Robotic exoskeletons can transform mobility for individuals with lower-limb disabilities. However, their widespread adoption is limited by controller degradation caused by varying gait dynamics across different users and environments. Here, we propose an online adaptation framework that leverages real-time data streams to continuously update the user state estimator model. This approach allows the exoskeleton to learn the user-specific gait patterns, effectively customizing the model for each new user. Additionally, we demonstrate a sensor signal transformation technique that enables model transfer across different exoskeleton hardware (from a research-grade exoskeleton to a commercial device). With less than one minute of adaptation, our framework improved gait phase estimation, which directly affects assistance timing, by 40.9% for able-bodied subjects and 65.9% for stroke survivors (p<0.05), and reduced torque profile error by 32.7% compared to the baseline model (p<0.05). Furthermore, in a pilot test, we applied our adaptation framework with human-in-the-loop optimization for control tuning. In a single stroke survivor, this approach led to a 21.8% increase in walking speed and a 6.5% reduction in metabolic cost compared to walking without exoskeleton. While preliminary, these results suggest the potential for personalized exoskeleton assistance in clinical populations.

Estimating human joint moments using wearable sensors has utility for personalized health monitoring and generalized exoskeleton control. Data-driven models have potential to map wearable sensor data to human joint moments, even with a reduced sensor suite and without subject-specific calibration. In this study, we quantified the RMSE and R2of a temporal convolutional network (TCN), trained to estimate human hip moments in the sagittal plane using exoskeleton sensor data (i.e., a hip encoder and thigh- and pelvis-mounted inertial measurement units). We conducted three analyses in which we iteratively retrained the network while: 1) varying the input sequence length of the model, 2) incorporating noncausal data into the input sequence, thus delaying the network estimates, and 3) time shifting the labels to train the model to anticipate (i.e., predict) human hip moments. We found that 930 ms of causal input data maintained model performance while minimizing input sequence length (validation RMSE and R2of 0.141±0.014 Nm/kg and 0.883±0.025, respectively). Further, delaying the model estimate by up to 200 ms significantly improved model performance compared to the best causal estimators (p2(p2>0.85) when predicting up to 200 ms ahead.

Lumbar spine injuries caused by repetitive lifting rank as the most prevalent workplace injury in the United States. While these injuries are caused by both symmetric and asymmetric lifting, asymmetric is often more damaging. Many back devices do not address asymmetry, so we present a new system called the Asymmetric Back Exosuit (ABX). The ABX addresses this important gap through unique design geometry and active cable-driven actuation. The suit allows the user to move in a wide range of lumbar trajectories while the “X” pattern cable routing allows variable assistance application for these trajectories. We also conducted a biomechanical analysis in OpenSim to map assistive cable force to effective lumbar torque assistance for a given trajectory, allowing for intuitive controller design in the lumbar joint space over the complex kinematic chain for varying lifting techniques. Human subject experiments illustrated that the ABX reduced lumbar erector spinae muscle activation during symmetric and asymmetric lifting by an average of 37.8% and 16.0%, respectively, compared to lifting without the exosuit. This result indicates the potential for our device to reduce lumbar injury risk.