High-resolution touch sensors reveal how experts control badminton rackets
High-resolution tactile observation makes hidden racket-control mechanisms learnable
Machine LearningHuman-Computer InteractionRobotics
Summary
Fine hand control during fast movements, like playing badminton, involves complex touch-based forces that are hard to notice consciously. The authors used a special glove with many sensors to record how people of different skill levels handle a badminton racket. They discovered specific patterns in how experts control grip and movement forces. These insights helped them create personalized training feedback that improved learners’ skills more than usual coaching.
What this means in practice
- •For sports coaches: Provide personalized feedback on force control and coordination to improve racket sports skills using tactile sensor data.
- •For robotic hand designers: Develop more dexterous robotic grippers by mimicking human grip stabilization and force modulation patterns revealed by high-resolution tactile sensing.
Authors
Haoyang Tian, Zhengwei Li, Houcheng Li, Xu Yang, Peigeng Gu, Xinyue Wang, Tairan Zhu, Shuo Jiang, Long Cheng
Abstract
Experts can master fine hand-object manipulation skills, yet limited conscious perception of rapid tactile interactions hinders their ability to articulate the underlying control mechanisms. Badminton racket control requires rapid, fine hand-force coordination, providing a demanding testbed for uncovering these mechanisms. An 864-node tactile-inertial glove with synchronized 100-Hz acquisition recorded over 14,000 strokes from more than 70 participants across five skills. Inspired by sensorimotor control, our mechanics-grounded two-layer framework inferred object-driving and grip-stabilizing control from tactile history, while resolving their spatiotemporal force realization. We found that higher proficiency was associated with selective rather than extensive control: greater skill specificity, anticipatory regulation, focal distal modulation and lower geometric torque cancellation, while spatiotemporal coordination showed a non-monotonic acquire-refine pattern. We translated these mechanisms into personalized guidance targeting force control and force-motion coordination. In a randomized cohort, mechanism-guided learners gained 0.72 expert-rated skill levels versus 0.05 with level-only feedback, making control mechanisms actionable.