Identification of Gait Phases with Neural Networks for Smooth Transparent Control of a Lower Limb Exoskeleton

TL;DR

This paper develops and tests a neural network-based gait phase segmentation method for lower limb exoskeletons, aiming to improve control smoothness and transparency during different activities.

Contribution

It introduces a nonlinear neural network approach for gait phase segmentation, outperforming linear regression, and demonstrates its real-time application with a user.

Findings

Neural network segmentation outperforms linear regression in accuracy.

The online implementation effectively adapts to user-specific gait patterns.

Enhanced control smoothness reduces interaction forces and jerky movements.

Abstract

Lower limbs exoskeletons provide assistance during standing, squatting, and walking. Gait dynamics, in particular, implies a change in the configuration of the device in terms of contact points, actuation, and system dynamics in general. In order to provide a comfortable experience and maximize performance, the exoskeleton should be controlled smoothly and in a transparent way, which means respectively, minimizing the interaction forces with the user and jerky behavior due to transitions between different configurations. A previous study showed that a smooth control of the exoskeleton can be achieved using a gait phase segmentation based on joint kinematics. Such a segmentation system can be implemented as linear regression and should be personalized for the user after a calibration procedure. In this work, a nonlinear segmentation function based on neural networks is implemented and compared with linear regression. An on-line implementation is then proposed and tested with a subject.