Scholarlink

<p>Virtual reality sculpting tools currently lack the tactile feedback essential for teaching material manipulation skills in sculptural education, limiting their pedagogical effectiveness compared to traditional hands-on training. This study presents SculpTouch, a haptic interface system that addresses this gap through distributed force sensing using finger-mounted capacitive sensor arrays (4 × 4 electrodes) sampling at 40&#xa0;kHz. The system implements a three-phase modeling workflow mimicking traditional clay sculpting: form stroking through palm pressure, material carving with precise finger movements, and detail pinching using thumb-index coordination. Neural network processing combining convolutional layers and bidirectional LSTMs enables real-time gesture recognition and haptic force computation. SculpTouch achieved 0.38&#xa0;mm spatial accuracy, sub-4&#xa0;ms latency, 0.01&#xa0;N force resolution, and 94.8% gesture classification accuracy across 25 participants. The system successfully distinguishes compression and tension zones during forming operations and maintains consistent parting lines during detail work, enabling authentic sculptural skill development in virtual environments. The bidirectional haptic rendering architecture generates realistic force feedback through spring–damper models (F = k·δ + b·δ̇) with forces up to 50&#xa0;N, providing the tactile experience necessary for effective motor skill acquisition in virtual sculptural education.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

HapticCraft: bidirectional haptic rendering with distributed capacitive sensing and neural gesture recognition for virtual reality sculptural education

  • 期刊论文

  • 发表日期：

    2026年3月16日

查看全文
  • Jian Teng,
  • Sukyoung Cho,
  • Shuyi Zhang

摘要

Virtual reality sculpting tools currently lack the tactile feedback essential for teaching material manipulation skills in sculptural education, limiting their pedagogical effectiveness compared to traditional hands-on training. This study presents SculpTouch, a haptic interface system that addresses this gap through distributed force sensing using finger-mounted capacitive sensor arrays (4 × 4 electrodes) sampling at 40 kHz. The system implements a three-phase modeling workflow mimicking traditional clay sculpting: form stroking through palm pressure, material carving with precise finger movements, and detail pinching using thumb-index coordination. Neural network processing combining convolutional layers and bidirectional LSTMs enables real-time gesture recognition and haptic force computation. SculpTouch achieved 0.38 mm spatial accuracy, sub-4 ms latency, 0.01 N force resolution, and 94.8% gesture classification accuracy across 25 participants. The system successfully distinguishes compression and tension zones during forming operations and maintains consistent parting lines during detail work, enabling authentic sculptural skill development in virtual environments. The bidirectional haptic rendering architecture generates realistic force feedback through spring–damper models (F = k·δ + b·δ̇) with forces up to 50 N, providing the tactile experience necessary for effective motor skill acquisition in virtual sculptural education.