Fig. 1: Data-driven exoskeleton optimization.
From: Personalizing exoskeleton assistance while walking in the real world
We used data from laboratory tests to train a model that can perform optimization in real-time outside the laboratory. a, During optimization, the participant walks with the exoskeleton and experiences a sequence of k control laws, each defining a pattern of exoskeleton torque. The optimizer’s goal is to identify the torque pattern that maximizes performance. b, Ankle angle (θ) and ankle velocity (\(\dot{\theta }\)) for each stride are recorded from sensors on the exoskeleton. c, All possible pairs of control laws are then compared (C). For each pair, differences in segmented motion data (Δ) are calculated by subtraction. d, Differences in motion are multiplied with classifier model weights (W), using a dot product operation, to obtain the pair coefficient (wij). e, A logistic function uses the pair coefficient to compute the probability (pij) that the first control law is more beneficial than the second. f, The score (S) for each control law (n) is computed by summing the probabilities of all pairs that include that control law. g, Control laws are then ranked by score and used to update an optimizer. h, The optimizer selects a set of k new control laws, consisting of d parameters, to evaluate. This optimization process is repeated until convergence criteria are satisfied, in this case a set number of evaluations having been completed. During real-world experiments, optimization was performed on the exoskeleton’s microcontroller.
