2020. Prevalence of autism spectrum disorder among children aged 8 years - Autism and developmental disabilities monitoring network. Eur. Arch. Psych. Clin. Neurosci. (2020). DOI:10.1007/s00406-020-01189-wGoogle Scholar
- B.-Y. Park, S. J. Hong, S. L. Valk, et al. 2021. Differences in subcortico-cortical interactions identified from connectome and microcircuit models in autism. Nat Commun. 12, 2225 (2021). https://doi.org/10.1038/s41467-021-21732-0Google Scholar
- L. Mottron and D. Bzdok. 2020. Autism spectrum heterogeneity: fact or artifact? Mol Psychiatry 25 (2020), 3178–3185. https://doi.org/10.1038/s41380-020-0748-yGoogle Scholar
Cross Ref
- M. Chen, Y. Jiang, N. Guizani, J. Zhou, G. Tao, J. Yin, and K. Hwang. 2020. Living with I-fabric: Smart living powered by intelligent fabric and deep analytics. IEEE Netw. 34, 5 (2020), 156–163.Google Scholar
Cross Ref
- S. S. Alwakeel, B. Alhalabi, H. Aggoune,et al.2015. A machine learning based WSN system for autism activity recognition. In IEEE 14th International Conference on Machine Learning and Applications (ICMLA). 771–776.Google Scholar
- W. Liu, M. Li, and L. Yi. 2016. Identifying children with autism spectrum disorder based on their face processing abnormality: A machine learning framework. Autism Res. 9, 8 (2016), 888–898.Google Scholar
Cross Ref
- L. A. Livingston, P. Shah, V. Milner, et al. 2020. Quantifying compensatory strategies in adults with and without diagnosed autism. Molecular Autism 11, 15 (2020). https://doi.org/10.1186/s13229-019-0308-yGoogle Scholar
- P. G. Esteban, P. Baxter, T. Belpaeme,et al.2017. How to build a supervised autonomous system for robot-enhanced therapy for children with autism spectrum disorder. Paladyn, J. Behav. Robot. 8, 1 (2017), 18–38.Google Scholar
Cross Ref
- H. Zhao, A. R. Swanson, A. S. Weitlauf, Z. E. Warren, and Nilanjan Sarkar. 2018. Hand-in-hand: A communication-enhancement collaborative virtual reality system for promoting social interaction in children with autism spectrum disorders. IEEE Trans. Hum.-mach. Syst. 48, 2 (2018), 136–148.Google Scholar
Cross Ref
- O. Rudovic, J. Lee, M. Dai, et al.2018. Personalized machine learning for robot perception of affect and engagement in autism therapy. Sci. Robot. 3, 19 (2018).Google Scholar
- F. Ke, J. Moon, and Z. Sokolikj. 2020. Virtual reality based social skills training for children with autism spectrum disorder. J. Spec. Educ. Technol. (2020). DOI:10.1177/0162643420945603Google Scholar
- M. Eni, I. Dinstein, M. Ilan, I. Menashe, G. Meiri, and Y. Zigel. 2020. Estimating autism severity in young children from speech signals using a deep neural network. IEEE Access 8 (2020), 139489–139500.Google Scholar
Cross Ref
- A. S. Heinsfeld, A. R. Franco, R. C. Craddock,et al.2018. Identification of autism spectrum disorder using deep learning and the ABIDE dataset. NeuroIm.: Clin. 17 (2018), 16–23.Google Scholar
Cross Ref
- N. M. Rad, S. M. Kia, C. Zarbo,et al.2018. Deep learning for automatic stereotypical motor movement detection using wearable sensors in autism spectrum disorders. Sig. Process. 144 (2018), 180–191. Google Scholar
Digital Library
- F. Thabtah and D. Peebles. 2020. A new machine learning model based on induction of rules for autism detection. Health Inform. J. 26, 1 (2020), 264–286.Google Scholar
Cross Ref
- M. Chen, J. Zhou, G. Tao,et al.2018. Wearable affective robot. IEEE Access 6 (2018), 64766–64776.Google Scholar
Cross Ref
- C. A. G. J. Huijnen, H. A. M. D. Verreussel-Willen, M. A. S. Lexis, et al. 2021. Robot KASPAR as mediator in making contact with children with Autism: A pilot study. Int. J. Soc. Robotics 13 (2021), 237–249. https://doi.org/10.1007/s12369-020-00633-0Google Scholar
Cross Ref
- C. C. Cheroni, N. Caporale, and G. Testa. 2020. Autism spectrum disorder at the crossroad between genes and environment: Contributions, convergences, and interactions in ASD developmental pathophysiology. Molec. Aut. 11, 1 (2020), 69.Google Scholar
Cross Ref
- A. D. Martino, C. G. Yan, Q. Li,et al.2014. The autism brain imaging data exchange: Towards a large-scale evaluation of the intrinsic brain architecture in autism. Molec. Psych. 19, 6 (2014), 659–667.Google Scholar
Cross Ref
- K. K. Mujeeb Rahman and M. Monica Subashini. 2021. A Deep Neural Network-Based Model for Screening Autism Spectrum Disorder Using the Quantitative Checklist for Autism in Toddlers (QCHAT). J. Autism Dev Disord (2021). https://doi.org/10.1007/s10803-021-05141-2Google Scholar
- Y. Liao, S. Kodagoda, Y. Wang,et al.2016. Understand scene categories by objects: A semantic regularized scene classifier using convolutional neural networks. In IEEE International Conference on Robotics and Automation (ICRA). 2318–2325.Google Scholar
- B. Weiner. 1980. A cognitive (attribution)-emotion-action model of motivated behavior: An analysis of judgments of help-giving. J. Person. Soc. Psychol. 39, 2 (1980), 186–200.Google Scholar
Cross Ref
- R. S. Sutton and A. G. Barto. 2018. Reinforcement Learning: An Introduction (2nd ed.). The MIT Press. Google Scholar
Digital Library
- D. I. Katzourakis, E. Velenis, D. Abbink, R. Happee, and E. Holweg. 2012. Race-car instrumentation for driving behavior studies. IEEE Trans. Instrum. Meas. 61, 2 (2012), 462–474. DOI:10.1109/TIM.2011.2164281Google Scholar
Cross Ref
- T. Baltrusaitis, A. Zadeh, Y. C. Lim, and L. Morency. 2018. OpenFace 2.0: Facial behavior analysis toolkit. In 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG’18). 59–66. DOI:10.1109/FG.2018.00019Google Scholar
Digital Library
- M. Chen and Y. Hao. 2020. Label-less learning for emotion cognition. IEEE Trans. Neural Netw. Learn. Syst. 31, 7 (2020), 2430–2440.Google Scholar
Index Terms
Cognitive Wearable Robotics for Autism Perception Enhancement
Recommendations
A case for low-dose robotics in autism therapy
HRI '11: Proceedings of the 6th international conference on Human-robot interactionRobots appear to be engaging to many children with autism, and evidence suggests that engagement can facilitate social interaction not only between child and robot but also between child and another human. To date, no objective evidence has established ...
Robotic assistants in therapy and education of children with autism: can a small humanoid robot help encourage social interaction skills?
This article presents a longitudinal study with four children with autism, who were exposed to a humanoid robot over a period of several months. The longitudinal approach allowed the children time to explore the space of robot–human, as well as human–...
Embodiment and Cognitive Learning – Can a Humanoid Robot Help Children with Autism to Learn about Tactile Social Behaviour?
Social RoboticsAbstractThe work presented in this paper is part of our investigation in the ROBOSKIN project. The project aims to develop new robot capabilities based on the tactile feedback provided by novel robotic skin. The main objective of the project is to develop ...






Comments