Scholarlink

<p>This study aims to develop a robotic gripper capable of in-hand multi-mode perception and grasping in unstructured environments without relying on fingertip sensors or vision-based methods. An underactuated gripper with sensorless fingertips, actuated by a single- acting pneumatic cylinder, was designed. Dynamic analysis was conducted to elucidate the multi-mode transmission-perception mechanism between the actuating and grasping spaces. A mechanism-data hybrid model was developed to achieve real-time multi-mode object size perception. A physical prototype was fabricated, and grasping experiments were conducted to validate the perception model. The results demonstrate the feasibility of the transmission-perception mechanism, with the hybrid model achieving an overall perception error of approximately 0.54 mm, indicating strong performance for object size perception. The proposed method holds potential for application in agricultural selective harvesting, as well as in industrial quality inspection and sorting tasks.</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

Design and evaluation of a pneumatic underactuated robotic gripper with in-hand multi-mode self-perception ability

  • 期刊论文

  • 发表日期：

    2025年7月3日

查看全文
  • Hongliang Hua,
  • Xiaofeng Wu,
  • Che Zhao,
  • Zhilin Wu,
  • Jie Song,
  • Zhenqiang Liao

摘要

This study aims to develop a robotic gripper capable of in-hand multi-mode perception and grasping in unstructured environments without relying on fingertip sensors or vision-based methods. An underactuated gripper with sensorless fingertips, actuated by a single- acting pneumatic cylinder, was designed. Dynamic analysis was conducted to elucidate the multi-mode transmission-perception mechanism between the actuating and grasping spaces. A mechanism-data hybrid model was developed to achieve real-time multi-mode object size perception. A physical prototype was fabricated, and grasping experiments were conducted to validate the perception model. The results demonstrate the feasibility of the transmission-perception mechanism, with the hybrid model achieving an overall perception error of approximately 0.54 mm, indicating strong performance for object size perception. The proposed method holds potential for application in agricultural selective harvesting, as well as in industrial quality inspection and sorting tasks.