Background: Autism Spectrum Disorder (ASD) is a neurodevelopmental condition with unique differences in social interaction, communication, and a spectrum of behavioral characteristics. In the past, motor disturbance in individuals with ASD has not been considered a significant core deficit due to the predominant focus on sociability and communication issues. However, recent studies indicate that motor deficits are indeed associated with the fundamental symptoms of ASD. As there is limited research on the motor behavior of children with ASD, particularly in China, the objective of this study is to investigate the development of fundamental movement skills (FMS) in children with ASD and compare them to typically developing children.Method: The study recruited 108 children with ASD (87 boys, 21 girls) aged 7–10 years from two special education rehabilitation centers in Wuhan, China. For comparison, a control group of 108 typically developing children, matched by age and gender, was randomly selected from three local primary schools. FMS were assessed using the Movement Assessment Battery for Children - Second Edition (MABC-2), which evaluates manual dexterity, aiming and catching, as well as static and dynamic balance. Group differences on MABC-2 percentile scores were analyzed using descriptive statistics and Mann–Whitney U test. Effect sizes were also calculated for practical significance.Results: Findings from the study showed that a significant majority, around 80%, of children with ASD either displayed motor challenges or were at risk of developing such delays. When comparing to their typically developing peers, children with ASD scored notably lower in areas of manual dexterity, ball skills, and both static and dynamic balance (with all these findings being statistically significant at p < 0.001). Interestingly, gender did not show a significant influence on these results (p > 0.05).Conclusion: In addition to addressing the other skill development areas outlined in the diagnostic manual for ASD, clinicians diagnosing and treating children with ASD should also assess the presence of motor skill development. For individuals with ASD who have co-existing motor difficulties, it is essential to offer evidence-based interventions tailored to their specific needs.

The current study examined the acquisition, retention, and transfer effects of a motor program. Children with autism spectrum disorder participated in a 9-week program that targeted 13 fundamental motor skills based upon the Test of Gross Motor Development-3. Assessments were conducted before and after the program, as well as at 2-month follow-up. Significant improvements were found on not only the trained fundamental motor skills (acquisition) but also the untrained tasks on balance (transfer). The follow-up tests revealed continuous improvement on the trained locomotor skills (retention), as well as the untrained skills on balance (retention + transfer). These findings highlight the importance of continuous support and long-term participation on motor practices.

Human pose estimation is the basis of many downstream tasks, such as motor intervention, behavior understanding, and human–computer interaction. The existing human pose estimation methods rely too much on the similarity of keypoints at the image feature level, which is vulnerable to three problems: object occlusion, keypoints ghost, and neighbor pose interference. We propose a dual-space-driven topology model for the human pose estimation task. Firstly, the model extracts relatively accurate keypoints features through a Transformer-based feature extraction method. Then, the correlation of keypoints in the physical space is introduced to alleviate the error localization problem caused by excessive dependence on the feature-level representation of the model. Finally, through the graph convolutional neural network, the spatial correlation of keypoints and the feature correlation are effectively fused to obtain more accurate human pose estimation results. The experimental results on real datasets also further verify the effectiveness of our proposed model.