In this study, the motion therapy elements necessary for student education were clarified through comparison of the therapeutic motion techniques of therapists and students using an educational arm robot (Samothrace: SAMO). Eight therapists and 25 fourth-year students participated. The therapeutic motion therapy task was a reciprocating exercise in which the elbow joint of SAMO was flexed from an extended position and then re-extended. This was performed for three types of muscle tone intensities (mild, moderate, and severe), and the peak velocity, angle ratio, velocity time, and movement time were recorded using SAMO. These data were then compared using analysis of covariance. It was found that the SAMO elbow joint kinematic data generated by therapists differed significantly from those of students for different muscle tones. Multiple comparisons showed that the therapeutic motion techniques of students were associated with a higher peak velocity, smaller peak angle ratio, and shorter peak velocity time and movement time than those of the therapists. Thus, when students learn therapeutic motion techniques, they should be taught to (1) deal with multiple muscle tone intensities and (2) reduce the joint movement speed applied to the patient to extend the exercise time and ensure maximum joint movement range.

We aimed to compare the effects of practical learning using an educational robot arm (Samothrace: SAMO) and a student simulating a patient in students’ acquisition of therapeutic motion techniques. For this study, twenty-five fourth-year students and eight therapists were included. Students were randomly assigned to the robot practice (Robo) group (n = 13) or conventional practice (Human) group (n = 12), wherein students practiced among themselves. The experimental procedure comprised a pre-practice test, practice, and post-practice test. We calculated the peak angle ratio, peak velocity, and movement time during flexion and extension using the elbow joint angle data. Machine learning was performed on students’ pre-practice and used therapists’ data to create identifiers that distinguish students and therapists to determine whether the students’ skills improved to the level of a therapist. However, regarding other kinematics data, there were no main effects or interactions between groups pre- and post-practice. Identifiers were created from machine learning of kinematics data pre-practice, and the effect was evaluated post-practice. A higher number of students in the Robo group were determined to possess skills at a therapist’s level. This study suggests the effectiveness of a simulation robot that can reproduce a patient’s pathological motions in educating students on upper limb exercise therapy.