Data-Efficient Framework for Personalized Physiotherapy Feedback

Abstract

Physiotherapy is a labor-intensive process that has become increasingly inaccessible. Existing telehealth solutions overcome many of the logistical problems, but they are cumbersome to re-calibrate for the various exercises involved. To facilitate self-exercise efficiently, we developed a framework for personalized physiotherapy exercises. Our approach eliminates the need to re-calibrate for different exercises, using only few userspecific demonstrations available during collocated therapy. Two types of augmented feedback are available to the user for self-correction. The framework's utility was demonstrated for the sit-to-stand task, an important activity of daily living. Although further testing is necessary, our results suggest that the framework can be generalized to the learning of arbitrary motor behaviors.

Predicting Sit-to-Stand Adaptations due to Muscle Strength Deficits and Assistance Trajectories to Complement Them

“…We have used the experimental data recordings of Lao et al (2019) and Lao et al (2020) to validate the 0% strength deficit model's STS trajectory generated. The experimental data contains optical marker trajectories, surface EMG signals and the ground and seat-pan reaction forces for 12 healthy adult subjects performing assisted and unassisted STS.…”