Abstract
Wearable robots can improve human walking economy; however, their effectiveness depends on user adaptation to assistance. This study introduces a framework for real-time estimation of user adaptation that relies only on wearable sensor data during operation. Metabolic measurements were used solely to establish the ground truth adaptation curves for model training and validation but are not required for real-time inference. Five healthy adults completed six days of treadmill walking while wearing a soft hip exosuit that provided hip extension assistance. Thigh-mounted inertial measurement units recorded step timing and hip-angle trajectories, from which three variability-based features (step-frequency variability, maximum hip-flexion variability, and maximum hip-extension variability) were extracted. A Long Short-Term Memory (LSTM) model used these gait-variability inputs to estimate each user's adaptation level relative to a metabolic cost benchmark obtained from respiratory gas analysis. Across sessions, the metabolic cost decreased by 9.0 ± 5.6% from Day 1 to Day 6 (p < 0.01) with a mean time constant of 202 ± 78 min, In contrast, the variability in step frequency, maximum hip flexion, and maximum hip extension decreased by 66.4 ± 6.8%, 37.9 ± 24.2%, and 42.8 ± 10.6%, respectively, indicating that these reductions were users' progressive adaptation to the exosuit's assistance. Under leave-one-subject-out (LOSO) evaluation across five participants, 59.2% of the model predictions fell within ±10 percentage points of the metabolic cost-based adaptation curve. These results suggest that simple kinematic variability measured with wearable sensors can track user adaptation and support practical approaches to real-time monitoring. Such capability can facilitate adaptive control and training protocols that personalize exosuit assistance.