抓住
工作区
计算机科学
稳健性(进化)
手势
模块化设计
人工智能
仿生学
机械手
计算机视觉
多边形网格
执行机构
模拟
机器人
计算机图形学(图像)
生物化学
化学
基因
程序设计语言
操作系统
作者
Zhicheng Tao,Shineng Sheng,Zhipei Chen,Guanjun Bao
出处
期刊:Industrial Robot-an International Journal
[Emerald Publishing Limited]
日期:2021-04-06
卷期号:48 (3): 463-472
被引量:1
标识
DOI:10.1108/ir-09-2020-0211
摘要
Purpose This paper aims to propose a novel method based on a gesture primitives analysis of human daily grasping tasks for designing dexterous hands with various grasping and in-hand manipulation abilities, which simplifies the complex and redundant humanoid five-finger hand system. Design/methodology/approach First, the authors developed the fingers and the joint configuration with a series of gesture primitives configurations and the modular virtual finger scheme, refined from the daily work gesture library by principal component analysis. Then, the authors optimized the joint degree-of-freedom configuration with the bionic design analysis of the anatomy, and the authors optimized the dexterity workspace. Furthermore, the adaptive fingertip and routing structure were designed based on the dexterous manipulation theory. Finally, the effectiveness of the design method was experimentally validated. Findings A novel lightweight three-finger and nine-degree-of-freedom dexterous hand with force/position perception was designed. The proposed routing structure was shown to have the capability of mapping the relationship between the joint space and actuator space. The adaptive fingertip with an embedded force sensor can effectively increase the robustness of the grasping operation. Moreover, the dexterous hand can grasp various objects in different configurations and perform in-hand manipulation dexterously. Originality/value The dexterous hand design developed in this study is less complex and performs better in dexterous manipulation than previous designs.
科研通智能强力驱动
Strongly Powered by AbleSci AI