AutismInsights
Back to research database
Emerging

Effectiveness and Adherence of a Robot-Enhanced Imitation Therapy in Autistic Children.

IEEE ... International Conference on Rehabilitation Robotics : [proceedings]2025

Fassina Gabriele, Annunziata Silvia, Brivio Michelle, Santos Laura, Ambrosini Emilia, Cavallini Anna, Pedrocchi Alessandra

What this study means for families

Researchers tested a 12-week therapy program where eight autistic children learned to copy gestures from songs with help from a robot. While children showed some improvements in social skills, the results weren't strong enough to prove the therapy worked better than normal development. However, children who participated more actively and copied gestures more accurately showed better improvements in social skills, suggesting that engagement matters for success.

Summary by AutismInsights from published abstract. This is not a substitute for reading the original paper.

Research summary

This preliminary study evaluated a 12-week Robot-Enhanced Therapy (RET) program focused on imitation training using gestures from children's songs in eight autistic children. The intervention aimed to improve social skills, with outcomes measured using the Adaptive Behavioral Assessment Scale (ABAS-II) and Primo Vocabolario del Bambino (PVB). While overall improvement trends were observed, the primary outcome (Social Adaptive Domain of ABAS-II) did not reach statistical significance. Notably, children with higher treatment adherence, measured as correctly imitated gestures using CNN-based recognition (F1-score 0.57), showed significantly better social skill improvements.

The study highlights the importance of active participation in robot-assisted interventions for autism.

Summary by AutismInsights from published abstract. This is not a substitute for reading the original paper.

Key findings

  • 1

    Primary outcome (Social Adaptive Domain of ABAS-II) did not reach statistical significance

    Confidence: highRelevance: moderate
  • 2

    Children with higher treatment adherence showed significantly better social skill improvements

    Confidence: highRelevance: high
  • 3

    Overall trends of improvement were observed across measures

    Confidence: moderateRelevance: moderate
  • 4

    CNN-based gesture recognition algorithm achieved F1-score of 0.57

    Confidence: highRelevance: low

Summary by AutismInsights from published abstract. This is not a substitute for reading the original paper.

Clinical implications

Robot-enhanced imitation therapy shows promise for autism interventions, with active participation being crucial for success. However, larger controlled studies are needed before clinical implementation. The significant association between adherence and outcomes suggests engagement strategies should be prioritized in robot-assisted therapies.

Summary by AutismInsights from published abstract. This is not a substitute for reading the original paper.

Limitations

Very small sample size (8 children), no control group for comparison, preliminary findings only, gesture recognition algorithm needs improvement (F1-score 0.57), adherence assessment tools require refinement, unable to differentiate therapy effects from natural developmental progression.

Summary by AutismInsights from published abstract. This is not a substitute for reading the original paper.

Original abstract

Robot-Enhanced Therapies (RET) are gaining recognition in autism interventions, though limited empirical evaluations of their effectiveness exist. This study introduces a novel RET focused on imitation training to promote social skills, incorporating gestures from children's songs to enhance engagement. This work presents preliminary findings from eight autistic children who underwent a 12 -week intervention, assessing improvements in adaptive abilities using the Adaptive Behavioral Assessment Scale (ABAS-II) and Primo Vocabolario del Bambino (PVB), with the Social Adaptive Domain (SAD) of ABAS-II as the primary outcome. Treatment adherence is measured as the proportion of correctly imitated gestures, which is also quantified by leveraging a CNN-based gesture recognition algorithm.

While results show overall trends of improvement, the primary outcome does not reach statistically significant. However, adherence was significantly higher in subjects with improved social skills, underscoring the importance of active participation The gesture recognition algorithm achieved an F1-score of 0.57. While findings are promising, the comparison with a control group will permit differentiating the outcomes of the therapy protocol and the developmental trajectory. Future efforts should focus on improving the gesture-imitation algorithm and refining adherence assessment tools.

View Original Paper

View original paperFull paper via publisher (may require subscription)

Evidence Grade

Emerging

emerging

Grade assigned by AutismInsights based on study type and published abstract.

Study Details

Journal
IEEE ... International Conference on Rehabilitation Robotics : [proceedings]
Year
2025
PMID
40644262
DOI
10.1109/ICORR66766.2025.11062960

MeSH Terms

HumansMaleAutistic DisorderRoboticsFemaleChildGesturesImitative BehaviorChild, PreschoolAlgorithmsTreatment Outcome