Vibrotactile Preference Learning: Uncertainty-Aware Preference Learning for Personalized Vibration Feedback

TL;DR

This paper introduces VPL, a Gaussian-process-based system that efficiently learns individual vibrotactile preferences through uncertainty-aware queries, enabling personalized haptic feedback.

Contribution

It presents a novel uncertainty-aware preference learning method for vibrotactile feedback, improving personalization efficiency in interactive systems.

Findings

VPL effectively learns individual preferences with fewer queries.

User study shows VPL maintains low workload and comfort.

VPL demonstrates scalable personalization of vibrotactile experiences.

Abstract

Individual differences in vibrotactile perception underscore the growing importance of personalization as haptic feedback becomes more prevalent in interactive systems. We propose Vibrotactile Preference Learning (VPL), a system that captures user-specific preference spaces over vibrotactile parameters via Gaussian-process-based uncertainty-aware preference learning. VPL uses an expected information gain-based acquisition strategy to guide query selection over 40 rounds of pairwise comparisons of overall user preference, augmented with user-reported uncertainty, enabling efficient exploration of the parameter space. We evaluate VPL in a user study (N = 13) using the vibrotactile feedback from a Microsoft Xbox controller, showing that it efficiently learns individualized preferences while maintaining comfortable, low-workload user interactions. These results highlight the potential of VPL for scalable personalization of vibrotactile experiences.