Robot-assisted hand training has shown positive effects on promoting neuromuscular control. Since both robot-assisted therapy and task-oriented training are often used in post-stroke rehabilitation, we raised the question of whether two interventions engender differential effects in different domains.
The study was conducted using a randomized, two-period crossover design. Twenty-four chronic stroke survivors received a 12-session robot-assisted intervention followed by a 12-session task-oriented intervention or vice versa. A 1-month washout period between each intervention was implemented. Outcome measures were evaluated before the intervention, after the first 12-session intervention, and after the second 12-session intervention. Clinical assessments included Fugl-Meyer Assessment for Upper Extremity, Wolf Motor Function Test, Action Research Arm Test and Motor Activity Log.
Our findings suggested that EMG-driven robot-assisted therapy was as effective as task-oriented training in terms of improving upper limbs functional performance in activity domain, and robot-assisted therapy was more effective in improving movement duration during functional tasks. Task-oriented training showed better improvement in body function domain and activity and participation domain, especially in improving spontaneous use of affected arm during daily activities.
Both intervention protocol had their own advantages in different domains, and robot-assisted therapy may save manpower and be considered as an alternative intervention to task-oriented training. Combining the two approaches could yield results greater than either alone, which awaits further study.
Trial registration: ClinicalTrials.gov Identifier: NCT03624153. Registered on 9th August 2018, https://clinicaltrials.gov/ct2/show/NCT03624153.
Recent years have witnessed the proliferation of social robots in various domains including special education. However, specialized tools to assess their effect on human behavior, as well as to holistically design social robot applications, are often missing. In response, this work presents novel tools for analysis of human behavior data regarding robot-assisted special education. The objectives include, first, an understanding of human behavior in response to an array of robot actions and, second, an improved intervention design based on suitable mathematical instruments. To achieve these objectives, Lattice Computing (LC) models in conjunction with machine learning techniques have been employed to construct a representation of a child’s behavioral state. Using data collected during real-world robot-assisted interventions with children diagnosed with Autism Spectrum Disorder (ASD) and the aforementioned behavioral state representation, time series of behavioral states were constructed. The paper then investigates the causal relationship between specific robot actions and the observed child behavioral states in order to determine how the different interaction modalities of the social robot affected the child’s behavior.