Main Article Content
This work is licensed under a Creative Commons Attribution 4.0 International License.
Soft, lightweight wearable robots can assist individuals with a lower limb weakness. However, it its challenging to identify control parameters that optimize the robotic assistance for a specific user and task. In this context, “human-in-the-loop” techniques have been suggested to automate this optimization process. Here, we show that the assistance from the Myosuit, a multi-joint wearable robot, can be optimized using a Covariance-Matrix Adaptation Evolution Strategy. The optimization resulted in a reduction of a participant’s energy expenditure that was nearly twice as large (18 % vs. 9.6 %) than when using hand-selected parameters, thereby motivating further work with impaired participants.