Skill-informed Data-driven Haptic Nudges for High-dimensional Human Motor Learning

2026-03-12

AI Summary

This study addresses the challenge of designing optimal haptic guidance feedback to accelerate the acquisition of high-dimensional motor skills. To this end, the authors propose a novel approach that employs an Input-Output Hidden Markov Model (IOHMM) to decouple the modeling of skill evolution from motion observations. The haptic guidance policy is formulated as a Partially Observable Markov Decision Process (POMDP), enabling data-driven, personalized feedback. This method uniquely disentangles skill dynamics from sensory observations and leverages the POMDP framework to generate implicit guidance strategies that steer learners more rapidly toward robust regions of the skill space. In experiments with 30 participants, the group receiving this adaptive haptic guidance significantly outperformed both heuristic and no-feedback baselines, demonstrating faster improvements in task performance and earlier emergence of efficient low-dimensional movement representations.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Learning to Search

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In this work, we propose a data-driven skill-informed framework to design optimal haptic nudge feedback for high-dimensional novel motor learning tasks. We first model the stochastic dynamics of human motor learning using an Input-Output Hidden Markov Model (IOHMM), which explicitly decouples latent skill evolution from observable kinematic emissions. Leveraging this predictive model, we formulate the haptic nudge feedback design problem as a Partially Observable Markov Decision Process (POMDP). This allows us to derive an optimal nudging policy that minimizes long-term performance cost, implicitly guiding the learner toward robust regions of the skill space. We validated our approach through a human-subject study ($N=30$) using a high-dimensional hand-exoskeleton task. Results demonstrate that participants trained with the POMDP-derived policy exhibited significantly accelerated task performance compared to groups receiving heuristic-based feedback or no feedback. Furthermore, synergy analysis revealed that the POMDP group discovered efficient low-dimensional motor representations more rapidly.

Problem

• haptic feedback
• motor learning
• high-dimensional tasks
• skill acquisition
• human-robot interaction

Innovation

• haptic nudges
• IOHMM
• POMDP
• motor learning
• skill inference