Scholarlink

<p>To enable robots to perform human-like dexterous manipulation, it is essential to understand how mechanical compliance, multi-modal sensing, and purposeful interaction jointly shape tactile perception. In this study, we use a dedicated <i>modular e-Skin</i> with interchangeable mechanical compliance and multi-modal sensing to systematically investigate how sensing embodiment and interaction strategies influence robotic perception of objects. Leveraging a curated set of soft <i>wave objects</i> with controlled viscoelastic and surface properties, we explore a rich set of <i>palpation primitives</i> that vary in indentation depth, frequency, and directionality. In addition, we propose the <i>latent filter</i>, an unsupervised, action-conditioned deep state-space model of the sophisticated interaction dynamics, and infer causal mechanical properties into a structured latent space. This provides in-depth, interpretable representation of how embodiment and interaction determine and influence perception. Our investigation demonstrates that multi-modal sensing outperforms unimodal sensing, emphasizing complex interaction between the environment and the mechanical properties of e-Skin.</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

Embodied tactile perception of soft objects properties

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年2月12日

查看全文
  • Anirvan Dutta,
  • Alexis WM Devillard,
  • Zhihua Zhang,
  • Xiaoxiao Cheng,
  • Etienne Burdet

摘要

To enable robots to perform human-like dexterous manipulation, it is essential to understand how mechanical compliance, multi-modal sensing, and purposeful interaction jointly shape tactile perception. In this study, we use a dedicated modular e-Skin with interchangeable mechanical compliance and multi-modal sensing to systematically investigate how sensing embodiment and interaction strategies influence robotic perception of objects. Leveraging a curated set of soft wave objects with controlled viscoelastic and surface properties, we explore a rich set of palpation primitives that vary in indentation depth, frequency, and directionality. In addition, we propose the latent filter, an unsupervised, action-conditioned deep state-space model of the sophisticated interaction dynamics, and infer causal mechanical properties into a structured latent space. This provides in-depth, interpretable representation of how embodiment and interaction determine and influence perception. Our investigation demonstrates that multi-modal sensing outperforms unimodal sensing, emphasizing complex interaction between the environment and the mechanical properties of e-Skin.