Choosing Exoskeleton Settings Like A Pandora Radio Station

A team of engineers from the University of Michigan, Google and Georgia Tech have designed a simple way for users to program their own exoskeleton assistance settings. This approach uses a machine learning algorithm to offer pairs of assistance profiles that are most likely to be comfortable for the wearer, and the user then selects one of these two. The team tested the approach with 14 participants, and found that the final assistance profile was chosen nine out of ten times. This highlights the accuracy of the proposed approach.