Framework for personalizing wearable devices using real-time physiological measures

Personalizing wearable robots by incorporating user physiological feedback can improve energy efficiency and comfort. However, many current personalization methods are specific to a particular device often require reprogramming, making them less accessible. In this study, we present an open-source, device-independent framework that allows for human-in-the-loop optimization. This modular includes cost functions optimization algorithms use response optimize robot parameters. We tested in three case studies involving diverse subjects robots. The first study focused on personalizing ankle-foot prosthesis using indirect calorimetry feedback. resulted 5.3% 18.1% reduction metabolic walking two individuals with transtibial amputation, compared the weight-based assistance. second personalized robotic ankle exoskeleton different speeds subjects. was reduced 1%, 2%, 5.8% one subject 20.8%, 1.9%, 19% other subject, generic assistance condition increasing speeds. third gait parameters, specifically step frequency, electrocardiogram (ECG)-based function along algorithm variant, resulting 43% time able-bodied subject. These suggest our effectively personalize parameters potentially enhance benefits.