Automated Feedback Selection for Robot-Assisted Training

Robot-assisted training can be enhanced by using augmented feedback to support trainees during learning. Efficacy of augmented feedback is assumed to be dependent on the trainee's skill level and task characteristics. Thus, selecting the most efficient augmented feedback for individual subjects over the course of training is challenging.

We present a general concept to automate feedback selection based on predicted performance improvement. As proof of concept, we applied our concept to trunkarm rowing. Using existing data, the assumption that improvement is skill level dependent was verified and a predictive linear mixed model was obtained. We used this model to automatically select feedback for new trainees. The observed improvements were used to adapt the prediction model to the individual subject. The prediction model did not over-fit and generalized to new subjects with this adaptation.

Mainly, feedback was selected that showed the highest baseline to retention learning in previous studies. By this replication of our former best results we demonstrate that a simple decision rule based on improvement prediction has the potential to reasonably select feedback, or to provide a comprehensible suggestion to a human supervisor. To our knowledge, this is the first time an automated feedback selection has been realized in motor learning.