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

2026-04-22

AI Summary

This work addresses the challenge of personalizing vibrotactile feedback arising from individual differences in tactile perception by proposing an uncertainty-aware preference learning approach. The method models users’ preference spaces over vibration parameters using Gaussian processes and explicitly incorporates user-reported uncertainty. An active querying strategy based on expected information gain enables efficient learning of personalized preferences through only 40 pairwise comparisons. This study is the first to introduce uncertainty modeling into the domain of vibrotactile feedback, substantially reducing users’ cognitive load. Experimental results with 13 participants demonstrate that the system rapidly converges to individual preferences while maintaining interaction comfort, thereby validating its efficiency, scalability, and practical utility.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Learning Human Values and Preferences
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

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.

Problem

• vibrotactile perception
• personalization
• haptic feedback
• individual differences
• preference learning

Innovation

• Vibrotactile Preference Learning
• Uncertainty-Aware Learning
• Gaussian Process
• Active Preference Learning
• Personalized Haptics