Scholarlink

<p>Haptic sciences and technologies benefit greatly from comprehensive datasets that capture tactile stimuli under controlled, systematic conditions. However, existing haptic datasets collect data through uncontrolled exploration, which hinders the systematic analysis of how motion parameters influence tactile perception. This paper introduces the Cluster Haptic Texture Dataset, a multimodal dataset recorded using a 3-axis machine with a rubber tip as an artificial finger to precisely control sliding velocity and direction. The dataset encompasses 118 textured surfaces across nine material categories, with recordings at five velocity levels, eight directions, and two normal-force levels. Each surface was tested under 160 conditions, yielding 18,880 synchronized recordings of audio, acceleration, force, position, and visual data. Validation using convolutional neural networks demonstrates classification accuracies of 96.0% for texture recognition, 88.8% for velocity estimation, and 78.8% for direction estimation, confirming the dataset’s utility for machine learning applications. This resource enables research in haptic rendering, texture recognition algorithms, and human tactile perception mechanisms, supporting the development of realistic haptic interfaces for virtual reality and robotic applications.</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

Cluster Haptic Texture Dataset: Haptic Texture Dataset with Varied Velocity-Direction Sliding Contacts

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月27日

查看全文
  • Michikuni Eguchi,
  • Tomohiro Hayase,
  • Yuichi Hiroi,
  • Takefumi Hiraki

摘要

Haptic sciences and technologies benefit greatly from comprehensive datasets that capture tactile stimuli under controlled, systematic conditions. However, existing haptic datasets collect data through uncontrolled exploration, which hinders the systematic analysis of how motion parameters influence tactile perception. This paper introduces the Cluster Haptic Texture Dataset, a multimodal dataset recorded using a 3-axis machine with a rubber tip as an artificial finger to precisely control sliding velocity and direction. The dataset encompasses 118 textured surfaces across nine material categories, with recordings at five velocity levels, eight directions, and two normal-force levels. Each surface was tested under 160 conditions, yielding 18,880 synchronized recordings of audio, acceleration, force, position, and visual data. Validation using convolutional neural networks demonstrates classification accuracies of 96.0% for texture recognition, 88.8% for velocity estimation, and 78.8% for direction estimation, confirming the dataset’s utility for machine learning applications. This resource enables research in haptic rendering, texture recognition algorithms, and human tactile perception mechanisms, supporting the development of realistic haptic interfaces for virtual reality and robotic applications.