Scholarlink

In this work, the idea of full-hand tactile perception is proposed. A 4-fingered fully-actuated dexterous hand with 16 degrees of freedom (DoFs) is designed, novel and facile piezoresistive flexible tactile sensor is then proposed and integrated on index finger, thumb and palm of the hand. Moreover, a graph convolutional network (GCN)-based grasp stability assessment system is introduced as a preliminary usage of full-hand tactile perception, where envelope grasp is taken into consideration with traditional precision prismatic 2-finger grasp. Experimental results show that the proposed system achieve precise hand movement and perception, grasping stability is also evaluated correctly, showing potential in achieving full-hand tactile coverage and more robust control.

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

Dexterous Hand Development with Full-Hand Tactile Perception and Learning-Based Grasp Stability Assessment

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Mingqi Chen,
  • Zhenyuan Zhang,
  • Zikai Yang,
  • Qihao Zhang,
  • Shukun Huang,
  • Xiaohong Yin,
  • Qiang Li

摘要

In this work, the idea of full-hand tactile perception is proposed. A 4-fingered fully-actuated dexterous hand with 16 degrees of freedom (DoFs) is designed, novel and facile piezoresistive flexible tactile sensor is then proposed and integrated on index finger, thumb and palm of the hand. Moreover, a graph convolutional network (GCN)-based grasp stability assessment system is introduced as a preliminary usage of full-hand tactile perception, where envelope grasp is taken into consideration with traditional precision prismatic 2-finger grasp. Experimental results show that the proposed system achieve precise hand movement and perception, grasping stability is also evaluated correctly, showing potential in achieving full-hand tactile coverage and more robust control.