Optimizing Locomotor Task Sets in Biological Joint Moment Estimation for Hip Exoskeleton Applications

TL;DR

This paper presents a method to optimize the selection of locomotor tasks for training neural networks to estimate hip joint moments, reducing data collection needs without sacrificing model accuracy in exoskeleton applications.

Contribution

It introduces a cluster-based task set optimization strategy that identifies a minimal, representative set of tasks for effective neural network training in joint moment estimation.

Findings

Optimized task set achieves RMSE of 0.30±0.05 Nm/kg.

Performance is significantly better than using only cyclic tasks.

Model accuracy is comparable to using the full task set.

Abstract

Accurate estimation of a user's biological joint moment from wearable sensor data is vital for improving exoskeleton control during real-world locomotor tasks. However, most state-of-the-art methods rely on deep learning techniques that necessitate extensive in-lab data collection, posing challenges in acquiring sufficient data to develop robust models. To address this challenge, we introduce a locomotor task set optimization strategy designed to identify a minimal, yet representative, set of tasks that preserves model performance while significantly reducing the data collection burden. In this optimization, we performed a cluster analysis on the dimensionally reduced biomechanical features of various cyclic and non-cyclic tasks. We identified the minimal viable clusters (i.e., tasks) to train a neural network for estimating hip joint moments and evaluated its performance. Our cross-validation analysis across subjects showed that the optimized task set-based model achieved a root mean squared error of 0.30$\pm$0.05 Nm/kg. This performance was significantly better than using only cyclic tasks (p<0.05) and was comparable to using the full set of tasks. Our results demonstrate the ability to maintain model accuracy while significantly reducing the cost associated with data collection and model training. This highlights the potential for future exoskeleton designers to leverage this strategy to minimize the data requirements for deep learning-based models in wearable robot control.