Rapid Online Learning of Hip Exoskeleton Assistance Preferences

TL;DR

This paper introduces a fast, preference-based learning method for customizing hip exoskeleton assistance, reducing tuning time by actively querying users and updating assistive profiles based on their feedback.

Contribution

It presents a novel active preference-learning algorithm that quickly personalizes exoskeleton assistance by integrating user feedback into assistive torque profile adjustments.

Findings

Users preferred distinct torque profiles aligned with their walking strategies

Preferences remained consistent despite profile perturbations

Assistive torques synchronized with user movements reduced negative power

Abstract

Hip exoskeletons are increasing in popularity due to their effectiveness across various scenarios and their ability to adapt to different users. However, personalizing the assistance often requires lengthy tuning procedures and computationally intensive algorithms, and most existing methods do not incorporate user feedback. In this work, we propose a novel approach for rapidly learning users' preferences for hip exoskeleton assistance. We perform pairwise comparisons of distinct randomly generated assistive profiles, and collect participants preferences through active querying. Users' feedback is integrated into a preference-learning algorithm that updates its belief, learns a user-dependent reward function, and changes the assistive torque profiles accordingly. Results from eight healthy subjects display distinct preferred torque profiles, and users' choices remain consistent when compared to a perturbed profile. A comprehensive evaluation of users' preferences reveals a close relationship with individual walking strategies. The tested torque profiles do not disrupt kinematic joint synergies, and participants favor assistive torques that are synchronized with their movements, resulting in lower negative power from the device. This straightforward approach enables the rapid learning of users preferences and rewards, grounding future studies on reward-based human-exoskeleton interaction.